{"cells": [{"cell_type": "markdown", "id": "e97dbf01", "metadata": {"papermill": {"duration": 0.035787, "end_time": "2021-10-10T16:36:26.406495", "exception": false, "start_time": "2021-10-10T16:36:26.370708", "status": "completed"}, "tags": []}, "source": ["\n", "# Tutorial 12: Meta-Learning - Learning to Learn\n", "\n", "* **Author:** Phillip Lippe\n", "* **License:** CC BY-SA\n", "* **Generated:** 2021-10-10T18:35:50.818431\n", "\n", "In this tutorial, we will discuss algorithms that learn models which can quickly adapt to new classes and/or tasks with few samples.\n", "This area of machine learning is called _Meta-Learning_ aiming at \"learning to learn\".\n", "Learning from very few examples is a natural task for humans. In contrast to current deep learning models, we need to see only a few examples of a police car or firetruck to recognize them in daily traffic.\n", "This is crucial ability since in real-world application, it is rarely the case that the data stays static and does not change over time.\n", "For example, an object detection system for mobile phones trained on data from 2000 will have troubles detecting today's common mobile phones, and thus, needs to adapt to new data without excessive label effort.\n", "The optimization techniques we have discussed so far struggle with this because they only aim at obtaining a good performance on a test set that had similar data.\n", "However, what if the test set has classes that we do not have in the training set?\n", "Or what if we want to test the model on a completely different task?\n", "We will discuss and implement three common Meta-Learning algorithms for such situations.\n", "This notebook is part of a lecture series on Deep Learning at the University of Amsterdam.\n", "The full list of tutorials can be found at https://uvadlc-notebooks.rtfd.io.\n", "\n", "\n", "---\n", "Open in [{height=\"20px\" width=\"117px\"}](https://colab.research.google.com/github/PytorchLightning/lightning-tutorials/blob/publication/.notebooks/course_UvA-DL/12-meta-learning.ipynb)\n", "\n", "Give us a \u2b50 [on Github](https://www.github.com/PytorchLightning/pytorch-lightning/)\n", "| Check out [the documentation](https://pytorch-lightning.readthedocs.io/en/latest/)\n", "| Join us [on Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-pw5v393p-qRaDgEk24~EjiZNBpSQFgQ)"]}, {"cell_type": "markdown", "id": "89d6c708", "metadata": {"papermill": {"duration": 0.034571, "end_time": "2021-10-10T16:36:26.475148", "exception": false, "start_time": "2021-10-10T16:36:26.440577", "status": "completed"}, "tags": []}, "source": ["## Setup\n", "This notebook requires some packages besides pytorch-lightning."]}, {"cell_type": "code", "execution_count": 1, "id": "2350fea0", "metadata": {"colab": {}, "colab_type": "code", "execution": {"iopub.execute_input": "2021-10-10T16:36:26.546320Z", "iopub.status.busy": "2021-10-10T16:36:26.545801Z", "iopub.status.idle": "2021-10-10T16:36:26.547964Z", "shell.execute_reply": "2021-10-10T16:36:26.548348Z"}, "id": "LfrJLKPFyhsK", "lines_to_next_cell": 0, "papermill": {"duration": 0.039795, "end_time": "2021-10-10T16:36:26.548525", "exception": false, "start_time": "2021-10-10T16:36:26.508730", "status": "completed"}, "tags": []}, "outputs": [], "source": ["# ! pip install --quiet \"torch>=1.6, <1.9\" \"matplotlib\" \"torchmetrics>=0.3\" \"seaborn\" \"torchvision\" \"pytorch-lightning>=1.3\""]}, {"cell_type": "markdown", "id": "5bc75be2", "metadata": {"papermill": {"duration": 0.033967, "end_time": "2021-10-10T16:36:26.617046", "exception": false, "start_time": "2021-10-10T16:36:26.583079", "status": "completed"}, "tags": []}, "source": ["<div class=\"center-wrapper\"><div class=\"video-wrapper\"><iframe src=\"https://www.youtube.com/embed/035rkmT8FfE\" title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen></iframe></div></div>\n", "Meta-Learning offers solutions to these situations, and we will discuss three popular algorithms: __Prototypical Networks__ ([Snell et al., 2017](https://arxiv.org/pdf/1703.05175.pdf)), __Model-Agnostic Meta-Learning / MAML__ ([Finn et al., 2017](http://proceedings.mlr.press/v70/finn17a.html)), and __Proto-MAML__ ([Triantafillou et al., 2020](https://openreview.net/pdf?id=rkgAGAVKPr)).\n", "We will focus on the task of few-shot classification where the training and test set have distinct sets of classes.\n", "For instance, we would train the model on the binary classifications of cats-birds and flowers-bikes, but during test time, the model would need to learn from 4 examples each the difference between dogs and otters, two classes we have not seen during training (Figure credit - [Lilian Weng](https://lilianweng.github.io/lil-log/2018/11/30/meta-learning.html)).\n", "\n", "<center width=\"100%\"><img src=\"https://github.com/PyTorchLightning/lightning-tutorials/raw/main/course_UvA-DL/12-meta-learning/few-shot-classification.png\" width=\"800px\"></center>\n", "\n", "A different setup, which is very common in Reinforcement Learning and recently Natural Language Processing, is to aim at few-shot learning of a completely new task.\n", "For example, an robot agent that learned to run, jump and pick up boxes, should quickly adapt to collecting and stacking boxes.\n", "In NLP, we can think of a model which was trained sentiment classification, hatespeech detection and sarcasm classification, to adapt to classifying the emotion of a text.\n", "All methods we will discuss in this notebook can be easily applied to these settings since we only use a different definition of a 'task'.\n", "For few-shot classification, we consider a task to distinguish between $M$ novel classes.\n", "Here, we would not only have novel classes, but also a completely different dataset.\n", "\n", "First of all, let's start with importing our standard libraries. We will again be using PyTorch Lightning."]}, {"cell_type": "code", "execution_count": 2, "id": "a414f0fb", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:26.695087Z", "iopub.status.busy": "2021-10-10T16:36:26.694610Z", "iopub.status.idle": "2021-10-10T16:36:28.445235Z", "shell.execute_reply": "2021-10-10T16:36:28.444817Z"}, "papermill": {"duration": 1.794133, "end_time": "2021-10-10T16:36:28.445346", "exception": false, "start_time": "2021-10-10T16:36:26.651213", "status": "completed"}, "tags": []}, "outputs": [{"name": "stderr", "output_type": "stream", "text": ["/tmp/ipykernel_739/3072189054.py:29: DeprecationWarning: `set_matplotlib_formats` is deprecated since IPython 7.23, directly use `matplotlib_inline.backend_inline.set_matplotlib_formats()`\n", " set_matplotlib_formats(\"svg\", \"pdf\") # For export\n", "Global seed set to 42\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Device: cuda:0\n"]}, {"data": {"text/plain": ["<Figure size 432x288 with 0 Axes>"]}, "metadata": {}, "output_type": "display_data"}], "source": ["import json\n", "import os\n", "import random\n", "import urllib.request\n", "from collections import defaultdict\n", "from copy import deepcopy\n", "from statistics import mean, stdev\n", "from urllib.error import HTTPError\n", "\n", "import matplotlib\n", "import matplotlib.pyplot as plt\n", "import numpy as np\n", "import pytorch_lightning as pl\n", "import seaborn as sns\n", "import torch\n", "import torch.nn.functional as F\n", "import torch.optim as optim\n", "import torch.utils.data as data\n", "import torchvision\n", "from IPython.display import set_matplotlib_formats\n", "from PIL import Image\n", "from pytorch_lightning.callbacks import LearningRateMonitor, ModelCheckpoint\n", "from torchvision import transforms\n", "from torchvision.datasets import CIFAR100, SVHN\n", "from tqdm.auto import tqdm\n", "\n", "plt.set_cmap(\"cividis\")\n", "# %matplotlib inline\n", "set_matplotlib_formats(\"svg\", \"pdf\") # For export\n", "matplotlib.rcParams[\"lines.linewidth\"] = 2.0\n", "sns.reset_orig()\n", "\n", "# Import tensorboard\n", "# %load_ext tensorboard\n", "\n", "# Path to the folder where the datasets are/should be downloaded (e.g. CIFAR10)\n", "DATASET_PATH = os.environ.get(\"PATH_DATASETS\", \"data/\")\n", "# Path to the folder where the pretrained models are saved\n", "CHECKPOINT_PATH = os.environ.get(\"PATH_CHECKPOINT\", \"saved_models/MetaLearning/\")\n", "\n", "# Setting the seed\n", "pl.seed_everything(42)\n", "\n", "# Ensure that all operations are deterministic on GPU (if used) for reproducibility\n", "torch.backends.cudnn.determinstic = True\n", "torch.backends.cudnn.benchmark = False\n", "\n", "device = torch.device(\"cuda:0\") if torch.cuda.is_available() else torch.device(\"cpu\")\n", "print(\"Device:\", device)"]}, {"cell_type": "markdown", "id": "ce51286e", "metadata": {"papermill": {"duration": 0.034776, "end_time": "2021-10-10T16:36:28.518803", "exception": false, "start_time": "2021-10-10T16:36:28.484027", "status": "completed"}, "tags": []}, "source": ["Training the models in this notebook can take between 2 and 8 hours, and the evaluation time of some algorithms is in the span of couples of minutes.\n", "Hence, we download pre-trained models and results below."]}, {"cell_type": "code", "execution_count": 3, "id": "fddcdeaa", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:28.594883Z", "iopub.status.busy": "2021-10-10T16:36:28.594389Z", "iopub.status.idle": "2021-10-10T16:36:29.453405Z", "shell.execute_reply": "2021-10-10T16:36:29.452919Z"}, "papermill": {"duration": 0.899529, "end_time": "2021-10-10T16:36:29.453517", "exception": false, "start_time": "2021-10-10T16:36:28.553988", "status": "completed"}, "tags": []}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial16/ProtoNet.ckpt...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial16/ProtoMAML.ckpt...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial16/tensorboards/ProtoNet/events.out.tfevents.ProtoNet...\n", "Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial16/tensorboards/ProtoMAML/events.out.tfevents.ProtoMAML...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial16/protomaml_fewshot.json...\n", "Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial16/protomaml_svhn_fewshot.json...\n"]}], "source": ["# Github URL where saved models are stored for this tutorial\n", "base_url = \"https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial16/\"\n", "# Files to download\n", "pretrained_files = [\n", " \"ProtoNet.ckpt\",\n", " \"ProtoMAML.ckpt\",\n", " \"tensorboards/ProtoNet/events.out.tfevents.ProtoNet\",\n", " \"tensorboards/ProtoMAML/events.out.tfevents.ProtoMAML\",\n", " \"protomaml_fewshot.json\",\n", " \"protomaml_svhn_fewshot.json\",\n", "]\n", "# Create checkpoint path if it doesn't exist yet\n", "os.makedirs(CHECKPOINT_PATH, exist_ok=True)\n", "\n", "# For each file, check whether it already exists. If not, try downloading it.\n", "for file_name in pretrained_files:\n", " file_path = os.path.join(CHECKPOINT_PATH, file_name)\n", " if \"/\" in file_name:\n", " os.makedirs(file_path.rsplit(\"/\", 1)[0], exist_ok=True)\n", " if not os.path.isfile(file_path):\n", " file_url = base_url + file_name\n", " print(\"Downloading %s...\" % file_url)\n", " try:\n", " urllib.request.urlretrieve(file_url, file_path)\n", " except HTTPError as e:\n", " print(\n", " \"Something went wrong. Please try to download the file from the GDrive folder, or contact the author with the full output including the following error:\\n\",\n", " e,\n", " )"]}, {"cell_type": "markdown", "id": "96d108b7", "metadata": {"papermill": {"duration": 0.038624, "end_time": "2021-10-10T16:36:29.528397", "exception": false, "start_time": "2021-10-10T16:36:29.489773", "status": "completed"}, "tags": []}, "source": ["## Few-shot classification\n", "\n", "We start our implementation by discussing the dataset setup.\n", "In this notebook, we will use CIFAR100 which we have already seen in Tutorial 6.\n", "CIFAR100 has 100 classes each with 600 images of size $32\\times 32$ pixels.\n", "Instead of splitting the training, validation and test set over examples, we will split them over classes: we will use 80 classes for training, and 10 for validation and 10 for testing.\n", "Our overall goal is to obtain a model that can distinguish between the 10 test classes with seeing very little examples.\n", "First, let's load the dataset and visualize some examples."]}, {"cell_type": "code", "execution_count": 4, "id": "2a4a4c43", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:29.603641Z", "iopub.status.busy": "2021-10-10T16:36:29.603170Z", "iopub.status.idle": "2021-10-10T16:36:34.357455Z", "shell.execute_reply": "2021-10-10T16:36:34.357029Z"}, "papermill": {"duration": 4.793304, "end_time": "2021-10-10T16:36:34.357578", "exception": false, "start_time": "2021-10-10T16:36:29.564274", "status": "completed"}, "tags": []}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Downloading https://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz to /__w/1/s/.datasets/cifar-100-python.tar.gz\n"]}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "f523d40c013f4da7bc639dc9291509e8", "version_major": 2, "version_minor": 0}, "text/plain": [" 0%| | 0/169001437 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"name": "stdout", "output_type": "stream", "text": ["Extracting /__w/1/s/.datasets/cifar-100-python.tar.gz to /__w/1/s/.datasets\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Files already downloaded and verified\n"]}], "source": ["# Loading CIFAR100 dataset\n", "cifar_train_set = CIFAR100(root=DATASET_PATH, train=True, download=True, transform=transforms.ToTensor())\n", "cifar_test_set = CIFAR100(root=DATASET_PATH, train=False, download=True, transform=transforms.ToTensor())"]}, {"cell_type": "code", "execution_count": 5, "id": "89dcf2d2", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:34.438125Z", "iopub.status.busy": "2021-10-10T16:36:34.437648Z", "iopub.status.idle": "2021-10-10T16:36:34.627198Z", "shell.execute_reply": "2021-10-10T16:36:34.627588Z"}, "papermill": {"duration": 0.231715, "end_time": "2021-10-10T16:36:34.627730", "exception": false, "start_time": "2021-10-10T16:36:34.396015", "status": "completed"}, "tags": []}, "outputs": [{"data": {"application/pdf": "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\n", "image/svg+xml": ["<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n", "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n", " \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n", "<svg height=\"181.207445pt\" version=\"1.1\" viewBox=\"0 0 460.8 181.207445\" width=\"460.8pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n", " <metadata>\n", " <rdf:RDF xmlns:cc=\"http://creativecommons.org/ns#\" xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\">\n", " <cc:Work>\n", " <dc:type rdf:resource=\"http://purl.org/dc/dcmitype/StillImage\"/>\n", " <dc:date>2021-10-10T18:36:34.496593</dc:date>\n", " <dc:format>image/svg+xml</dc:format>\n", " <dc:creator>\n", " <cc:Agent>\n", " <dc:title>Matplotlib v3.4.3, https://matplotlib.org/</dc:title>\n", " </cc:Agent>\n", " </dc:creator>\n", " </cc:Work>\n", " </rdf:RDF>\n", " </metadata>\n", " <defs>\n", " <style type=\"text/css\">*{stroke-linecap:butt;stroke-linejoin:round;}</style>\n", " </defs>\n", " <g id=\"figure_1\">\n", " <g id=\"patch_1\">\n", " <path d=\"M 0 181.207445 \n", "L 460.8 181.207445 \n", "L 460.8 0 \n", "L 0 0 \n", "z\n", "\" style=\"fill:none;\"/>\n", " </g>\n", " <g id=\"axes_1\">\n", " <g clip-path=\"url(#p980563102a)\">\n", " <image height=\"152\" id=\"image7d6ee9c5a6\" transform=\"scale(1 -1)translate(0 -152)\" width=\"447\" x=\"7.2\" xlink:href=\"data:image/png;base64,\n", "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\" y=\"-22.007445\"/>\n", " </g>\n", " <g id=\"text_1\">\n", " <!-- Image examples of the CIFAR100 dataset -->\n", " <g transform=\"translate(106.216875 16.318125)scale(0.12 -0.12)\">\n", " <defs>\n", " <path d=\"M 628 4666 \n", "L 1259 4666 \n", "L 1259 0 \n", "L 628 0 \n", "L 628 4666 \n", "z\n", "\" id=\"DejaVuSans-49\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3328 2828 \n", "Q 3544 3216 3844 3400 \n", "Q 4144 3584 4550 3584 \n", "Q 5097 3584 5394 3201 \n", "Q 5691 2819 5691 2113 \n", "L 5691 0 \n", "L 5113 0 \n", "L 5113 2094 \n", "Q 5113 2597 4934 2840 \n", "Q 4756 3084 4391 3084 \n", "Q 3944 3084 3684 2787 \n", "Q 3425 2491 3425 1978 \n", "L 3425 0 \n", "L 2847 0 \n", "L 2847 2094 \n", "Q 2847 2600 2669 2842 \n", "Q 2491 3084 2119 3084 \n", "Q 1678 3084 1418 2786 \n", "Q 1159 2488 1159 1978 \n", "L 1159 0 \n", "L 581 0 \n", "L 581 3500 \n", "L 1159 3500 \n", "L 1159 2956 \n", "Q 1356 3278 1631 3431 \n", "Q 1906 3584 2284 3584 \n", "Q 2666 3584 2933 3390 \n", "Q 3200 3197 3328 2828 \n", "z\n", "\" id=\"DejaVuSans-6d\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2194 1759 \n", "Q 1497 1759 1228 1600 \n", "Q 959 1441 959 1056 \n", "Q 959 750 1161 570 \n", "Q 1363 391 1709 391 \n", "Q 2188 391 2477 730 \n", "Q 2766 1069 2766 1631 \n", "L 2766 1759 \n", "L 2194 1759 \n", "z\n", "M 3341 1997 \n", "L 3341 0 \n", "L 2766 0 \n", "L 2766 531 \n", "Q 2569 213 2275 61 \n", "Q 1981 -91 1556 -91 \n", "Q 1019 -91 701 211 \n", "Q 384 513 384 1019 \n", "Q 384 1609 779 1909 \n", "Q 1175 2209 1959 2209 \n", "L 2766 2209 \n", "L 2766 2266 \n", "Q 2766 2663 2505 2880 \n", "Q 2244 3097 1772 3097 \n", "Q 1472 3097 1187 3025 \n", "Q 903 2953 641 2809 \n", "L 641 3341 \n", "Q 956 3463 1253 3523 \n", "Q 1550 3584 1831 3584 \n", "Q 2591 3584 2966 3190 \n", "Q 3341 2797 3341 1997 \n", "z\n", "\" id=\"DejaVuSans-61\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2906 1791 \n", "Q 2906 2416 2648 2759 \n", "Q 2391 3103 1925 3103 \n", "Q 1463 3103 1205 2759 \n", "Q 947 2416 947 1791 \n", "Q 947 1169 1205 825 \n", "Q 1463 481 1925 481 \n", "Q 2391 481 2648 825 \n", "Q 2906 1169 2906 1791 \n", "z\n", "M 3481 434 \n", "Q 3481 -459 3084 -895 \n", "Q 2688 -1331 1869 -1331 \n", "Q 1566 -1331 1297 -1286 \n", "Q 1028 -1241 775 -1147 \n", "L 775 -588 \n", "Q 1028 -725 1275 -790 \n", "Q 1522 -856 1778 -856 \n", "Q 2344 -856 2625 -561 \n", "Q 2906 -266 2906 331 \n", "L 2906 616 \n", "Q 2728 306 2450 153 \n", "Q 2172 0 1784 0 \n", "Q 1141 0 747 490 \n", "Q 353 981 353 1791 \n", "Q 353 2603 747 3093 \n", "Q 1141 3584 1784 3584 \n", "Q 2172 3584 2450 3431 \n", "Q 2728 3278 2906 2969 \n", "L 2906 3500 \n", "L 3481 3500 \n", "L 3481 434 \n", "z\n", "\" id=\"DejaVuSans-67\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3597 1894 \n", "L 3597 1613 \n", "L 953 1613 \n", "Q 991 1019 1311 708 \n", "Q 1631 397 2203 397 \n", "Q 2534 397 2845 478 \n", "Q 3156 559 3463 722 \n", "L 3463 178 \n", "Q 3153 47 2828 -22 \n", "Q 2503 -91 2169 -91 \n", "Q 1331 -91 842 396 \n", "Q 353 884 353 1716 \n", "Q 353 2575 817 3079 \n", "Q 1281 3584 2069 3584 \n", "Q 2775 3584 3186 3129 \n", "Q 3597 2675 3597 1894 \n", "z\n", "M 3022 2063 \n", "Q 3016 2534 2758 2815 \n", "Q 2500 3097 2075 3097 \n", "Q 1594 3097 1305 2825 \n", "Q 1016 2553 972 2059 \n", "L 3022 2063 \n", "z\n", "\" id=\"DejaVuSans-65\" transform=\"scale(0.015625)\"/>\n", " <path id=\"DejaVuSans-20\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3513 3500 \n", "L 2247 1797 \n", "L 3578 0 \n", "L 2900 0 \n", "L 1881 1375 \n", "L 863 0 \n", "L 184 0 \n", "L 1544 1831 \n", "L 300 3500 \n", "L 978 3500 \n", "L 1906 2253 \n", "L 2834 3500 \n", "L 3513 3500 \n", "z\n", "\" id=\"DejaVuSans-78\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1159 525 \n", "L 1159 -1331 \n", "L 581 -1331 \n", "L 581 3500 \n", "L 1159 3500 \n", "L 1159 2969 \n", "Q 1341 3281 1617 3432 \n", "Q 1894 3584 2278 3584 \n", "Q 2916 3584 3314 3078 \n", "Q 3713 2572 3713 1747 \n", "Q 3713 922 3314 415 \n", "Q 2916 -91 2278 -91 \n", "Q 1894 -91 1617 61 \n", "Q 1341 213 1159 525 \n", "z\n", "M 3116 1747 \n", "Q 3116 2381 2855 2742 \n", "Q 2594 3103 2138 3103 \n", "Q 1681 3103 1420 2742 \n", "Q 1159 2381 1159 1747 \n", "Q 1159 1113 1420 752 \n", "Q 1681 391 2138 391 \n", "Q 2594 391 2855 752 \n", "Q 3116 1113 3116 1747 \n", "z\n", "\" id=\"DejaVuSans-70\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 603 4863 \n", "L 1178 4863 \n", "L 1178 0 \n", "L 603 0 \n", "L 603 4863 \n", "z\n", "\" id=\"DejaVuSans-6c\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2834 3397 \n", "L 2834 2853 \n", "Q 2591 2978 2328 3040 \n", "Q 2066 3103 1784 3103 \n", "Q 1356 3103 1142 2972 \n", "Q 928 2841 928 2578 \n", "Q 928 2378 1081 2264 \n", "Q 1234 2150 1697 2047 \n", "L 1894 2003 \n", "Q 2506 1872 2764 1633 \n", "Q 3022 1394 3022 966 \n", "Q 3022 478 2636 193 \n", "Q 2250 -91 1575 -91 \n", "Q 1294 -91 989 -36 \n", "Q 684 19 347 128 \n", "L 347 722 \n", "Q 666 556 975 473 \n", "Q 1284 391 1588 391 \n", "Q 1994 391 2212 530 \n", "Q 2431 669 2431 922 \n", "Q 2431 1156 2273 1281 \n", "Q 2116 1406 1581 1522 \n", "L 1381 1569 \n", "Q 847 1681 609 1914 \n", "Q 372 2147 372 2553 \n", "Q 372 3047 722 3315 \n", "Q 1072 3584 1716 3584 \n", "Q 2034 3584 2315 3537 \n", "Q 2597 3491 2834 3397 \n", "z\n", "\" id=\"DejaVuSans-73\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1959 3097 \n", "Q 1497 3097 1228 2736 \n", "Q 959 2375 959 1747 \n", "Q 959 1119 1226 758 \n", "Q 1494 397 1959 397 \n", "Q 2419 397 2687 759 \n", "Q 2956 1122 2956 1747 \n", "Q 2956 2369 2687 2733 \n", "Q 2419 3097 1959 3097 \n", "z\n", "M 1959 3584 \n", "Q 2709 3584 3137 3096 \n", "Q 3566 2609 3566 1747 \n", "Q 3566 888 3137 398 \n", "Q 2709 -91 1959 -91 \n", "Q 1206 -91 779 398 \n", "Q 353 888 353 1747 \n", "Q 353 2609 779 3096 \n", "Q 1206 3584 1959 3584 \n", "z\n", "\" id=\"DejaVuSans-6f\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2375 4863 \n", "L 2375 4384 \n", "L 1825 4384 \n", "Q 1516 4384 1395 4259 \n", "Q 1275 4134 1275 3809 \n", "L 1275 3500 \n", "L 2222 3500 \n", "L 2222 3053 \n", "L 1275 3053 \n", "L 1275 0 \n", "L 697 0 \n", "L 697 3053 \n", "L 147 3053 \n", "L 147 3500 \n", "L 697 3500 \n", "L 697 3744 \n", "Q 697 4328 969 4595 \n", "Q 1241 4863 1831 4863 \n", "L 2375 4863 \n", "z\n", "\" id=\"DejaVuSans-66\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1172 4494 \n", "L 1172 3500 \n", "L 2356 3500 \n", "L 2356 3053 \n", "L 1172 3053 \n", "L 1172 1153 \n", "Q 1172 725 1289 603 \n", "Q 1406 481 1766 481 \n", "L 2356 481 \n", "L 2356 0 \n", "L 1766 0 \n", "Q 1100 0 847 248 \n", "Q 594 497 594 1153 \n", "L 594 3053 \n", "L 172 3053 \n", "L 172 3500 \n", "L 594 3500 \n", "L 594 4494 \n", "L 1172 4494 \n", "z\n", "\" id=\"DejaVuSans-74\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3513 2113 \n", "L 3513 0 \n", "L 2938 0 \n", "L 2938 2094 \n", "Q 2938 2591 2744 2837 \n", "Q 2550 3084 2163 3084 \n", "Q 1697 3084 1428 2787 \n", "Q 1159 2491 1159 1978 \n", "L 1159 0 \n", "L 581 0 \n", "L 581 4863 \n", "L 1159 4863 \n", "L 1159 2956 \n", "Q 1366 3272 1645 3428 \n", "Q 1925 3584 2291 3584 \n", "Q 2894 3584 3203 3211 \n", "Q 3513 2838 3513 2113 \n", "z\n", "\" id=\"DejaVuSans-68\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 4122 4306 \n", "L 4122 3641 \n", "Q 3803 3938 3442 4084 \n", "Q 3081 4231 2675 4231 \n", "Q 1875 4231 1450 3742 \n", "Q 1025 3253 1025 2328 \n", "Q 1025 1406 1450 917 \n", "Q 1875 428 2675 428 \n", "Q 3081 428 3442 575 \n", "Q 3803 722 4122 1019 \n", "L 4122 359 \n", "Q 3791 134 3420 21 \n", "Q 3050 -91 2638 -91 \n", "Q 1578 -91 968 557 \n", "Q 359 1206 359 2328 \n", "Q 359 3453 968 4101 \n", "Q 1578 4750 2638 4750 \n", "Q 3056 4750 3426 4639 \n", "Q 3797 4528 4122 4306 \n", "z\n", "\" id=\"DejaVuSans-43\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 628 4666 \n", "L 3309 4666 \n", "L 3309 4134 \n", "L 1259 4134 \n", "L 1259 2759 \n", "L 3109 2759 \n", "L 3109 2228 \n", "L 1259 2228 \n", "L 1259 0 \n", "L 628 0 \n", "L 628 4666 \n", "z\n", "\" id=\"DejaVuSans-46\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2188 4044 \n", "L 1331 1722 \n", "L 3047 1722 \n", "L 2188 4044 \n", "z\n", "M 1831 4666 \n", "L 2547 4666 \n", "L 4325 0 \n", "L 3669 0 \n", "L 3244 1197 \n", "L 1141 1197 \n", "L 716 0 \n", "L 50 0 \n", "L 1831 4666 \n", "z\n", "\" id=\"DejaVuSans-41\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2841 2188 \n", "Q 3044 2119 3236 1894 \n", "Q 3428 1669 3622 1275 \n", "L 4263 0 \n", "L 3584 0 \n", "L 2988 1197 \n", "Q 2756 1666 2539 1819 \n", "Q 2322 1972 1947 1972 \n", "L 1259 1972 \n", "L 1259 0 \n", "L 628 0 \n", "L 628 4666 \n", "L 2053 4666 \n", "Q 2853 4666 3247 4331 \n", "Q 3641 3997 3641 3322 \n", "Q 3641 2881 3436 2590 \n", "Q 3231 2300 2841 2188 \n", "z\n", "M 1259 4147 \n", "L 1259 2491 \n", "L 2053 2491 \n", "Q 2509 2491 2742 2702 \n", "Q 2975 2913 2975 3322 \n", "Q 2975 3731 2742 3939 \n", "Q 2509 4147 2053 4147 \n", "L 1259 4147 \n", "z\n", "\" id=\"DejaVuSans-52\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 794 531 \n", "L 1825 531 \n", "L 1825 4091 \n", "L 703 3866 \n", "L 703 4441 \n", "L 1819 4666 \n", "L 2450 4666 \n", "L 2450 531 \n", "L 3481 531 \n", "L 3481 0 \n", "L 794 0 \n", "L 794 531 \n", "z\n", "\" id=\"DejaVuSans-31\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2034 4250 \n", "Q 1547 4250 1301 3770 \n", "Q 1056 3291 1056 2328 \n", "Q 1056 1369 1301 889 \n", "Q 1547 409 2034 409 \n", "Q 2525 409 2770 889 \n", "Q 3016 1369 3016 2328 \n", "Q 3016 3291 2770 3770 \n", "Q 2525 4250 2034 4250 \n", "z\n", "M 2034 4750 \n", "Q 2819 4750 3233 4129 \n", "Q 3647 3509 3647 2328 \n", "Q 3647 1150 3233 529 \n", "Q 2819 -91 2034 -91 \n", "Q 1250 -91 836 529 \n", "Q 422 1150 422 2328 \n", "Q 422 3509 836 4129 \n", "Q 1250 4750 2034 4750 \n", "z\n", "\" id=\"DejaVuSans-30\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2906 2969 \n", "L 2906 4863 \n", "L 3481 4863 \n", "L 3481 0 \n", "L 2906 0 \n", "L 2906 525 \n", "Q 2725 213 2448 61 \n", "Q 2172 -91 1784 -91 \n", "Q 1150 -91 751 415 \n", "Q 353 922 353 1747 \n", "Q 353 2572 751 3078 \n", "Q 1150 3584 1784 3584 \n", "Q 2172 3584 2448 3432 \n", "Q 2725 3281 2906 2969 \n", "z\n", "M 947 1747 \n", "Q 947 1113 1208 752 \n", "Q 1469 391 1925 391 \n", "Q 2381 391 2643 752 \n", "Q 2906 1113 2906 1747 \n", "Q 2906 2381 2643 2742 \n", "Q 2381 3103 1925 3103 \n", "Q 1469 3103 1208 2742 \n", "Q 947 2381 947 1747 \n", "z\n", "\" id=\"DejaVuSans-64\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-49\"/>\n", " <use x=\"29.492188\" xlink:href=\"#DejaVuSans-6d\"/>\n", " <use x=\"126.904297\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"188.183594\" xlink:href=\"#DejaVuSans-67\"/>\n", " <use x=\"251.660156\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"313.183594\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"344.970703\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"404.744141\" xlink:href=\"#DejaVuSans-78\"/>\n", " <use x=\"463.923828\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"525.203125\" xlink:href=\"#DejaVuSans-6d\"/>\n", " <use x=\"622.615234\" xlink:href=\"#DejaVuSans-70\"/>\n", " <use x=\"686.091797\" xlink:href=\"#DejaVuSans-6c\"/>\n", " <use x=\"713.875\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"775.398438\" xlink:href=\"#DejaVuSans-73\"/>\n", " <use x=\"827.498047\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"859.285156\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"920.466797\" xlink:href=\"#DejaVuSans-66\"/>\n", " <use x=\"955.671875\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"987.458984\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"1026.667969\" xlink:href=\"#DejaVuSans-68\"/>\n", " <use x=\"1090.046875\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"1151.570312\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"1183.357422\" xlink:href=\"#DejaVuSans-43\"/>\n", " <use x=\"1253.181641\" xlink:href=\"#DejaVuSans-49\"/>\n", " <use x=\"1282.673828\" xlink:href=\"#DejaVuSans-46\"/>\n", " <use x=\"1331.068359\" xlink:href=\"#DejaVuSans-41\"/>\n", " <use x=\"1399.476562\" xlink:href=\"#DejaVuSans-52\"/>\n", " <use x=\"1468.958984\" xlink:href=\"#DejaVuSans-31\"/>\n", " <use x=\"1532.582031\" xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"1596.205078\" xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"1659.828125\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"1691.615234\" xlink:href=\"#DejaVuSans-64\"/>\n", " <use x=\"1755.091797\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"1816.371094\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"1855.580078\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"1916.859375\" xlink:href=\"#DejaVuSans-73\"/>\n", " <use x=\"1968.958984\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"2030.482422\" xlink:href=\"#DejaVuSans-74\"/>\n", " </g>\n", " </g>\n", " </g>\n", " </g>\n", " <defs>\n", " <clipPath id=\"p980563102a\">\n", " <rect height=\"151.68932\" width=\"446.4\" x=\"7.2\" y=\"22.318125\"/>\n", " </clipPath>\n", " </defs>\n", "</svg>\n"], "text/plain": ["<Figure size 576x576 with 1 Axes>"]}, "metadata": {"needs_background": "light"}, "output_type": "display_data"}], "source": ["# Visualize some examples\n", "NUM_IMAGES = 12\n", "cifar_images = [cifar_train_set[np.random.randint(len(cifar_train_set))][0] for idx in range(NUM_IMAGES)]\n", "cifar_images = torch.stack(cifar_images, dim=0)\n", "img_grid = torchvision.utils.make_grid(cifar_images, nrow=6, normalize=True, pad_value=0.9)\n", "img_grid = img_grid.permute(1, 2, 0)\n", "\n", "plt.figure(figsize=(8, 8))\n", "plt.title(\"Image examples of the CIFAR100 dataset\")\n", "plt.imshow(img_grid)\n", "plt.axis(\"off\")\n", "plt.show()\n", "plt.close()"]}, {"cell_type": "markdown", "id": "6393f96b", "metadata": {"papermill": {"duration": 0.041466, "end_time": "2021-10-10T16:36:34.711913", "exception": false, "start_time": "2021-10-10T16:36:34.670447", "status": "completed"}, "tags": []}, "source": ["### Data preprocessing\n", "\n", "Next, we need to prepare the dataset in the training, validation and test split as mentioned before.\n", "The torchvision package gives us the training and test set as two separate dataset objects.\n", "The next code cells will merge the original training and test set, and then create the new train-val-test split."]}, {"cell_type": "code", "execution_count": 6, "id": "ce60f407", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:34.798013Z", "iopub.status.busy": "2021-10-10T16:36:34.797539Z", "iopub.status.idle": "2021-10-10T16:36:34.875295Z", "shell.execute_reply": "2021-10-10T16:36:34.875698Z"}, "papermill": {"duration": 0.122697, "end_time": "2021-10-10T16:36:34.875846", "exception": false, "start_time": "2021-10-10T16:36:34.753149", "status": "completed"}, "tags": []}, "outputs": [], "source": ["# Merging original training and test set\n", "cifar_all_images = np.concatenate([cifar_train_set.data, cifar_test_set.data], axis=0)\n", "cifar_all_targets = torch.LongTensor(cifar_train_set.targets + cifar_test_set.targets)"]}, {"cell_type": "markdown", "id": "3f939d72", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.040873, "end_time": "2021-10-10T16:36:34.959229", "exception": false, "start_time": "2021-10-10T16:36:34.918356", "status": "completed"}, "tags": []}, "source": ["To have an easier time handling the dataset, we define our own, simple dataset class below.\n", "It takes a set of images, labels/targets, and image transformations, and\n", "returns the corresponding images and labels element-wise."]}, {"cell_type": "code", "execution_count": 7, "id": "83d1fcac", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:35.051943Z", "iopub.status.busy": "2021-10-10T16:36:35.051455Z", "iopub.status.idle": "2021-10-10T16:36:35.053594Z", "shell.execute_reply": "2021-10-10T16:36:35.053130Z"}, "papermill": {"duration": 0.053299, "end_time": "2021-10-10T16:36:35.053692", "exception": false, "start_time": "2021-10-10T16:36:35.000393", "status": "completed"}, "tags": []}, "outputs": [], "source": ["class ImageDataset(data.Dataset):\n", " def __init__(self, imgs, targets, img_transform=None):\n", " \"\"\"\n", " Inputs:\n", " imgs - Numpy array of shape [N,32,32,3] containing all images.\n", " targets - PyTorch array of shape [N] containing all labels.\n", " img_transform - A torchvision transformation that should be applied\n", " to the images before returning. If none, no transformation\n", " is applied.\n", " \"\"\"\n", " super().__init__()\n", " self.img_transform = img_transform\n", " self.imgs = imgs\n", " self.targets = targets\n", "\n", " def __getitem__(self, idx):\n", " img, target = self.imgs[idx], self.targets[idx]\n", " img = Image.fromarray(img)\n", "\n", " if self.img_transform is not None:\n", " img = self.img_transform(img)\n", "\n", " return img, target\n", "\n", " def __len__(self):\n", " return self.imgs.shape[0]"]}, {"cell_type": "markdown", "id": "8afc6b05", "metadata": {"papermill": {"duration": 0.041697, "end_time": "2021-10-10T16:36:35.136827", "exception": false, "start_time": "2021-10-10T16:36:35.095130", "status": "completed"}, "tags": []}, "source": ["Now, we can create the class splits.\n", "We will assign the classes randomly to training, validation and test, and use a 80%-10%-10% split."]}, {"cell_type": "code", "execution_count": 8, "id": "5ff3abd6", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:35.223236Z", "iopub.status.busy": "2021-10-10T16:36:35.222768Z", "iopub.status.idle": "2021-10-10T16:36:35.226508Z", "shell.execute_reply": "2021-10-10T16:36:35.226037Z"}, "papermill": {"duration": 0.048464, "end_time": "2021-10-10T16:36:35.226609", "exception": false, "start_time": "2021-10-10T16:36:35.178145", "status": "completed"}, "tags": []}, "outputs": [{"name": "stderr", "output_type": "stream", "text": ["Global seed set to 0\n"]}], "source": ["pl.seed_everything(0) # Set seed for reproducibility\n", "classes = torch.randperm(100) # Returns random permutation of numbers 0 to 99\n", "train_classes, val_classes, test_classes = classes[:80], classes[80:90], classes[90:]"]}, {"cell_type": "markdown", "id": "32cdc6d7", "metadata": {"papermill": {"duration": 0.042958, "end_time": "2021-10-10T16:36:35.311335", "exception": false, "start_time": "2021-10-10T16:36:35.268377", "status": "completed"}, "tags": []}, "source": ["To get an intuition of the validation and test classes, we print the class names below:"]}, {"cell_type": "code", "execution_count": 9, "id": "3ba456f9", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:35.405497Z", "iopub.status.busy": "2021-10-10T16:36:35.405025Z", "iopub.status.idle": "2021-10-10T16:36:35.408515Z", "shell.execute_reply": "2021-10-10T16:36:35.408107Z"}, "papermill": {"duration": 0.052713, "end_time": "2021-10-10T16:36:35.408617", "exception": false, "start_time": "2021-10-10T16:36:35.355904", "status": "completed"}, "tags": []}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Validation classes: ['caterpillar', 'castle', 'skunk', 'ray', 'bus', 'motorcycle', 'keyboard', 'chimpanzee', 'possum', 'tiger']\n", "Test classes: ['kangaroo', 'crocodile', 'butterfly', 'shark', 'forest', 'pickup_truck', 'telephone', 'lion', 'worm', 'mushroom']\n"]}], "source": ["# Printing validation and test classes\n", "idx_to_class = {val: key for key, val in cifar_train_set.class_to_idx.items()}\n", "print(\"Validation classes:\", [idx_to_class[c.item()] for c in val_classes])\n", "print(\"Test classes:\", [idx_to_class[c.item()] for c in test_classes])"]}, {"cell_type": "markdown", "id": "ce1f7d09", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.041936, "end_time": "2021-10-10T16:36:35.493337", "exception": false, "start_time": "2021-10-10T16:36:35.451401", "status": "completed"}, "tags": []}, "source": ["As we can see, the classes have quite some variety and some classes might be easier to distinguish than others.\n", "For instance, in the test classes, 'pickup_truck' is the only vehicle while the classes 'mushroom', 'worm' and 'forest' might be harder to keep apart.\n", "Remember that we want to learn the classification of those ten classes from 80 other classes in our training set, and few examples from the actual test classes.\n", "We will experiment with the number of examples per class.\n", "\n", "Finally, we can create the training, validation and test dataset according to our split above.\n", "For this, we create dataset objects of our previously defined class `ImageDataset`."]}, {"cell_type": "code", "execution_count": 10, "id": "32f068d1", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:35.581555Z", "iopub.status.busy": "2021-10-10T16:36:35.581087Z", "iopub.status.idle": "2021-10-10T16:36:35.583171Z", "shell.execute_reply": "2021-10-10T16:36:35.582711Z"}, "papermill": {"duration": 0.04763, "end_time": "2021-10-10T16:36:35.583269", "exception": false, "start_time": "2021-10-10T16:36:35.535639", "status": "completed"}, "tags": []}, "outputs": [], "source": ["def dataset_from_labels(imgs, targets, class_set, **kwargs):\n", " class_mask = (targets[:, None] == class_set[None, :]).any(dim=-1)\n", " return ImageDataset(imgs=imgs[class_mask], targets=targets[class_mask], **kwargs)"]}, {"cell_type": "markdown", "id": "e8d4fb26", "metadata": {"papermill": {"duration": 0.041782, "end_time": "2021-10-10T16:36:35.667114", "exception": false, "start_time": "2021-10-10T16:36:35.625332", "status": "completed"}, "tags": []}, "source": ["As in our experiments before on CIFAR in Tutorial 5, 6 and 9, we normalize the dataset.\n", "Additionally, we use small augmentations during training to prevent overfitting."]}, {"cell_type": "code", "execution_count": 11, "id": "25bb398a", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:35.757452Z", "iopub.status.busy": "2021-10-10T16:36:35.756975Z", "iopub.status.idle": "2021-10-10T16:36:38.059891Z", "shell.execute_reply": "2021-10-10T16:36:38.059376Z"}, "papermill": {"duration": 2.350192, "end_time": "2021-10-10T16:36:38.060028", "exception": false, "start_time": "2021-10-10T16:36:35.709836", "status": "completed"}, "tags": []}, "outputs": [], "source": ["DATA_MEANS = (cifar_train_set.data / 255.0).mean(axis=(0, 1, 2))\n", "DATA_STD = (cifar_train_set.data / 255.0).std(axis=(0, 1, 2))\n", "\n", "test_transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize(DATA_MEANS, DATA_STD)])\n", "# For training, we add some augmentation.\n", "train_transform = transforms.Compose(\n", " [\n", " transforms.RandomHorizontalFlip(),\n", " transforms.RandomResizedCrop((32, 32), scale=(0.8, 1.0), ratio=(0.9, 1.1)),\n", " transforms.ToTensor(),\n", " transforms.Normalize(DATA_MEANS, DATA_STD),\n", " ]\n", ")\n", "\n", "train_set = dataset_from_labels(cifar_all_images, cifar_all_targets, train_classes, img_transform=train_transform)\n", "val_set = dataset_from_labels(cifar_all_images, cifar_all_targets, val_classes, img_transform=test_transform)\n", "test_set = dataset_from_labels(cifar_all_images, cifar_all_targets, test_classes, img_transform=test_transform)"]}, {"cell_type": "markdown", "id": "3456a8f9", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.042069, "end_time": "2021-10-10T16:36:38.145286", "exception": false, "start_time": "2021-10-10T16:36:38.103217", "status": "completed"}, "tags": []}, "source": ["### Data sampling\n", "\n", "The strategy of how to use the available training data for learning few-shot adaptation is crucial in meta-learning.\n", "All three algorithms that we discuss here have a similar idea: simulate few-shot learning during training.\n", "Specifically, at each training step, we randomly select a small number of classes, and sample a small number of examples for each class.\n", "This represents our few-shot training batch, which we also refer to as **support set**.\n", "Additionally, we sample a second set of examples from the same classes, and refer to this batch as **query set**.\n", "Our training objective is to classify the query set correctly from seeing the support set and its corresponding labels.\n", "The main difference between our three methods (ProtoNet, MAML, and Proto-MAML) is in how they use the support set to adapt to the training classes.\n", "\n", "This subsection summarizes the code that is needed to create such training batches.\n", "In PyTorch, we can specify the data sampling procedure by so-called `Sampler` ([documentation](https://pytorch.org/docs/stable/data.html#data-loading-order-and-sampler)).\n", "Samplers are iteratable objects that return indices in the order in which the data elements should be sampled.\n", "In our previous notebooks, we usually used the option `shuffle=True` in the `data.DataLoader` objects which creates a sampler returning the data indices in a random order.\n", "Here, we focus on samplers that return batches of indices that correspond to support and query set batches.\n", "Below, we implement such a sampler."]}, {"cell_type": "code", "execution_count": 12, "id": "c0bad2d9", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:38.237449Z", "iopub.status.busy": "2021-10-10T16:36:38.236947Z", "iopub.status.idle": "2021-10-10T16:36:38.243012Z", "shell.execute_reply": "2021-10-10T16:36:38.242609Z"}, "papermill": {"duration": 0.055637, "end_time": "2021-10-10T16:36:38.243112", "exception": false, "start_time": "2021-10-10T16:36:38.187475", "status": "completed"}, "tags": []}, "outputs": [], "source": ["class FewShotBatchSampler:\n", " def __init__(self, dataset_targets, N_way, K_shot, include_query=False, shuffle=True, shuffle_once=False):\n", " \"\"\"\n", " Inputs:\n", " dataset_targets - PyTorch tensor of the labels of the data elements.\n", " N_way - Number of classes to sample per batch.\n", " K_shot - Number of examples to sample per class in the batch.\n", " include_query - If True, returns batch of size N_way*K_shot*2, which\n", " can be split into support and query set. Simplifies\n", " the implementation of sampling the same classes but\n", " distinct examples for support and query set.\n", " shuffle - If True, examples and classes are newly shuffled in each\n", " iteration (for training)\n", " shuffle_once - If True, examples and classes are shuffled once in\n", " the beginning, but kept constant across iterations\n", " (for validation)\n", " \"\"\"\n", " super().__init__()\n", " self.dataset_targets = dataset_targets\n", " self.N_way = N_way\n", " self.K_shot = K_shot\n", " self.shuffle = shuffle\n", " self.include_query = include_query\n", " if self.include_query:\n", " self.K_shot *= 2\n", " self.batch_size = self.N_way * self.K_shot # Number of overall images per batch\n", "\n", " # Organize examples by class\n", " self.classes = torch.unique(self.dataset_targets).tolist()\n", " self.num_classes = len(self.classes)\n", " self.indices_per_class = {}\n", " self.batches_per_class = {} # Number of K-shot batches that each class can provide\n", " for c in self.classes:\n", " self.indices_per_class[c] = torch.where(self.dataset_targets == c)[0]\n", " self.batches_per_class[c] = self.indices_per_class[c].shape[0] // self.K_shot\n", "\n", " # Create a list of classes from which we select the N classes per batch\n", " self.iterations = sum(self.batches_per_class.values()) // self.N_way\n", " self.class_list = [c for c in self.classes for _ in range(self.batches_per_class[c])]\n", " if shuffle_once or self.shuffle:\n", " self.shuffle_data()\n", " else:\n", " # For testing, we iterate over classes instead of shuffling them\n", " sort_idxs = [\n", " i + p * self.num_classes for i, c in enumerate(self.classes) for p in range(self.batches_per_class[c])\n", " ]\n", " self.class_list = np.array(self.class_list)[np.argsort(sort_idxs)].tolist()\n", "\n", " def shuffle_data(self):\n", " # Shuffle the examples per class\n", " for c in self.classes:\n", " perm = torch.randperm(self.indices_per_class[c].shape[0])\n", " self.indices_per_class[c] = self.indices_per_class[c][perm]\n", " # Shuffle the class list from which we sample. Note that this way of shuffling\n", " # does not prevent to choose the same class twice in a batch. However, for\n", " # training and validation, this is not a problem.\n", " random.shuffle(self.class_list)\n", "\n", " def __iter__(self):\n", " # Shuffle data\n", " if self.shuffle:\n", " self.shuffle_data()\n", "\n", " # Sample few-shot batches\n", " start_index = defaultdict(int)\n", " for it in range(self.iterations):\n", " class_batch = self.class_list[it * self.N_way : (it + 1) * self.N_way] # Select N classes for the batch\n", " index_batch = []\n", " for c in class_batch: # For each class, select the next K examples and add them to the batch\n", " index_batch.extend(self.indices_per_class[c][start_index[c] : start_index[c] + self.K_shot])\n", " start_index[c] += self.K_shot\n", " if self.include_query: # If we return support+query set, sort them so that they are easy to split\n", " index_batch = index_batch[::2] + index_batch[1::2]\n", " yield index_batch\n", "\n", " def __len__(self):\n", " return self.iterations"]}, {"cell_type": "markdown", "id": "966baf43", "metadata": {"papermill": {"duration": 0.041981, "end_time": "2021-10-10T16:36:38.327241", "exception": false, "start_time": "2021-10-10T16:36:38.285260", "status": "completed"}, "tags": []}, "source": ["Now, we can create our intended data loaders by passing an object of `FewShotBatchSampler` as `batch_sampler=...` input to the PyTorch data loader object.\n", "For our experiments, we will use a 5-class 4-shot training setting.\n", "This means that each support set contains 5 classes with 4 examples each, i.e., 20 images overall.\n", "Usually, it is good to keep the number of shots equal to the number that you aim to test on.\n", "However, we will experiment later with different number of shots, and hence, we pick 4 as a compromise for now.\n", "To get the best performing model, it is recommended to consider the\n", "number of training shots as hyperparameter in a grid search."]}, {"cell_type": "code", "execution_count": 13, "id": "6e5eee4a", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:38.415592Z", "iopub.status.busy": "2021-10-10T16:36:38.415120Z", "iopub.status.idle": "2021-10-10T16:36:38.437251Z", "shell.execute_reply": "2021-10-10T16:36:38.436842Z"}, "papermill": {"duration": 0.068099, "end_time": "2021-10-10T16:36:38.437354", "exception": false, "start_time": "2021-10-10T16:36:38.369255", "status": "completed"}, "tags": []}, "outputs": [], "source": ["N_WAY = 5\n", "K_SHOT = 4\n", "train_data_loader = data.DataLoader(\n", " train_set,\n", " batch_sampler=FewShotBatchSampler(train_set.targets, include_query=True, N_way=N_WAY, K_shot=K_SHOT, shuffle=True),\n", " num_workers=4,\n", ")\n", "val_data_loader = data.DataLoader(\n", " val_set,\n", " batch_sampler=FewShotBatchSampler(\n", " val_set.targets, include_query=True, N_way=N_WAY, K_shot=K_SHOT, shuffle=False, shuffle_once=True\n", " ),\n", " num_workers=4,\n", ")"]}, {"cell_type": "markdown", "id": "3105a10e", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.042422, "end_time": "2021-10-10T16:36:38.521966", "exception": false, "start_time": "2021-10-10T16:36:38.479544", "status": "completed"}, "tags": []}, "source": ["For simplicity, we implemented the sampling of a support and query set as sampling a support set with twice the number of examples.\n", "After sampling a batch from the data loader, we need to split it into a support and query set.\n", "We can summarize this step in the following function:"]}, {"cell_type": "code", "execution_count": 14, "id": "928a254e", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:38.609800Z", "iopub.status.busy": "2021-10-10T16:36:38.608312Z", "iopub.status.idle": "2021-10-10T16:36:38.611864Z", "shell.execute_reply": "2021-10-10T16:36:38.611397Z"}, "papermill": {"duration": 0.048021, "end_time": "2021-10-10T16:36:38.611980", "exception": false, "start_time": "2021-10-10T16:36:38.563959", "status": "completed"}, "tags": []}, "outputs": [], "source": ["def split_batch(imgs, targets):\n", " support_imgs, query_imgs = imgs.chunk(2, dim=0)\n", " support_targets, query_targets = targets.chunk(2, dim=0)\n", " return support_imgs, query_imgs, support_targets, query_targets"]}, {"cell_type": "markdown", "id": "ac8356fb", "metadata": {"papermill": {"duration": 0.041927, "end_time": "2021-10-10T16:36:38.696240", "exception": false, "start_time": "2021-10-10T16:36:38.654313", "status": "completed"}, "tags": []}, "source": ["Finally, to ensure that our implementation of the data sampling process is correct, we can sample a batch and visualize its support and query set.\n", "What we would like to see is that the support and query set have the same classes, but distinct examples."]}, {"cell_type": "code", "execution_count": 15, "id": "18340de4", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:38.786640Z", "iopub.status.busy": "2021-10-10T16:36:38.786168Z", "iopub.status.idle": "2021-10-10T16:36:39.045016Z", "shell.execute_reply": "2021-10-10T16:36:39.044567Z"}, "papermill": {"duration": 0.306369, "end_time": "2021-10-10T16:36:39.045134", "exception": false, "start_time": "2021-10-10T16:36:38.738765", "status": "completed"}, "tags": []}, "outputs": [], "source": ["imgs, targets = next(iter(val_data_loader)) # We use the validation set since it does not apply augmentations\n", "support_imgs, query_imgs, _, _ = split_batch(imgs, targets)\n", "support_grid = torchvision.utils.make_grid(support_imgs, nrow=K_SHOT, normalize=True, pad_value=0.9)\n", "support_grid = support_grid.permute(1, 2, 0)\n", "query_grid = torchvision.utils.make_grid(query_imgs, nrow=K_SHOT, normalize=True, pad_value=0.9)\n", "query_grid = query_grid.permute(1, 2, 0)\n", "\n", "fig, ax = plt.subplots(1, 2, figsize=(8, 5))\n", "ax[0].imshow(support_grid)\n", "ax[0].set_title(\"Support set\")\n", "ax[0].axis(\"off\")\n", "ax[1].imshow(query_grid)\n", "ax[1].set_title(\"Query set\")\n", "ax[1].axis(\"off\")\n", "fig.suptitle(\"Few Shot Batch\", weight=\"bold\")\n", "fig.show()\n", "plt.close(fig)"]}, {"cell_type": "markdown", "id": "06b51e8e", "metadata": {"papermill": {"duration": 0.042585, "end_time": "2021-10-10T16:36:39.130534", "exception": false, "start_time": "2021-10-10T16:36:39.087949", "status": "completed"}, "tags": []}, "source": ["As we can see, the support and query set have the same five classes, but different examples.\n", "The models will be tasked to classify the examples in the query set by learning from the support set and its labels.\n", "With the data sampling in place, we can now start to implement our first meta-learning model: Prototypical Networks."]}, {"cell_type": "markdown", "id": "40315428", "metadata": {"papermill": {"duration": 0.042341, "end_time": "2021-10-10T16:36:39.214888", "exception": false, "start_time": "2021-10-10T16:36:39.172547", "status": "completed"}, "tags": []}, "source": ["## Prototypical Networks\n", "\n", "<div class=\"center-wrapper\"><div class=\"video-wrapper\"><iframe src=\"https://www.youtube.com/embed/LhZGPOtTd_Y\" title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen></iframe></div></div>"]}, {"cell_type": "markdown", "id": "e32fdcd0", "metadata": {"papermill": {"duration": 0.042438, "end_time": "2021-10-10T16:36:39.299755", "exception": false, "start_time": "2021-10-10T16:36:39.257317", "status": "completed"}, "tags": []}, "source": ["The Prototypical Network, or ProtoNet for short, is a metric-based meta-learning algorithm which operates similar to a nearest neighbor classification.\n", "Metric-based meta-learning methods classify a new example $\\mathbf{x}$ based on some distance function $d_{\\varphi}$ between $x$ and all elements in the support set.\n", "ProtoNets implements this idea with the concept of prototypes in a learned feature space.\n", "First, ProtoNet uses an embedding function $f_{\\theta}$ to encode each input in the support set into a $L$-dimensional feature vector.\n", "Next, for each class $c$, we collect the feature vectors of all examples with label $c$, and average their feature vectors.\n", "Formally, we can define this as:\n", "\n", "$$\\mathbf{v}_c=\\frac{1}{|S_c|}\\sum_{(\\mathbf{x}_i,y_i)\\in S_c}f_{\\theta}(\\mathbf{x}_i)$$\n", "\n", "where $S_c$ is the part of the support set $S$ for which $y_i=c$, and $\\mathbf{v}_c$ represents the _prototype_ of class $c$.\n", "The prototype calculation is visualized below for a 2-dimensional feature space and 3 classes (Figure credit - [Snell et al.](https://arxiv.org/pdf/1703.05175.pdf)).\n", "The colored dots represent encoded support elements with color-corresponding class label, and the black dots next to the class label are the averaged prototypes.\n", "\n", "<center width=\"100%\"><img src=\"https://github.com/PyTorchLightning/lightning-tutorials/raw/main/course_UvA-DL/12-meta-learning/protonet_classification.svg\" width=\"300px\"></center>\n", "\n", "Based on these prototypes, we want to classify a new example.\n", "Remember that since we want to learn the encoding function $f_{\\theta}$, this classification must be differentiable and hence, we need to define a probability distribution across classes.\n", "For this, we will make use of the distance function $d_{\\varphi}$: the closer a new example $\\mathbf{x}$ is to a prototype $\\mathbf{v}_c$, the higher the probability for $\\mathbf{x}$ belonging to class $c$.\n", "Formally, we can simply use a softmax over the distances of $\\mathbf{x}$ to all class prototypes:\n", "\n", "$$p(y=c\\vert\\mathbf{x})=\\text{softmax}(-d_{\\varphi}(f_{\\theta}(\\mathbf{x}), \\mathbf{v}_c))=\\frac{\\exp\\left(-d_{\\varphi}(f_{\\theta}(\\mathbf{x}), \\mathbf{v}_c)\\right)}{\\sum_{c'\\in \\mathcal{C}}\\exp\\left(-d_{\\varphi}(f_{\\theta}(\\mathbf{x}), \\mathbf{v}_{c'})\\right)}$$\n", "\n", "Note that the negative sign is necessary since we want to increase the probability for close-by vectors and have a low probability for distant vectors.\n", "We train the network $f_{\\theta}$ based on the cross entropy error of the training query set examples.\n", "Thereby, the gradient flows through both the prototypes $\\mathbf{v}_c$ and the query set encodings $f_{\\theta}(\\mathbf{x})$.\n", "For the distance function $d_{\\varphi}$, we can choose any function as long as it is differentiable with respect to both of its inputs.\n", "The most common function, which we also use here, is the squared\n", "euclidean distance, but there has been several works on different\n", "distance functions as well."]}, {"cell_type": "markdown", "id": "d400bfc2", "metadata": {"papermill": {"duration": 0.042184, "end_time": "2021-10-10T16:36:39.384014", "exception": false, "start_time": "2021-10-10T16:36:39.341830", "status": "completed"}, "tags": []}, "source": ["### ProtoNet implementation"]}, {"cell_type": "markdown", "id": "a10ef367", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.042386, "end_time": "2021-10-10T16:36:39.468678", "exception": false, "start_time": "2021-10-10T16:36:39.426292", "status": "completed"}, "tags": []}, "source": ["Now that we know how a ProtoNet works in principle, let's look at how we can apply to our specific problem of few-shot image classification, and implement it below.\n", "First, we need to define the encoder function $f_{\\theta}$.\n", "Since we work with CIFAR images, we can take a look back at Tutorial 5 where we compared common Computer Vision architectures, and choose one of the best performing ones.\n", "Here, we go with a DenseNet since it is in general more parameter efficient than ResNet.\n", "Luckily, we do not need to implement DenseNet ourselves again and can rely on torchvision's model package instead.\n", "We use common hyperparameters of 64 initial feature channels, add 32 per block, and use a bottleneck size of 64 (i.e. 2 times the growth rate).\n", "We use 4 stages of 6 layers each, which results in overall about 1 million parameters.\n", "Note that the torchvision package assumes that the last layer is used for classification and hence calls its output size `num_classes`.\n", "However, we can instead just use it as the feature space of ProtoNet, and choose an arbitrary dimensionality.\n", "We will use the same network for other algorithms in this notebook to ensure a fair comparison."]}, {"cell_type": "code", "execution_count": 16, "id": "2ba373cc", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:39.567463Z", "iopub.status.busy": "2021-10-10T16:36:39.566989Z", "iopub.status.idle": "2021-10-10T16:36:39.569062Z", "shell.execute_reply": "2021-10-10T16:36:39.568593Z"}, "lines_to_next_cell": 2, "papermill": {"duration": 0.056702, "end_time": "2021-10-10T16:36:39.569165", "exception": false, "start_time": "2021-10-10T16:36:39.512463", "status": "completed"}, "tags": []}, "outputs": [], "source": ["def get_convnet(output_size):\n", " convnet = torchvision.models.DenseNet(\n", " growth_rate=32,\n", " block_config=(6, 6, 6, 6),\n", " bn_size=2,\n", " num_init_features=64,\n", " num_classes=output_size, # Output dimensionality\n", " )\n", " return convnet"]}, {"cell_type": "markdown", "id": "50da6f0b", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.042572, "end_time": "2021-10-10T16:36:39.654722", "exception": false, "start_time": "2021-10-10T16:36:39.612150", "status": "completed"}, "tags": []}, "source": ["Next, we can look at implementing ProtoNet.\n", "We will define it as PyTorch Lightning module to use all functionalities of PyTorch Lightning.\n", "The first step during training is to encode all images in a batch with our network.\n", "Next, we calculate the class prototypes from the support set (function `calculate_prototypes`), and classify the query set examples according to the prototypes (function `classify_feats`).\n", "Keep in mind that we use the data sampling described before, such that the support and query set are stacked together in the batch.\n", "Thus, we use our previously defined function `split_batch` to split them apart.\n", "The full code can be found below."]}, {"cell_type": "code", "execution_count": 17, "id": "08c3adca", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:39.751136Z", "iopub.status.busy": "2021-10-10T16:36:39.750647Z", "iopub.status.idle": "2021-10-10T16:36:39.752752Z", "shell.execute_reply": "2021-10-10T16:36:39.752285Z"}, "lines_to_next_cell": 2, "papermill": {"duration": 0.055843, "end_time": "2021-10-10T16:36:39.752853", "exception": false, "start_time": "2021-10-10T16:36:39.697010", "status": "completed"}, "tags": []}, "outputs": [], "source": ["class ProtoNet(pl.LightningModule):\n", " def __init__(self, proto_dim, lr):\n", " \"\"\"Inputs.\n", "\n", " proto_dim - Dimensionality of prototype feature space\n", " lr - Learning rate of Adam optimizer\n", " \"\"\"\n", " super().__init__()\n", " self.save_hyperparameters()\n", " self.model = get_convnet(output_size=self.hparams.proto_dim)\n", "\n", " def configure_optimizers(self):\n", " optimizer = optim.AdamW(self.parameters(), lr=self.hparams.lr)\n", " scheduler = optim.lr_scheduler.MultiStepLR(optimizer, milestones=[140, 180], gamma=0.1)\n", " return [optimizer], [scheduler]\n", "\n", " @staticmethod\n", " def calculate_prototypes(features, targets):\n", " # Given a stack of features vectors and labels, return class prototypes\n", " # features - shape [N, proto_dim], targets - shape [N]\n", " classes, _ = torch.unique(targets).sort() # Determine which classes we have\n", " prototypes = []\n", " for c in classes:\n", " p = features[torch.where(targets == c)[0]].mean(dim=0) # Average class feature vectors\n", " prototypes.append(p)\n", " prototypes = torch.stack(prototypes, dim=0)\n", " # Return the 'classes' tensor to know which prototype belongs to which class\n", " return prototypes, classes\n", "\n", " def classify_feats(self, prototypes, classes, feats, targets):\n", " # Classify new examples with prototypes and return classification error\n", " dist = torch.pow(prototypes[None, :] - feats[:, None], 2).sum(dim=2) # Squared euclidean distance\n", " preds = F.log_softmax(-dist, dim=1)\n", " labels = (classes[None, :] == targets[:, None]).long().argmax(dim=-1)\n", " acc = (preds.argmax(dim=1) == labels).float().mean()\n", " return preds, labels, acc\n", "\n", " def calculate_loss(self, batch, mode):\n", " # Determine training loss for a given support and query set\n", " imgs, targets = batch\n", " features = self.model(imgs) # Encode all images of support and query set\n", " support_feats, query_feats, support_targets, query_targets = split_batch(features, targets)\n", " prototypes, classes = ProtoNet.calculate_prototypes(support_feats, support_targets)\n", " preds, labels, acc = self.classify_feats(prototypes, classes, query_feats, query_targets)\n", " loss = F.cross_entropy(preds, labels)\n", "\n", " self.log(\"%s_loss\" % mode, loss)\n", " self.log(\"%s_acc\" % mode, acc)\n", " return loss\n", "\n", " def training_step(self, batch, batch_idx):\n", " return self.calculate_loss(batch, mode=\"train\")\n", "\n", " def validation_step(self, batch, batch_idx):\n", " self.calculate_loss(batch, mode=\"val\")"]}, {"cell_type": "markdown", "id": "1d28cde2", "metadata": {"papermill": {"duration": 0.042403, "end_time": "2021-10-10T16:36:39.837555", "exception": false, "start_time": "2021-10-10T16:36:39.795152", "status": "completed"}, "tags": []}, "source": ["For validation, we use the same principle as training and sample support and query sets from the hold-out 10 classes.\n", "However, this gives us noisy scores depending on which query sets are chosen to which support sets.\n", "This is why we will use a different strategy during testing.\n", "For validation, our training strategy is sufficient since it is much\n", "faster than testing, and gives a good estimate of the training\n", "generalization as long as we keep the support-query sets constant across\n", "validation iterations."]}, {"cell_type": "markdown", "id": "02222c05", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.042841, "end_time": "2021-10-10T16:36:39.923166", "exception": false, "start_time": "2021-10-10T16:36:39.880325", "status": "completed"}, "tags": []}, "source": ["### Training\n", "\n", "After implementing the model, we can already start training it.\n", "We use our common PyTorch Lightning training function, and train the model for 200 epochs.\n", "The training function takes `model_class` as input argument, i.e. the\n", "PyTorch Lightning module class that should be trained, since we will\n", "reuse this function for other algorithms as well."]}, {"cell_type": "code", "execution_count": 18, "id": "76c40dce", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:40.014200Z", "iopub.status.busy": "2021-10-10T16:36:40.013719Z", "iopub.status.idle": "2021-10-10T16:36:40.015817Z", "shell.execute_reply": "2021-10-10T16:36:40.015348Z"}, "papermill": {"duration": 0.050208, "end_time": "2021-10-10T16:36:40.015917", "exception": false, "start_time": "2021-10-10T16:36:39.965709", "status": "completed"}, "tags": []}, "outputs": [], "source": ["def train_model(model_class, train_loader, val_loader, **kwargs):\n", " trainer = pl.Trainer(\n", " default_root_dir=os.path.join(CHECKPOINT_PATH, model_class.__name__),\n", " gpus=1 if str(device) == \"cuda:0\" else 0,\n", " max_epochs=200,\n", " callbacks=[\n", " ModelCheckpoint(save_weights_only=True, mode=\"max\", monitor=\"val_acc\"),\n", " LearningRateMonitor(\"epoch\"),\n", " ],\n", " progress_bar_refresh_rate=0,\n", " )\n", " trainer.logger._default_hp_metric = None\n", "\n", " # Check whether pretrained model exists. If yes, load it and skip training\n", " pretrained_filename = os.path.join(CHECKPOINT_PATH, model_class.__name__ + \".ckpt\")\n", " if os.path.isfile(pretrained_filename):\n", " print(\"Found pretrained model at %s, loading...\" % pretrained_filename)\n", " # Automatically loads the model with the saved hyperparameters\n", " model = model_class.load_from_checkpoint(pretrained_filename)\n", " else:\n", " pl.seed_everything(42) # To be reproducable\n", " model = model_class(**kwargs)\n", " trainer.fit(model, train_loader, val_loader)\n", " model = model_class.load_from_checkpoint(\n", " trainer.checkpoint_callback.best_model_path\n", " ) # Load best checkpoint after training\n", "\n", " return model"]}, {"cell_type": "markdown", "id": "6bd74652", "metadata": {"papermill": {"duration": 0.043123, "end_time": "2021-10-10T16:36:40.102077", "exception": false, "start_time": "2021-10-10T16:36:40.058954", "status": "completed"}, "tags": []}, "source": ["Below is the training call for our ProtoNet.\n", "We use a 64-dimensional feature space.\n", "Larger feature spaces showed to give noisier results since the squared euclidean distance becomes proportionally larger in expectation, and smaller feature spaces might not allow for enough flexibility.\n", "We recommend to load the pre-trained model here at first, but feel free\n", "to play around with the hyperparameters yourself."]}, {"cell_type": "code", "execution_count": 19, "id": "91cae9d3", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:40.192927Z", "iopub.status.busy": "2021-10-10T16:36:40.192456Z", "iopub.status.idle": "2021-10-10T16:36:40.257180Z", "shell.execute_reply": "2021-10-10T16:36:40.256698Z"}, "papermill": {"duration": 0.1128, "end_time": "2021-10-10T16:36:40.257291", "exception": false, "start_time": "2021-10-10T16:36:40.144491", "status": "completed"}, "tags": []}, "outputs": [{"name": "stderr", "output_type": "stream", "text": ["GPU available: True, used: True\n"]}, {"name": "stderr", "output_type": "stream", "text": ["TPU available: False, using: 0 TPU cores\n"]}, {"name": "stderr", "output_type": "stream", "text": ["IPU available: False, using: 0 IPUs\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Found pretrained model at saved_models/MetaLearning/ProtoNet.ckpt, loading...\n"]}], "source": ["protonet_model = train_model(\n", " ProtoNet, proto_dim=64, lr=2e-4, train_loader=train_data_loader, val_loader=val_data_loader\n", ")"]}, {"cell_type": "markdown", "id": "92207f47", "metadata": {"papermill": {"duration": 0.043516, "end_time": "2021-10-10T16:36:40.344935", "exception": false, "start_time": "2021-10-10T16:36:40.301419", "status": "completed"}, "tags": []}, "source": ["We can also take a closer look at the TensorBoard below."]}, {"cell_type": "code", "execution_count": 20, "id": "7b2883ee", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:40.435675Z", "iopub.status.busy": "2021-10-10T16:36:40.435210Z", "iopub.status.idle": "2021-10-10T16:36:40.437301Z", "shell.execute_reply": "2021-10-10T16:36:40.436898Z"}, "papermill": {"duration": 0.048812, "end_time": "2021-10-10T16:36:40.437398", "exception": false, "start_time": "2021-10-10T16:36:40.388586", "status": "completed"}, "tags": []}, "outputs": [], "source": ["# Opens tensorboard in notebook. Adjust the path to your CHECKPOINT_PATH if needed\n", "# # %tensorboard --logdir ../saved_models/tutorial16/tensorboards/ProtoNet/"]}, {"cell_type": "markdown", "id": "a96395e2", "metadata": {"papermill": {"duration": 0.043172, "end_time": "2021-10-10T16:36:40.524550", "exception": false, "start_time": "2021-10-10T16:36:40.481378", "status": "completed"}, "tags": []}, "source": ["<center width=\"100%\"><img src=\"https://github.com/PyTorchLightning/lightning-tutorials/raw/main/course_UvA-DL/12-meta-learning/tensorboard_screenshot_ProtoNet.png\" width=\"1100px\"></center>\n", "\n", "In contrast to standard supervised learning, we see that ProtoNet does not overfit as much as we would expect.\n", "The validation accuracy is of course lower than the average training, but the training loss does not stick close to zero.\n", "This is because no training batch is as the other, and we also mix new examples in the support set and query set.\n", "This gives us slightly different prototypes in every iteration, and makes it harder for the network to fully overfit."]}, {"cell_type": "markdown", "id": "fe724d6e", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.043726, "end_time": "2021-10-10T16:36:40.611913", "exception": false, "start_time": "2021-10-10T16:36:40.568187", "status": "completed"}, "tags": []}, "source": ["### Testing\n", "\n", "Our goal of meta-learning is to obtain a model that can quickly adapt to a new task, or in this case, new classes to distinguish between.\n", "To test this, we will use our trained ProtoNet and adapt it to the 10 test classes.\n", "Thereby, we pick $k$ examples per class from which we determine the prototypes, and test the classification accuracy on all other examples.\n", "This can be seen as using the $k$ examples per class as support set, and the rest of the dataset as a query set.\n", "We iterate through the dataset such that each example has been once included in a support set.\n", "The average performance over all support sets tells us how well we can expect ProtoNet to perform when seeing only $k$ examples per class.\n", "During training, we used $k=4$.\n", "In testing, we will experiment with $k=\\{2,4,8,16,32\\}$ to get a better sense of how $k$ influences the results.\n", "We would expect that we achieve higher accuracies the more examples we have in the support set, but we don't know how it scales.\n", "Hence, let's first implement a function that executes the testing procedure for a given $k$:"]}, {"cell_type": "code", "execution_count": 21, "id": "9e43469f", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:40.708839Z", "iopub.status.busy": "2021-10-10T16:36:40.706609Z", "iopub.status.idle": "2021-10-10T16:36:40.710916Z", "shell.execute_reply": "2021-10-10T16:36:40.710471Z"}, "papermill": {"duration": 0.055241, "end_time": "2021-10-10T16:36:40.711017", "exception": false, "start_time": "2021-10-10T16:36:40.655776", "status": "completed"}, "tags": []}, "outputs": [], "source": ["@torch.no_grad()\n", "def test_proto_net(model, dataset, data_feats=None, k_shot=4):\n", " \"\"\"Inputs.\n", "\n", " model - Pretrained ProtoNet model\n", " dataset - The dataset on which the test should be performed.\n", " Should be instance of ImageDataset\n", " data_feats - The encoded features of all images in the dataset.\n", " If None, they will be newly calculated, and returned\n", " for later usage.\n", " k_shot - Number of examples per class in the support set.\n", " \"\"\"\n", " model = model.to(device)\n", " model.eval()\n", " num_classes = dataset.targets.unique().shape[0]\n", " exmps_per_class = dataset.targets.shape[0] // num_classes # We assume uniform example distribution here\n", "\n", " # The encoder network remains unchanged across k-shot settings. Hence, we only need\n", " # to extract the features for all images once.\n", " if data_feats is None:\n", " # Dataset preparation\n", " dataloader = data.DataLoader(dataset, batch_size=128, num_workers=4, shuffle=False, drop_last=False)\n", "\n", " img_features = []\n", " img_targets = []\n", " for imgs, targets in tqdm(dataloader, \"Extracting image features\", leave=False):\n", " imgs = imgs.to(device)\n", " feats = model.model(imgs)\n", " img_features.append(feats.detach().cpu())\n", " img_targets.append(targets)\n", " img_features = torch.cat(img_features, dim=0)\n", " img_targets = torch.cat(img_targets, dim=0)\n", " # Sort by classes, so that we obtain tensors of shape [num_classes, exmps_per_class, ...]\n", " # Makes it easier to process later\n", " img_targets, sort_idx = img_targets.sort()\n", " img_targets = img_targets.reshape(num_classes, exmps_per_class).transpose(0, 1)\n", " img_features = img_features[sort_idx].reshape(num_classes, exmps_per_class, -1).transpose(0, 1)\n", " else:\n", " img_features, img_targets = data_feats\n", "\n", " # We iterate through the full dataset in two manners. First, to select the k-shot batch.\n", " # Second, the evaluate the model on all other examples\n", " accuracies = []\n", " for k_idx in tqdm(range(0, img_features.shape[0], k_shot), \"Evaluating prototype classification\", leave=False):\n", " # Select support set and calculate prototypes\n", " k_img_feats = img_features[k_idx : k_idx + k_shot].flatten(0, 1)\n", " k_targets = img_targets[k_idx : k_idx + k_shot].flatten(0, 1)\n", " prototypes, proto_classes = model.calculate_prototypes(k_img_feats, k_targets)\n", " # Evaluate accuracy on the rest of the dataset\n", " batch_acc = 0\n", " for e_idx in range(0, img_features.shape[0], k_shot):\n", " if k_idx == e_idx: # Do not evaluate on the support set examples\n", " continue\n", " e_img_feats = img_features[e_idx : e_idx + k_shot].flatten(0, 1)\n", " e_targets = img_targets[e_idx : e_idx + k_shot].flatten(0, 1)\n", " _, _, acc = model.classify_feats(prototypes, proto_classes, e_img_feats, e_targets)\n", " batch_acc += acc.item()\n", " batch_acc /= img_features.shape[0] // k_shot - 1\n", " accuracies.append(batch_acc)\n", "\n", " return (mean(accuracies), stdev(accuracies)), (img_features, img_targets)"]}, {"cell_type": "markdown", "id": "e8adff5f", "metadata": {"papermill": {"duration": 0.043398, "end_time": "2021-10-10T16:36:40.798077", "exception": false, "start_time": "2021-10-10T16:36:40.754679", "status": "completed"}, "tags": []}, "source": ["Testing ProtoNet is relatively quick if we have processed all images once. Hence, we can do in this notebook:"]}, {"cell_type": "code", "execution_count": 22, "id": "6b522e34", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:36:40.891051Z", "iopub.status.busy": "2021-10-10T16:36:40.890582Z", "iopub.status.idle": "2021-10-10T16:37:25.334685Z", "shell.execute_reply": "2021-10-10T16:37:25.334200Z"}, "papermill": {"duration": 44.492916, "end_time": "2021-10-10T16:37:25.334799", "exception": false, "start_time": "2021-10-10T16:36:40.841883", "status": "completed"}, "tags": []}, "outputs": [{"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "59b3b0d90a7548ae8ec79d1fb1aa783e", "version_major": 2, "version_minor": 0}, "text/plain": ["Extracting image features: 0%| | 0/47 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "c2ce51ed3ad643b2b521e696f82af495", "version_major": 2, "version_minor": 0}, "text/plain": ["Evaluating prototype classification: 0%| | 0/300 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"name": "stdout", "output_type": "stream", "text": ["Accuracy for k=2: 44.30% (+-3.63%)\n"]}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "18aca4955a7a4c64a8eb12925d3704d7", "version_major": 2, "version_minor": 0}, "text/plain": ["Evaluating prototype classification: 0%| | 0/150 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"name": "stdout", "output_type": "stream", "text": ["Accuracy for k=4: 52.07% (+-2.27%)\n"]}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "b6767d1462de4f8b8eb018e9f51ef402", "version_major": 2, "version_minor": 0}, "text/plain": ["Evaluating prototype classification: 0%| | 0/75 [00:20<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"name": "stdout", "output_type": "stream", "text": ["Accuracy for k=8: 57.59% (+-1.30%)\n"]}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "219937af24194529826e86cbeaa92dc1", "version_major": 2, "version_minor": 0}, "text/plain": ["Evaluating prototype classification: 0%| | 0/38 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"name": "stdout", "output_type": "stream", "text": ["Accuracy for k=16: 62.56% (+-1.02%)\n"]}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "ffaf8189884a44548efd49c252a85a7a", "version_major": 2, "version_minor": 0}, "text/plain": ["Evaluating prototype classification: 0%| | 0/19 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"name": "stdout", "output_type": "stream", "text": ["Accuracy for k=32: 66.49% (+-0.87%)\n"]}], "source": ["protonet_accuracies = dict()\n", "data_feats = None\n", "for k in [2, 4, 8, 16, 32]:\n", " protonet_accuracies[k], data_feats = test_proto_net(protonet_model, test_set, data_feats=data_feats, k_shot=k)\n", " print(\n", " \"Accuracy for k=%i: %4.2f%% (+-%4.2f%%)\"\n", " % (k, 100.0 * protonet_accuracies[k][0], 100 * protonet_accuracies[k][1])\n", " )"]}, {"cell_type": "markdown", "id": "15ae8c3d", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.048333, "end_time": "2021-10-10T16:37:25.430916", "exception": false, "start_time": "2021-10-10T16:37:25.382583", "status": "completed"}, "tags": []}, "source": ["Before discussing the results above, let's first plot the accuracies over number of examples in the support set:"]}, {"cell_type": "code", "execution_count": 23, "id": "36dc12c6", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:25.533731Z", "iopub.status.busy": "2021-10-10T16:37:25.533253Z", "iopub.status.idle": "2021-10-10T16:37:25.534911Z", "shell.execute_reply": "2021-10-10T16:37:25.535289Z"}, "papermill": {"duration": 0.057357, "end_time": "2021-10-10T16:37:25.535406", "exception": false, "start_time": "2021-10-10T16:37:25.478049", "status": "completed"}, "tags": []}, "outputs": [], "source": ["def plot_few_shot(acc_dict, name, color=None, ax=None):\n", " sns.set()\n", " if ax is None:\n", " fig, ax = plt.subplots(1, 1, figsize=(5, 3))\n", " ks = sorted(list(acc_dict.keys()))\n", " mean_accs = [acc_dict[k][0] for k in ks]\n", " std_accs = [acc_dict[k][1] for k in ks]\n", " ax.plot(ks, mean_accs, marker=\"o\", markeredgecolor=\"k\", markersize=6, label=name, color=color)\n", " ax.fill_between(\n", " ks,\n", " [m - s for m, s in zip(mean_accs, std_accs)],\n", " [m + s for m, s in zip(mean_accs, std_accs)],\n", " alpha=0.2,\n", " color=color,\n", " )\n", " ax.set_xticks(ks)\n", " ax.set_xlim([ks[0] - 1, ks[-1] + 1])\n", " ax.set_xlabel(\"Number of shots per class\", weight=\"bold\")\n", " ax.set_ylabel(\"Accuracy\", weight=\"bold\")\n", " if len(ax.get_title()) == 0:\n", " ax.set_title(\"Few-Shot Performance \" + name, weight=\"bold\")\n", " else:\n", " ax.set_title(ax.get_title() + \" and \" + name, weight=\"bold\")\n", " ax.legend()\n", " return ax"]}, {"cell_type": "code", "execution_count": 24, "id": "5b80ec9b", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:25.668929Z", "iopub.status.busy": "2021-10-10T16:37:25.662393Z", "iopub.status.idle": "2021-10-10T16:37:25.951305Z", "shell.execute_reply": "2021-10-10T16:37:25.950859Z"}, "papermill": {"duration": 0.362353, "end_time": "2021-10-10T16:37:25.951419", "exception": false, "start_time": "2021-10-10T16:37:25.589066", "status": "completed"}, "tags": []}, "outputs": [{"data": {"application/pdf": "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\n", "image/svg+xml": ["<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n", "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n", " \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n", "<svg height=\"228.357813pt\" version=\"1.1\" viewBox=\"0 0 343.005937 228.357813\" width=\"343.005937pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n", " <metadata>\n", " <rdf:RDF xmlns:cc=\"http://creativecommons.org/ns#\" xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\">\n", " <cc:Work>\n", " <dc:type rdf:resource=\"http://purl.org/dc/dcmitype/StillImage\"/>\n", " <dc:date>2021-10-10T18:37:25.755286</dc:date>\n", " <dc:format>image/svg+xml</dc:format>\n", " <dc:creator>\n", " <cc:Agent>\n", " <dc:title>Matplotlib v3.4.3, https://matplotlib.org/</dc:title>\n", " </cc:Agent>\n", " </dc:creator>\n", " </cc:Work>\n", " </rdf:RDF>\n", " </metadata>\n", " <defs>\n", " <style type=\"text/css\">*{stroke-linecap:butt;stroke-linejoin:round;}</style>\n", " </defs>\n", " <g id=\"figure_1\">\n", " <g id=\"patch_1\">\n", " <path d=\"M 0 228.357813 \n", "L 343.005937 228.357813 \n", "L 343.005937 0 \n", "L 0 0 \n", "z\n", "\" style=\"fill:#ffffff;\"/>\n", " </g>\n", " <g id=\"axes_1\">\n", " <g id=\"patch_2\">\n", " <path d=\"M 56.805937 185.398125 \n", "L 335.805938 185.398125 \n", "L 335.805938 22.318125 \n", "L 56.805937 22.318125 \n", "z\n", "\" style=\"fill:#eaeaf2;\"/>\n", " </g>\n", " <g id=\"matplotlib.axis_1\">\n", " <g id=\"xtick_1\">\n", " <g id=\"line2d_1\">\n", " <path clip-path=\"url(#p754f80f5a3)\" d=\"M 65.524687 185.398125 \n", "L 65.524687 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_1\">\n", " <!-- 2 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(62.025312 203.256406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 1228 531 \n", "L 3431 531 \n", "L 3431 0 \n", "L 469 0 \n", "L 469 531 \n", "Q 828 903 1448 1529 \n", "Q 2069 2156 2228 2338 \n", "Q 2531 2678 2651 2914 \n", "Q 2772 3150 2772 3378 \n", "Q 2772 3750 2511 3984 \n", "Q 2250 4219 1831 4219 \n", "Q 1534 4219 1204 4116 \n", "Q 875 4013 500 3803 \n", "L 500 4441 \n", "Q 881 4594 1212 4672 \n", "Q 1544 4750 1819 4750 \n", "Q 2544 4750 2975 4387 \n", "Q 3406 4025 3406 3419 \n", "Q 3406 3131 3298 2873 \n", "Q 3191 2616 2906 2266 \n", "Q 2828 2175 2409 1742 \n", "Q 1991 1309 1228 531 \n", "z\n", "\" id=\"DejaVuSans-32\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-32\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_2\">\n", " <g id=\"line2d_2\">\n", " <path clip-path=\"url(#p754f80f5a3)\" d=\"M 82.962187 185.398125 \n", "L 82.962187 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_2\">\n", " <!-- 4 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(79.462812 203.256406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 2419 4116 \n", "L 825 1625 \n", "L 2419 1625 \n", "L 2419 4116 \n", "z\n", "M 2253 4666 \n", "L 3047 4666 \n", "L 3047 1625 \n", "L 3713 1625 \n", "L 3713 1100 \n", "L 3047 1100 \n", "L 3047 0 \n", "L 2419 0 \n", "L 2419 1100 \n", "L 313 1100 \n", "L 313 1709 \n", "L 2253 4666 \n", "z\n", "\" id=\"DejaVuSans-34\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-34\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_3\">\n", " <g id=\"line2d_3\">\n", " <path clip-path=\"url(#p754f80f5a3)\" d=\"M 117.837187 185.398125 \n", "L 117.837187 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_3\">\n", " <!-- 8 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(114.337812 203.256406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 2034 2216 \n", "Q 1584 2216 1326 1975 \n", "Q 1069 1734 1069 1313 \n", "Q 1069 891 1326 650 \n", "Q 1584 409 2034 409 \n", "Q 2484 409 2743 651 \n", "Q 3003 894 3003 1313 \n", "Q 3003 1734 2745 1975 \n", "Q 2488 2216 2034 2216 \n", "z\n", "M 1403 2484 \n", "Q 997 2584 770 2862 \n", "Q 544 3141 544 3541 \n", "Q 544 4100 942 4425 \n", "Q 1341 4750 2034 4750 \n", "Q 2731 4750 3128 4425 \n", "Q 3525 4100 3525 3541 \n", "Q 3525 3141 3298 2862 \n", "Q 3072 2584 2669 2484 \n", "Q 3125 2378 3379 2068 \n", "Q 3634 1759 3634 1313 \n", "Q 3634 634 3220 271 \n", "Q 2806 -91 2034 -91 \n", "Q 1263 -91 848 271 \n", "Q 434 634 434 1313 \n", "Q 434 1759 690 2068 \n", "Q 947 2378 1403 2484 \n", "z\n", "M 1172 3481 \n", "Q 1172 3119 1398 2916 \n", "Q 1625 2713 2034 2713 \n", "Q 2441 2713 2670 2916 \n", "Q 2900 3119 2900 3481 \n", "Q 2900 3844 2670 4047 \n", "Q 2441 4250 2034 4250 \n", "Q 1625 4250 1398 4047 \n", "Q 1172 3844 1172 3481 \n", "z\n", "\" id=\"DejaVuSans-38\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-38\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_4\">\n", " <g id=\"line2d_4\">\n", " <path clip-path=\"url(#p754f80f5a3)\" d=\"M 187.587187 185.398125 \n", "L 187.587187 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_4\">\n", " <!-- 16 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(180.588437 203.256406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 794 531 \n", "L 1825 531 \n", "L 1825 4091 \n", "L 703 3866 \n", "L 703 4441 \n", "L 1819 4666 \n", "L 2450 4666 \n", "L 2450 531 \n", "L 3481 531 \n", "L 3481 0 \n", "L 794 0 \n", "L 794 531 \n", "z\n", "\" id=\"DejaVuSans-31\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2113 2584 \n", "Q 1688 2584 1439 2293 \n", "Q 1191 2003 1191 1497 \n", "Q 1191 994 1439 701 \n", "Q 1688 409 2113 409 \n", "Q 2538 409 2786 701 \n", "Q 3034 994 3034 1497 \n", "Q 3034 2003 2786 2293 \n", "Q 2538 2584 2113 2584 \n", "z\n", "M 3366 4563 \n", "L 3366 3988 \n", "Q 3128 4100 2886 4159 \n", "Q 2644 4219 2406 4219 \n", "Q 1781 4219 1451 3797 \n", "Q 1122 3375 1075 2522 \n", "Q 1259 2794 1537 2939 \n", "Q 1816 3084 2150 3084 \n", "Q 2853 3084 3261 2657 \n", "Q 3669 2231 3669 1497 \n", "Q 3669 778 3244 343 \n", "Q 2819 -91 2113 -91 \n", "Q 1303 -91 875 529 \n", "Q 447 1150 447 2328 \n", "Q 447 3434 972 4092 \n", "Q 1497 4750 2381 4750 \n", "Q 2619 4750 2861 4703 \n", "Q 3103 4656 3366 4563 \n", "z\n", "\" id=\"DejaVuSans-36\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-31\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-36\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_5\">\n", " <g id=\"line2d_5\">\n", " <path clip-path=\"url(#p754f80f5a3)\" d=\"M 327.087188 185.398125 \n", "L 327.087188 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_5\">\n", " <!-- 32 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(320.088438 203.256406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 2597 2516 \n", "Q 3050 2419 3304 2112 \n", "Q 3559 1806 3559 1356 \n", "Q 3559 666 3084 287 \n", "Q 2609 -91 1734 -91 \n", "Q 1441 -91 1130 -33 \n", "Q 819 25 488 141 \n", "L 488 750 \n", "Q 750 597 1062 519 \n", "Q 1375 441 1716 441 \n", "Q 2309 441 2620 675 \n", "Q 2931 909 2931 1356 \n", "Q 2931 1769 2642 2001 \n", "Q 2353 2234 1838 2234 \n", "L 1294 2234 \n", "L 1294 2753 \n", "L 1863 2753 \n", "Q 2328 2753 2575 2939 \n", "Q 2822 3125 2822 3475 \n", "Q 2822 3834 2567 4026 \n", "Q 2313 4219 1838 4219 \n", "Q 1578 4219 1281 4162 \n", "Q 984 4106 628 3988 \n", "L 628 4550 \n", "Q 988 4650 1302 4700 \n", "Q 1616 4750 1894 4750 \n", "Q 2613 4750 3031 4423 \n", "Q 3450 4097 3450 3541 \n", "Q 3450 3153 3228 2886 \n", "Q 3006 2619 2597 2516 \n", "z\n", "\" id=\"DejaVuSans-33\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-33\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-32\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"text_6\">\n", " <!-- Number of shots per class -->\n", " <g style=\"fill:#262626;\" transform=\"translate(107.82 218.662188)scale(0.12 -0.12)\">\n", " <defs>\n", " <path d=\"M 588 4666 \n", "L 1931 4666 \n", "L 3628 1466 \n", "L 3628 4666 \n", "L 4769 4666 \n", "L 4769 0 \n", "L 3425 0 \n", "L 1728 3200 \n", "L 1728 0 \n", "L 588 0 \n", "L 588 4666 \n", "z\n", "\" id=\"DejaVuSans-Bold-4e\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 500 1363 \n", "L 500 3500 \n", "L 1625 3500 \n", "L 1625 3150 \n", "Q 1625 2866 1622 2436 \n", "Q 1619 2006 1619 1863 \n", "Q 1619 1441 1641 1255 \n", "Q 1663 1069 1716 984 \n", "Q 1784 875 1895 815 \n", "Q 2006 756 2150 756 \n", "Q 2500 756 2700 1025 \n", "Q 2900 1294 2900 1772 \n", "L 2900 3500 \n", "L 4019 3500 \n", "L 4019 0 \n", "L 2900 0 \n", "L 2900 506 \n", "Q 2647 200 2364 54 \n", "Q 2081 -91 1741 -91 \n", "Q 1134 -91 817 281 \n", "Q 500 653 500 1363 \n", "z\n", "\" id=\"DejaVuSans-Bold-75\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3781 2919 \n", "Q 3994 3244 4286 3414 \n", "Q 4578 3584 4928 3584 \n", "Q 5531 3584 5847 3212 \n", "Q 6163 2841 6163 2131 \n", "L 6163 0 \n", "L 5038 0 \n", "L 5038 1825 \n", "Q 5041 1866 5042 1909 \n", "Q 5044 1953 5044 2034 \n", "Q 5044 2406 4934 2573 \n", "Q 4825 2741 4581 2741 \n", "Q 4263 2741 4089 2478 \n", "Q 3916 2216 3909 1719 \n", "L 3909 0 \n", "L 2784 0 \n", "L 2784 1825 \n", "Q 2784 2406 2684 2573 \n", "Q 2584 2741 2328 2741 \n", "Q 2006 2741 1831 2477 \n", "Q 1656 2213 1656 1722 \n", "L 1656 0 \n", "L 531 0 \n", "L 531 3500 \n", "L 1656 3500 \n", "L 1656 2988 \n", "Q 1863 3284 2130 3434 \n", "Q 2397 3584 2719 3584 \n", "Q 3081 3584 3359 3409 \n", "Q 3638 3234 3781 2919 \n", "z\n", "\" id=\"DejaVuSans-Bold-6d\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2400 722 \n", "Q 2759 722 2948 984 \n", "Q 3138 1247 3138 1747 \n", "Q 3138 2247 2948 2509 \n", "Q 2759 2772 2400 2772 \n", "Q 2041 2772 1848 2508 \n", "Q 1656 2244 1656 1747 \n", "Q 1656 1250 1848 986 \n", "Q 2041 722 2400 722 \n", "z\n", "M 1656 2988 \n", "Q 1888 3294 2169 3439 \n", "Q 2450 3584 2816 3584 \n", "Q 3463 3584 3878 3070 \n", "Q 4294 2556 4294 1747 \n", "Q 4294 938 3878 423 \n", "Q 3463 -91 2816 -91 \n", "Q 2450 -91 2169 54 \n", "Q 1888 200 1656 506 \n", "L 1656 0 \n", "L 538 0 \n", "L 538 4863 \n", "L 1656 4863 \n", "L 1656 2988 \n", "z\n", "\" id=\"DejaVuSans-Bold-62\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 4031 1759 \n", "L 4031 1441 \n", "L 1416 1441 \n", "Q 1456 1047 1700 850 \n", "Q 1944 653 2381 653 \n", "Q 2734 653 3104 758 \n", "Q 3475 863 3866 1075 \n", "L 3866 213 \n", "Q 3469 63 3072 -14 \n", "Q 2675 -91 2278 -91 \n", "Q 1328 -91 801 392 \n", "Q 275 875 275 1747 \n", "Q 275 2603 792 3093 \n", "Q 1309 3584 2216 3584 \n", "Q 3041 3584 3536 3087 \n", "Q 4031 2591 4031 1759 \n", "z\n", "M 2881 2131 \n", "Q 2881 2450 2695 2645 \n", "Q 2509 2841 2209 2841 \n", "Q 1884 2841 1681 2658 \n", "Q 1478 2475 1428 2131 \n", "L 2881 2131 \n", "z\n", "\" id=\"DejaVuSans-Bold-65\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3138 2547 \n", "Q 2991 2616 2845 2648 \n", "Q 2700 2681 2553 2681 \n", "Q 2122 2681 1889 2404 \n", "Q 1656 2128 1656 1613 \n", "L 1656 0 \n", "L 538 0 \n", "L 538 3500 \n", "L 1656 3500 \n", "L 1656 2925 \n", "Q 1872 3269 2151 3426 \n", "Q 2431 3584 2822 3584 \n", "Q 2878 3584 2943 3579 \n", "Q 3009 3575 3134 3559 \n", "L 3138 2547 \n", "z\n", "\" id=\"DejaVuSans-Bold-72\" transform=\"scale(0.015625)\"/>\n", " <path id=\"DejaVuSans-Bold-20\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2203 2784 \n", "Q 1831 2784 1636 2517 \n", "Q 1441 2250 1441 1747 \n", "Q 1441 1244 1636 976 \n", "Q 1831 709 2203 709 \n", "Q 2569 709 2762 976 \n", "Q 2956 1244 2956 1747 \n", "Q 2956 2250 2762 2517 \n", "Q 2569 2784 2203 2784 \n", "z\n", "M 2203 3584 \n", "Q 3106 3584 3614 3096 \n", "Q 4122 2609 4122 1747 \n", "Q 4122 884 3614 396 \n", "Q 3106 -91 2203 -91 \n", "Q 1297 -91 786 396 \n", "Q 275 884 275 1747 \n", "Q 275 2609 786 3096 \n", "Q 1297 3584 2203 3584 \n", "z\n", "\" id=\"DejaVuSans-Bold-6f\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2841 4863 \n", "L 2841 4128 \n", "L 2222 4128 \n", "Q 1984 4128 1890 4042 \n", "Q 1797 3956 1797 3744 \n", "L 1797 3500 \n", "L 2753 3500 \n", "L 2753 2700 \n", "L 1797 2700 \n", "L 1797 0 \n", "L 678 0 \n", "L 678 2700 \n", "L 122 2700 \n", "L 122 3500 \n", "L 678 3500 \n", "L 678 3744 \n", "Q 678 4316 997 4589 \n", "Q 1316 4863 1984 4863 \n", "L 2841 4863 \n", "z\n", "\" id=\"DejaVuSans-Bold-66\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3272 3391 \n", "L 3272 2541 \n", "Q 2913 2691 2578 2766 \n", "Q 2244 2841 1947 2841 \n", "Q 1628 2841 1473 2761 \n", "Q 1319 2681 1319 2516 \n", "Q 1319 2381 1436 2309 \n", "Q 1553 2238 1856 2203 \n", "L 2053 2175 \n", "Q 2913 2066 3209 1816 \n", "Q 3506 1566 3506 1031 \n", "Q 3506 472 3093 190 \n", "Q 2681 -91 1863 -91 \n", "Q 1516 -91 1145 -36 \n", "Q 775 19 384 128 \n", "L 384 978 \n", "Q 719 816 1070 734 \n", "Q 1422 653 1784 653 \n", "Q 2113 653 2278 743 \n", "Q 2444 834 2444 1013 \n", "Q 2444 1163 2330 1236 \n", "Q 2216 1309 1875 1350 \n", "L 1678 1375 \n", "Q 931 1469 631 1722 \n", "Q 331 1975 331 2491 \n", "Q 331 3047 712 3315 \n", "Q 1094 3584 1881 3584 \n", "Q 2191 3584 2531 3537 \n", "Q 2872 3491 3272 3391 \n", "z\n", "\" id=\"DejaVuSans-Bold-73\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 4056 2131 \n", "L 4056 0 \n", "L 2931 0 \n", "L 2931 347 \n", "L 2931 1625 \n", "Q 2931 2084 2911 2256 \n", "Q 2891 2428 2841 2509 \n", "Q 2775 2619 2662 2680 \n", "Q 2550 2741 2406 2741 \n", "Q 2056 2741 1856 2470 \n", "Q 1656 2200 1656 1722 \n", "L 1656 0 \n", "L 538 0 \n", "L 538 4863 \n", "L 1656 4863 \n", "L 1656 2988 \n", "Q 1909 3294 2193 3439 \n", "Q 2478 3584 2822 3584 \n", "Q 3428 3584 3742 3212 \n", "Q 4056 2841 4056 2131 \n", "z\n", "\" id=\"DejaVuSans-Bold-68\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1759 4494 \n", "L 1759 3500 \n", "L 2913 3500 \n", "L 2913 2700 \n", "L 1759 2700 \n", "L 1759 1216 \n", "Q 1759 972 1856 886 \n", "Q 1953 800 2241 800 \n", "L 2816 800 \n", "L 2816 0 \n", "L 1856 0 \n", "Q 1194 0 917 276 \n", "Q 641 553 641 1216 \n", "L 641 2700 \n", "L 84 2700 \n", "L 84 3500 \n", "L 641 3500 \n", "L 641 4494 \n", "L 1759 4494 \n", "z\n", "\" id=\"DejaVuSans-Bold-74\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1656 506 \n", "L 1656 -1331 \n", "L 538 -1331 \n", "L 538 3500 \n", "L 1656 3500 \n", "L 1656 2988 \n", "Q 1888 3294 2169 3439 \n", "Q 2450 3584 2816 3584 \n", "Q 3463 3584 3878 3070 \n", "Q 4294 2556 4294 1747 \n", "Q 4294 938 3878 423 \n", "Q 3463 -91 2816 -91 \n", "Q 2450 -91 2169 54 \n", "Q 1888 200 1656 506 \n", "z\n", "M 2400 2772 \n", "Q 2041 2772 1848 2508 \n", "Q 1656 2244 1656 1747 \n", "Q 1656 1250 1848 986 \n", "Q 2041 722 2400 722 \n", "Q 2759 722 2948 984 \n", "Q 3138 1247 3138 1747 \n", "Q 3138 2247 2948 2509 \n", "Q 2759 2772 2400 2772 \n", "z\n", "\" id=\"DejaVuSans-Bold-70\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3366 3391 \n", "L 3366 2478 \n", "Q 3138 2634 2908 2709 \n", "Q 2678 2784 2431 2784 \n", "Q 1963 2784 1702 2511 \n", "Q 1441 2238 1441 1747 \n", "Q 1441 1256 1702 982 \n", "Q 1963 709 2431 709 \n", "Q 2694 709 2930 787 \n", "Q 3166 866 3366 1019 \n", "L 3366 103 \n", "Q 3103 6 2833 -42 \n", "Q 2563 -91 2291 -91 \n", "Q 1344 -91 809 395 \n", "Q 275 881 275 1747 \n", "Q 275 2613 809 3098 \n", "Q 1344 3584 2291 3584 \n", "Q 2566 3584 2833 3536 \n", "Q 3100 3488 3366 3391 \n", "z\n", "\" id=\"DejaVuSans-Bold-63\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 538 4863 \n", "L 1656 4863 \n", "L 1656 0 \n", "L 538 0 \n", "L 538 4863 \n", "z\n", "\" id=\"DejaVuSans-Bold-6c\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2106 1575 \n", "Q 1756 1575 1579 1456 \n", "Q 1403 1338 1403 1106 \n", "Q 1403 894 1545 773 \n", "Q 1688 653 1941 653 \n", "Q 2256 653 2472 879 \n", "Q 2688 1106 2688 1447 \n", "L 2688 1575 \n", "L 2106 1575 \n", "z\n", "M 3816 1997 \n", "L 3816 0 \n", "L 2688 0 \n", "L 2688 519 \n", "Q 2463 200 2181 54 \n", "Q 1900 -91 1497 -91 \n", "Q 953 -91 614 226 \n", "Q 275 544 275 1050 \n", "Q 275 1666 698 1953 \n", "Q 1122 2241 2028 2241 \n", "L 2688 2241 \n", "L 2688 2328 \n", "Q 2688 2594 2478 2717 \n", "Q 2269 2841 1825 2841 \n", "Q 1466 2841 1156 2769 \n", "Q 847 2697 581 2553 \n", "L 581 3406 \n", "Q 941 3494 1303 3539 \n", "Q 1666 3584 2028 3584 \n", "Q 2975 3584 3395 3211 \n", "Q 3816 2838 3816 1997 \n", "z\n", "\" id=\"DejaVuSans-Bold-61\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-Bold-4e\"/>\n", " <use x=\"83.691406\" xlink:href=\"#DejaVuSans-Bold-75\"/>\n", " <use x=\"154.882812\" xlink:href=\"#DejaVuSans-Bold-6d\"/>\n", " <use x=\"259.082031\" xlink:href=\"#DejaVuSans-Bold-62\"/>\n", " <use x=\"330.664062\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"398.486328\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"447.802734\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"482.617188\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"551.318359\" xlink:href=\"#DejaVuSans-Bold-66\"/>\n", " <use x=\"594.824219\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"629.638672\" xlink:href=\"#DejaVuSans-Bold-73\"/>\n", " <use x=\"689.160156\" xlink:href=\"#DejaVuSans-Bold-68\"/>\n", " <use x=\"760.351562\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"829.052734\" xlink:href=\"#DejaVuSans-Bold-74\"/>\n", " <use x=\"876.855469\" xlink:href=\"#DejaVuSans-Bold-73\"/>\n", " <use x=\"936.376953\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"971.191406\" xlink:href=\"#DejaVuSans-Bold-70\"/>\n", " <use x=\"1042.773438\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"1110.595703\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"1159.912109\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"1194.726562\" xlink:href=\"#DejaVuSans-Bold-63\"/>\n", " <use x=\"1254.003906\" xlink:href=\"#DejaVuSans-Bold-6c\"/>\n", " <use x=\"1288.28125\" xlink:href=\"#DejaVuSans-Bold-61\"/>\n", " <use x=\"1355.761719\" xlink:href=\"#DejaVuSans-Bold-73\"/>\n", " <use x=\"1415.283203\" xlink:href=\"#DejaVuSans-Bold-73\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"matplotlib.axis_2\">\n", " <g id=\"ytick_1\">\n", " <g id=\"line2d_6\">\n", " <path clip-path=\"url(#p754f80f5a3)\" d=\"M 56.805937 181.685024 \n", "L 335.805938 181.685024 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_7\">\n", " <!-- 0.40 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 185.864164)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 2034 4250 \n", "Q 1547 4250 1301 3770 \n", "Q 1056 3291 1056 2328 \n", "Q 1056 1369 1301 889 \n", "Q 1547 409 2034 409 \n", "Q 2525 409 2770 889 \n", "Q 3016 1369 3016 2328 \n", "Q 3016 3291 2770 3770 \n", "Q 2525 4250 2034 4250 \n", "z\n", "M 2034 4750 \n", "Q 2819 4750 3233 4129 \n", "Q 3647 3509 3647 2328 \n", "Q 3647 1150 3233 529 \n", "Q 2819 -91 2034 -91 \n", "Q 1250 -91 836 529 \n", "Q 422 1150 422 2328 \n", "Q 422 3509 836 4129 \n", "Q 1250 4750 2034 4750 \n", "z\n", "\" id=\"DejaVuSans-30\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 684 794 \n", "L 1344 794 \n", "L 1344 0 \n", "L 684 0 \n", "L 684 794 \n", "z\n", "\" id=\"DejaVuSans-2e\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-34\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_2\">\n", " <g id=\"line2d_7\">\n", " <path clip-path=\"url(#p754f80f5a3)\" d=\"M 56.805937 153.919401 \n", "L 335.805938 153.919401 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_8\">\n", " <!-- 0.45 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 158.098542)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 691 4666 \n", "L 3169 4666 \n", "L 3169 4134 \n", "L 1269 4134 \n", "L 1269 2991 \n", "Q 1406 3038 1543 3061 \n", "Q 1681 3084 1819 3084 \n", "Q 2600 3084 3056 2656 \n", "Q 3513 2228 3513 1497 \n", "Q 3513 744 3044 326 \n", "Q 2575 -91 1722 -91 \n", "Q 1428 -91 1123 -41 \n", "Q 819 9 494 109 \n", "L 494 744 \n", "Q 775 591 1075 516 \n", "Q 1375 441 1709 441 \n", "Q 2250 441 2565 725 \n", "Q 2881 1009 2881 1497 \n", "Q 2881 1984 2565 2268 \n", "Q 2250 2553 1709 2553 \n", "Q 1456 2553 1204 2497 \n", "Q 953 2441 691 2322 \n", "L 691 4666 \n", "z\n", "\" id=\"DejaVuSans-35\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-34\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-35\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_3\">\n", " <g id=\"line2d_8\">\n", " <path clip-path=\"url(#p754f80f5a3)\" d=\"M 56.805937 126.153779 \n", "L 335.805938 126.153779 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_9\">\n", " <!-- 0.50 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 130.332919)scale(0.11 -0.11)\">\n", " <use xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-35\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_4\">\n", " <g id=\"line2d_9\">\n", " <path clip-path=\"url(#p754f80f5a3)\" d=\"M 56.805937 98.388156 \n", "L 335.805938 98.388156 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_10\">\n", " <!-- 0.55 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 102.567297)scale(0.11 -0.11)\">\n", " <use xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-35\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-35\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_5\">\n", " <g id=\"line2d_10\">\n", " <path clip-path=\"url(#p754f80f5a3)\" d=\"M 56.805937 70.622534 \n", "L 335.805938 70.622534 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_11\">\n", " <!-- 0.60 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 74.801675)scale(0.11 -0.11)\">\n", " <use xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-36\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_6\">\n", " <g id=\"line2d_11\">\n", " <path clip-path=\"url(#p754f80f5a3)\" d=\"M 56.805937 42.856912 \n", "L 335.805938 42.856912 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_12\">\n", " <!-- 0.65 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 47.036052)scale(0.11 -0.11)\">\n", " <use xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-36\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-35\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"text_13\">\n", " <!-- Accuracy -->\n", " <g style=\"fill:#262626;\" transform=\"translate(16.224375 134.3625)rotate(-90)scale(0.12 -0.12)\">\n", " <defs>\n", " <path d=\"M 3419 850 \n", "L 1538 850 \n", "L 1241 0 \n", "L 31 0 \n", "L 1759 4666 \n", "L 3194 4666 \n", "L 4922 0 \n", "L 3713 0 \n", "L 3419 850 \n", "z\n", "M 1838 1716 \n", "L 3116 1716 \n", "L 2478 3572 \n", "L 1838 1716 \n", "z\n", "\" id=\"DejaVuSans-Bold-41\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 78 3500 \n", "L 1197 3500 \n", "L 2138 1125 \n", "L 2938 3500 \n", "L 4056 3500 \n", "L 2584 -331 \n", "Q 2363 -916 2067 -1148 \n", "Q 1772 -1381 1288 -1381 \n", "L 641 -1381 \n", "L 641 -647 \n", "L 991 -647 \n", "Q 1275 -647 1404 -556 \n", "Q 1534 -466 1606 -231 \n", "L 1638 -134 \n", "L 78 3500 \n", "z\n", "\" id=\"DejaVuSans-Bold-79\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-Bold-41\"/>\n", " <use x=\"77.392578\" xlink:href=\"#DejaVuSans-Bold-63\"/>\n", " <use x=\"136.669922\" xlink:href=\"#DejaVuSans-Bold-63\"/>\n", " <use x=\"195.947266\" xlink:href=\"#DejaVuSans-Bold-75\"/>\n", " <use x=\"267.138672\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"316.455078\" xlink:href=\"#DejaVuSans-Bold-61\"/>\n", " <use x=\"383.935547\" xlink:href=\"#DejaVuSans-Bold-63\"/>\n", " <use x=\"443.212891\" xlink:href=\"#DejaVuSans-Bold-79\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"PolyCollection_1\">\n", " <defs>\n", " <path d=\"M 65.524687 -90.689176 \n", "L 65.524687 -50.372415 \n", "L 82.962187 -101.07789 \n", "L 117.837187 -137.10154 \n", "L 187.587187 -166.283292 \n", "L 327.087188 -188.954701 \n", "L 327.087188 -198.62696 \n", "L 327.087188 -198.62696 \n", "L 187.587187 -177.653117 \n", "L 117.837187 -151.581445 \n", "L 82.962187 -126.322843 \n", "L 65.524687 -90.689176 \n", "z\n", "\" id=\"m3515cabac5\" style=\"stroke:#dd8452;stroke-opacity:0.2;\"/>\n", " </defs>\n", " <g clip-path=\"url(#p754f80f5a3)\">\n", " <use style=\"fill:#dd8452;fill-opacity:0.2;stroke:#dd8452;stroke-opacity:0.2;\" x=\"0\" xlink:href=\"#m3515cabac5\" y=\"228.357813\"/>\n", " </g>\n", " </g>\n", " <g id=\"line2d_12\">\n", " <path clip-path=\"url(#p754f80f5a3)\" d=\"M 65.524687 157.827017 \n", "L 82.962187 114.657446 \n", "L 117.837187 84.01632 \n", "L 187.587187 56.389608 \n", "L 327.087188 34.566982 \n", "\" style=\"fill:none;stroke:#dd8452;stroke-linecap:round;stroke-width:1.5;\"/>\n", " <defs>\n", " <path d=\"M 0 3 \n", "C 0.795609 3 1.55874 2.683901 2.12132 2.12132 \n", "C 2.683901 1.55874 3 0.795609 3 0 \n", "C 3 -0.795609 2.683901 -1.55874 2.12132 -2.12132 \n", "C 1.55874 -2.683901 0.795609 -3 0 -3 \n", "C -0.795609 -3 -1.55874 -2.683901 -2.12132 -2.12132 \n", "C -2.683901 -1.55874 -3 -0.795609 -3 0 \n", "C -3 0.795609 -2.683901 1.55874 -2.12132 2.12132 \n", "C -1.55874 2.683901 -0.795609 3 0 3 \n", "z\n", "\" id=\"m477528a3e5\" style=\"stroke:#1a1a1a;\"/>\n", " </defs>\n", " <g clip-path=\"url(#p754f80f5a3)\">\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"65.524687\" xlink:href=\"#m477528a3e5\" y=\"157.827017\"/>\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"82.962187\" xlink:href=\"#m477528a3e5\" y=\"114.657446\"/>\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"117.837187\" xlink:href=\"#m477528a3e5\" y=\"84.01632\"/>\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"187.587187\" xlink:href=\"#m477528a3e5\" y=\"56.389608\"/>\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"327.087188\" xlink:href=\"#m477528a3e5\" y=\"34.566982\"/>\n", " </g>\n", " </g>\n", " <g id=\"patch_3\">\n", " <path d=\"M 56.805937 185.398125 \n", "L 56.805937 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:square;stroke-linejoin:miter;stroke-width:1.25;\"/>\n", " </g>\n", " <g id=\"patch_4\">\n", " <path d=\"M 335.805938 185.398125 \n", "L 335.805938 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:square;stroke-linejoin:miter;stroke-width:1.25;\"/>\n", " </g>\n", " <g id=\"patch_5\">\n", " <path d=\"M 56.805937 185.398125 \n", "L 335.805938 185.398125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:square;stroke-linejoin:miter;stroke-width:1.25;\"/>\n", " </g>\n", " <g id=\"patch_6\">\n", " <path d=\"M 56.805937 22.318125 \n", "L 335.805938 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:square;stroke-linejoin:miter;stroke-width:1.25;\"/>\n", " </g>\n", " <g id=\"text_14\">\n", " <!-- Few-Shot Performance ProtoNet -->\n", " <g style=\"fill:#262626;\" transform=\"translate(86.840625 16.318125)scale(0.12 -0.12)\">\n", " <defs>\n", " <path d=\"M 588 4666 \n", "L 3834 4666 \n", "L 3834 3756 \n", "L 1791 3756 \n", "L 1791 2888 \n", "L 3713 2888 \n", "L 3713 1978 \n", "L 1791 1978 \n", "L 1791 0 \n", "L 588 0 \n", "L 588 4666 \n", "z\n", "\" id=\"DejaVuSans-Bold-46\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 225 3500 \n", "L 1313 3500 \n", "L 1900 1088 \n", "L 2491 3500 \n", "L 3425 3500 \n", "L 4013 1113 \n", "L 4603 3500 \n", "L 5691 3500 \n", "L 4769 0 \n", "L 3547 0 \n", "L 2956 2406 \n", "L 2369 0 \n", "L 1147 0 \n", "L 225 3500 \n", "z\n", "\" id=\"DejaVuSans-Bold-77\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 347 2297 \n", "L 2309 2297 \n", "L 2309 1388 \n", "L 347 1388 \n", "L 347 2297 \n", "z\n", "\" id=\"DejaVuSans-Bold-2d\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3834 4519 \n", "L 3834 3531 \n", "Q 3450 3703 3084 3790 \n", "Q 2719 3878 2394 3878 \n", "Q 1963 3878 1756 3759 \n", "Q 1550 3641 1550 3391 \n", "Q 1550 3203 1689 3098 \n", "Q 1828 2994 2194 2919 \n", "L 2706 2816 \n", "Q 3484 2659 3812 2340 \n", "Q 4141 2022 4141 1434 \n", "Q 4141 663 3683 286 \n", "Q 3225 -91 2284 -91 \n", "Q 1841 -91 1394 -6 \n", "Q 947 78 500 244 \n", "L 500 1259 \n", "Q 947 1022 1364 901 \n", "Q 1781 781 2169 781 \n", "Q 2563 781 2772 912 \n", "Q 2981 1044 2981 1288 \n", "Q 2981 1506 2839 1625 \n", "Q 2697 1744 2272 1838 \n", "L 1806 1941 \n", "Q 1106 2091 782 2419 \n", "Q 459 2747 459 3303 \n", "Q 459 4000 909 4375 \n", "Q 1359 4750 2203 4750 \n", "Q 2588 4750 2994 4692 \n", "Q 3400 4634 3834 4519 \n", "z\n", "\" id=\"DejaVuSans-Bold-53\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 588 4666 \n", "L 2584 4666 \n", "Q 3475 4666 3951 4270 \n", "Q 4428 3875 4428 3144 \n", "Q 4428 2409 3951 2014 \n", "Q 3475 1619 2584 1619 \n", "L 1791 1619 \n", "L 1791 0 \n", "L 588 0 \n", "L 588 4666 \n", "z\n", "M 1791 3794 \n", "L 1791 2491 \n", "L 2456 2491 \n", "Q 2806 2491 2997 2661 \n", "Q 3188 2831 3188 3144 \n", "Q 3188 3456 2997 3625 \n", "Q 2806 3794 2456 3794 \n", "L 1791 3794 \n", "z\n", "\" id=\"DejaVuSans-Bold-50\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 4056 2131 \n", "L 4056 0 \n", "L 2931 0 \n", "L 2931 347 \n", "L 2931 1631 \n", "Q 2931 2084 2911 2256 \n", "Q 2891 2428 2841 2509 \n", "Q 2775 2619 2662 2680 \n", "Q 2550 2741 2406 2741 \n", "Q 2056 2741 1856 2470 \n", "Q 1656 2200 1656 1722 \n", "L 1656 0 \n", "L 538 0 \n", "L 538 3500 \n", "L 1656 3500 \n", "L 1656 2988 \n", "Q 1909 3294 2193 3439 \n", "Q 2478 3584 2822 3584 \n", "Q 3428 3584 3742 3212 \n", "Q 4056 2841 4056 2131 \n", "z\n", "\" id=\"DejaVuSans-Bold-6e\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-Bold-46\"/>\n", " <use x=\"64.310547\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"132.132812\" xlink:href=\"#DejaVuSans-Bold-77\"/>\n", " <use x=\"224.515625\" xlink:href=\"#DejaVuSans-Bold-2d\"/>\n", " <use x=\"266.019531\" xlink:href=\"#DejaVuSans-Bold-53\"/>\n", " <use x=\"338.041016\" xlink:href=\"#DejaVuSans-Bold-68\"/>\n", " <use x=\"409.232422\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"477.933594\" xlink:href=\"#DejaVuSans-Bold-74\"/>\n", " <use x=\"525.736328\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"560.550781\" xlink:href=\"#DejaVuSans-Bold-50\"/>\n", " <use x=\"633.841797\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"701.664062\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"750.980469\" xlink:href=\"#DejaVuSans-Bold-66\"/>\n", " <use x=\"794.486328\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"863.1875\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"912.503906\" xlink:href=\"#DejaVuSans-Bold-6d\"/>\n", " <use x=\"1016.703125\" xlink:href=\"#DejaVuSans-Bold-61\"/>\n", " <use x=\"1084.183594\" xlink:href=\"#DejaVuSans-Bold-6e\"/>\n", " <use x=\"1155.375\" xlink:href=\"#DejaVuSans-Bold-63\"/>\n", " <use x=\"1214.652344\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"1282.474609\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"1317.289062\" xlink:href=\"#DejaVuSans-Bold-50\"/>\n", " <use x=\"1390.580078\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"1439.896484\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"1508.597656\" xlink:href=\"#DejaVuSans-Bold-74\"/>\n", " <use x=\"1556.400391\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"1625.101562\" xlink:href=\"#DejaVuSans-Bold-4e\"/>\n", " <use x=\"1708.792969\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"1776.615234\" xlink:href=\"#DejaVuSans-Bold-74\"/>\n", " </g>\n", " </g>\n", " <g id=\"legend_1\">\n", " <g id=\"patch_7\">\n", " <path d=\"M 64.505938 47.264063 \n", "L 147.504375 47.264063 \n", "Q 149.704375 47.264063 149.704375 45.064063 \n", "L 149.704375 30.018125 \n", "Q 149.704375 27.818125 147.504375 27.818125 \n", "L 64.505938 27.818125 \n", "Q 62.305938 27.818125 62.305938 30.018125 \n", "L 62.305938 45.064063 \n", "Q 62.305938 47.264063 64.505938 47.264063 \n", "z\n", "\" style=\"fill:#eaeaf2;opacity:0.8;stroke:#cccccc;stroke-linejoin:miter;\"/>\n", " </g>\n", " <g id=\"line2d_13\">\n", " <path d=\"M 66.705938 36.726406 \n", "L 88.705938 36.726406 \n", "\" style=\"fill:none;stroke:#dd8452;stroke-linecap:round;stroke-width:1.5;\"/>\n", " </g>\n", " <g id=\"line2d_14\">\n", " <g>\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"77.705938\" xlink:href=\"#m477528a3e5\" y=\"36.726406\"/>\n", " </g>\n", " </g>\n", " <g id=\"text_15\">\n", " <!-- ProtoNet -->\n", " <g style=\"fill:#262626;\" transform=\"translate(97.505938 40.576406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 1259 4147 \n", "L 1259 2394 \n", "L 2053 2394 \n", "Q 2494 2394 2734 2622 \n", "Q 2975 2850 2975 3272 \n", "Q 2975 3691 2734 3919 \n", "Q 2494 4147 2053 4147 \n", "L 1259 4147 \n", "z\n", "M 628 4666 \n", "L 2053 4666 \n", "Q 2838 4666 3239 4311 \n", "Q 3641 3956 3641 3272 \n", "Q 3641 2581 3239 2228 \n", "Q 2838 1875 2053 1875 \n", "L 1259 1875 \n", "L 1259 0 \n", "L 628 0 \n", "L 628 4666 \n", "z\n", "\" id=\"DejaVuSans-50\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2631 2963 \n", "Q 2534 3019 2420 3045 \n", "Q 2306 3072 2169 3072 \n", "Q 1681 3072 1420 2755 \n", "Q 1159 2438 1159 1844 \n", "L 1159 0 \n", "L 581 0 \n", "L 581 3500 \n", "L 1159 3500 \n", "L 1159 2956 \n", "Q 1341 3275 1631 3429 \n", "Q 1922 3584 2338 3584 \n", "Q 2397 3584 2469 3576 \n", "Q 2541 3569 2628 3553 \n", "L 2631 2963 \n", "z\n", "\" id=\"DejaVuSans-72\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1959 3097 \n", "Q 1497 3097 1228 2736 \n", "Q 959 2375 959 1747 \n", "Q 959 1119 1226 758 \n", "Q 1494 397 1959 397 \n", "Q 2419 397 2687 759 \n", "Q 2956 1122 2956 1747 \n", "Q 2956 2369 2687 2733 \n", "Q 2419 3097 1959 3097 \n", "z\n", "M 1959 3584 \n", "Q 2709 3584 3137 3096 \n", "Q 3566 2609 3566 1747 \n", "Q 3566 888 3137 398 \n", "Q 2709 -91 1959 -91 \n", "Q 1206 -91 779 398 \n", "Q 353 888 353 1747 \n", "Q 353 2609 779 3096 \n", "Q 1206 3584 1959 3584 \n", "z\n", "\" id=\"DejaVuSans-6f\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1172 4494 \n", "L 1172 3500 \n", "L 2356 3500 \n", "L 2356 3053 \n", "L 1172 3053 \n", "L 1172 1153 \n", "Q 1172 725 1289 603 \n", "Q 1406 481 1766 481 \n", "L 2356 481 \n", "L 2356 0 \n", "L 1766 0 \n", "Q 1100 0 847 248 \n", "Q 594 497 594 1153 \n", "L 594 3053 \n", "L 172 3053 \n", "L 172 3500 \n", "L 594 3500 \n", "L 594 4494 \n", "L 1172 4494 \n", "z\n", "\" id=\"DejaVuSans-74\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 628 4666 \n", "L 1478 4666 \n", "L 3547 763 \n", "L 3547 4666 \n", "L 4159 4666 \n", "L 4159 0 \n", "L 3309 0 \n", "L 1241 3903 \n", "L 1241 0 \n", "L 628 0 \n", "L 628 4666 \n", "z\n", "\" id=\"DejaVuSans-4e\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3597 1894 \n", "L 3597 1613 \n", "L 953 1613 \n", "Q 991 1019 1311 708 \n", "Q 1631 397 2203 397 \n", "Q 2534 397 2845 478 \n", "Q 3156 559 3463 722 \n", "L 3463 178 \n", "Q 3153 47 2828 -22 \n", "Q 2503 -91 2169 -91 \n", "Q 1331 -91 842 396 \n", "Q 353 884 353 1716 \n", "Q 353 2575 817 3079 \n", "Q 1281 3584 2069 3584 \n", "Q 2775 3584 3186 3129 \n", "Q 3597 2675 3597 1894 \n", "z\n", "M 3022 2063 \n", "Q 3016 2534 2758 2815 \n", "Q 2500 3097 2075 3097 \n", "Q 1594 3097 1305 2825 \n", "Q 1016 2553 972 2059 \n", "L 3022 2063 \n", "z\n", "\" id=\"DejaVuSans-65\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-50\"/>\n", " <use x=\"58.552734\" xlink:href=\"#DejaVuSans-72\"/>\n", " <use x=\"97.416016\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"158.597656\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"197.806641\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"258.988281\" xlink:href=\"#DejaVuSans-4e\"/>\n", " <use x=\"333.792969\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"395.316406\" xlink:href=\"#DejaVuSans-74\"/>\n", " </g>\n", " </g>\n", " </g>\n", " </g>\n", " </g>\n", " <defs>\n", " <clipPath id=\"p754f80f5a3\">\n", " <rect height=\"163.08\" width=\"279\" x=\"56.805937\" y=\"22.318125\"/>\n", " </clipPath>\n", " </defs>\n", "</svg>\n"], "text/plain": ["<Figure size 360x216 with 1 Axes>"]}, "metadata": {}, "output_type": "display_data"}], "source": ["ax = plot_few_shot(protonet_accuracies, name=\"ProtoNet\", color=\"C1\")\n", "plt.show()\n", "plt.close()"]}, {"cell_type": "markdown", "id": "d99265a0", "metadata": {"papermill": {"duration": 0.04916, "end_time": "2021-10-10T16:37:26.050508", "exception": false, "start_time": "2021-10-10T16:37:26.001348", "status": "completed"}, "tags": []}, "source": ["As we initially expected, the performance of ProtoNet indeed increases the more samples we have.\n", "However, even with just two samples per class, we classify almost half of the images correctly, which is well above random accuracy (10%).\n", "The curve shows an exponentially dampend trend, meaning that adding 2 extra examples to $k=2$ has a much higher impact than adding 2 extra samples if we already have $k=16$.\n", "Nonetheless, we can say that ProtoNet adapts fairly well to new classes."]}, {"cell_type": "markdown", "id": "41e5a54a", "metadata": {"papermill": {"duration": 0.05058, "end_time": "2021-10-10T16:37:26.152476", "exception": false, "start_time": "2021-10-10T16:37:26.101896", "status": "completed"}, "tags": []}, "source": ["## MAML and ProtoMAML\n", "\n", "<div class=\"center-wrapper\"><div class=\"video-wrapper\"><iframe src=\"https://www.youtube.com/embed/xKcA6g-esH4\" title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen></iframe></div></div>"]}, {"cell_type": "markdown", "id": "209a64ec", "metadata": {"papermill": {"duration": 0.051648, "end_time": "2021-10-10T16:37:26.254669", "exception": false, "start_time": "2021-10-10T16:37:26.203021", "status": "completed"}, "tags": []}, "source": ["The second meta-learning algorithm we will look at is MAML, short for Model-Agnostic Meta-Learning.\n", "MAML is an optimization-based meta-learning algorithm, which means that it tries to adjust the standard optimization procedure to a few-shot setting.\n", "The idea of MAML is relatively simple: given a model, support and query set during training, we optimize the model for $m$ steps on the support set, and evaluate the gradients of the query loss with respect to the original model's parameters.\n", "For the same model, we do it for a few different support-query sets and accumulate the gradients.\n", "This results in learning a model that provides a good initialization for being quickly adapted to the training tasks.\n", "If we denote the model parameters with $\\theta$, we can visualize the procedure as follows (Figure credit - [Finn et al. ](http://proceedings.mlr.press/v70/finn17a.html)).\n", "\n", "<center width=\"100%\"><img src=\"https://github.com/PyTorchLightning/lightning-tutorials/raw/main/course_UvA-DL/12-meta-learning/MAML_figure.svg\" width=\"300px\"></center>"]}, {"cell_type": "markdown", "id": "d0f6ca26", "metadata": {"papermill": {"duration": 0.049624, "end_time": "2021-10-10T16:37:26.354505", "exception": false, "start_time": "2021-10-10T16:37:26.304881", "status": "completed"}, "tags": []}, "source": ["The full algorithm of MAML is therefore as follows.\n", "At each training step, we sample a batch of tasks, i.e., a batch of support-query set pairs.\n", "For each task $\\mathcal{T}_i$, we optimize a model $f_{\\theta}$ on the support set via SGD, and denote this model as $f_{\\theta_i'}$.\n", "We refer to this optimization as _inner loop_.\n", "Using this new model, we calculate the gradients of the original parameters, $\\theta$, with respect to the query loss on $f_{\\theta_i'}$.\n", "These gradients are accumulated over all tasks, and used to update $\\theta$.\n", "This is called _outer loop_ since we iterate over tasks.\n", "The full MAML algorithm is summarized below (Figure credit - [Finn et al. ](http://proceedings.mlr.press/v70/finn17a.html)).\n", "\n", "<center width=\"100%\"><img src=\"https://github.com/PyTorchLightning/lightning-tutorials/raw/main/course_UvA-DL/12-meta-learning/MAML_algorithm.svg\" width=\"400px\"></center>"]}, {"cell_type": "markdown", "id": "1555184d", "metadata": {"papermill": {"duration": 0.049633, "end_time": "2021-10-10T16:37:26.455355", "exception": false, "start_time": "2021-10-10T16:37:26.405722", "status": "completed"}, "tags": []}, "source": ["To obtain gradients for the initial parameters $\\theta$ from the optimized model $f_{\\theta_i'}$, we actually need second-order gradients, i.e. gradients of gradients, as the support set gradients depend on $\\theta$ as well.\n", "This makes MAML computationally expensive, especially when using mulitple inner loop steps.\n", "A simpler, yet almost equally well performing alternative is First-Order MAML (FOMAML) which only uses first-order gradients.\n", "This means that the second-order gradients are ignored, and we can calculate the outer loop gradients (line 10 in algorithm 2) simply by calculating the gradients with respect to $\\theta_i'$, and use those as update to $\\theta$.\n", "Hence, the new update rule becomes:\n", "$$\\theta\\leftarrow\\theta-\\beta\\sum_{\\mathcal{T}_i\\sim p(\\mathcal{T})}\\nabla_{\\theta_i'}\\mathcal{L}_{\\mathcal{T}_i}(f_{\\theta_i'})$$\n", "Note the change of $\\theta$ to $\\theta_i'$ for $\\nabla$."]}, {"cell_type": "markdown", "id": "fcef41fa", "metadata": {"papermill": {"duration": 0.050818, "end_time": "2021-10-10T16:37:26.556682", "exception": false, "start_time": "2021-10-10T16:37:26.505864", "status": "completed"}, "tags": []}, "source": ["### ProtoMAML\n", "\n", "A problem of MAML is how to design the output classification layer.\n", "In case all tasks have different number of classes, we need to initialize the output layer with zeros or randomly in every iteration.\n", "Even if we always have the same number of classes, we just start from random predictions.\n", "This requires several inner loop steps to reach a reasonable classification result.\n", "To overcome this problem, Triantafillou et al.\n", "(2020) propose to combine the merits of Prototypical Networks and MAML.\n", "Specifically, we can use prototypes to initialize our output layer to have a strong initialization.\n", "Thereby, it can be shown that the softmax over euclidean distances can be reformulated as a linear layer with softmax.\n", "To see this, let's first write out the negative euclidean distance between a feature vector $f_{\\theta}(\\mathbf{x}^{*})$ of a new data point $\\mathbf{x}^{*}$ to a prototype $\\mathbf{v}_c$ of class $c$:\n", "$$\n", "-||f_{\\theta}(\\mathbf{x}^{*})-\\mathbf{v}_c||^2=-f_{\\theta}(\\mathbf{x}^{*})^Tf_{\\theta}(\\mathbf{x}^{*})+2\\mathbf{v}_c^{T}f_{\\theta}(\\mathbf{x}^{*})-\\mathbf{v}_c^T\\mathbf{v}_c\n", "$$\n", "\n", "We perform the classification across all classes $c\\in\\mathcal{C}$ and take a softmax on the distance.\n", "Hence, any term that is same for all classes can be removed without changing the output probabilities.\n", "In the equation above, this is true for $-f_{\\theta}(\\mathbf{x}^{*})^Tf_{\\theta}(\\mathbf{x}^{*})$ since it is independent of any class prototype.\n", "Thus, we can write:\n", "\n", "$$\n", "-||f_{\\theta}(\\mathbf{x}^{*})-\\mathbf{v}_c||^2=2\\mathbf{v}_c^{T}f_{\\theta}(\\mathbf{x}^{*})-||\\mathbf{v}_c||^2+\\text{constant}\n", "$$\n", "\n", "Taking a second look at the equation above, it looks a lot like a linear layer.\n", "For this, we use $\\mathbf{W}_{c,\\cdot}=2\\mathbf{v}_c$ and $b_c=-||\\mathbf{v}_c||^2$ which gives us the linear layer $\\mathbf{W}f_{\\theta}(\\mathbf{x}^{*})+\\mathbf{b}$.\n", "Hence, if we initialize the output weight with twice the prototypes, and the biases by the negative squared L2 norm of the prototypes, we start with a Prototypical Network.\n", "MAML allows us to adapt this layer and the rest of the network further.\n", "\n", "In the following, we will implement First-Order ProtoMAML for few-shot classification.\n", "The implementation of MAML would be the same except the output layer initialization."]}, {"cell_type": "markdown", "id": "352f15a0", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.050087, "end_time": "2021-10-10T16:37:26.657875", "exception": false, "start_time": "2021-10-10T16:37:26.607788", "status": "completed"}, "tags": []}, "source": ["### ProtoMAML implementation\n", "\n", "For implementing ProtoMAML, we can follow Algorithm 2 with minor modifications.\n", "At each training step, we first sample a batch of tasks, and a support and query set for each task.\n", "In our case of few-shot classification, this means that we simply sample multiple support-query set pairs from our sampler.\n", "For each task, we finetune our current model on the support set.\n", "However, since we need to remember the original parameters for the other tasks, the outer loop gradient update and future training steps, we need to create a copy of our model, and finetune only the copy.\n", "We can copy a model by using standard Python functions like `deepcopy`.\n", "The inner loop is implemented in the function `adapt_few_shot` in the PyTorch Lightning module below.\n", "\n", "After finetuning the model, we apply it on the query set and calculate the first-order gradients with respect to the original parameters $\\theta$.\n", "In contrast to simple MAML, we also have to consider the gradients with respect to the output layer initialization, i.e. the prototypes, since they directly rely on $\\theta$.\n", "To realize this efficiently, we take two steps.\n", "First, we calculate the prototypes by applying the original model, i.e. not the copied model, on the support elements.\n", "When initializing the output layer, we detach the prototypes to stop the gradients.\n", "This is because in the inner loop itself, we do not want to consider gradients through the prototypes back to the original model.\n", "However, after the inner loop is finished, we re-attach the computation graph of the prototypes by writing `output_weight = (output_weight - init_weight).detach() + init_weight`.\n", "While this line does not change the value of the variable `output_weight`, it adds its dependency on the prototype initialization `init_weight`.\n", "Thus, if we call `.backward` on `output_weight`, we will automatically calculate the first-order gradients with respect to the prototype initialization in the original model.\n", "\n", "After calculating all gradients and summing them together in the original model, we can take a standard optimizer step.\n", "PyTorch Lightning's method is however designed to return a loss-tensor on which we call `.backward` first.\n", "Since this is not possible here, we need to perform the optimization step ourselves.\n", "All details can be found in the code below.\n", "\n", "For implementing (Proto-)MAML with second-order gradients, it is recommended to use libraries such as [$\\nabla$higher](https://github.com/facebookresearch/higher) from Facebook AI Research.\n", "For simplicity, we stick with first-order methods here."]}, {"cell_type": "code", "execution_count": 25, "id": "7fb5c1c7", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:26.777531Z", "iopub.status.busy": "2021-10-10T16:37:26.774558Z", "iopub.status.idle": "2021-10-10T16:37:26.779554Z", "shell.execute_reply": "2021-10-10T16:37:26.779118Z"}, "lines_to_next_cell": 2, "papermill": {"duration": 0.070015, "end_time": "2021-10-10T16:37:26.779661", "exception": false, "start_time": "2021-10-10T16:37:26.709646", "status": "completed"}, "tags": []}, "outputs": [], "source": ["class ProtoMAML(pl.LightningModule):\n", " def __init__(self, proto_dim, lr, lr_inner, lr_output, num_inner_steps):\n", " \"\"\"Inputs.\n", "\n", " proto_dim - Dimensionality of prototype feature space\n", " lr - Learning rate of the outer loop Adam optimizer\n", " lr_inner - Learning rate of the inner loop SGD optimizer\n", " lr_output - Learning rate for the output layer in the inner loop\n", " num_inner_steps - Number of inner loop updates to perform\n", " \"\"\"\n", " super().__init__()\n", " self.save_hyperparameters()\n", " self.model = get_convnet(output_size=self.hparams.proto_dim)\n", "\n", " def configure_optimizers(self):\n", " optimizer = optim.AdamW(self.parameters(), lr=self.hparams.lr)\n", " scheduler = optim.lr_scheduler.MultiStepLR(optimizer, milestones=[140, 180], gamma=0.1)\n", " return [optimizer], [scheduler]\n", "\n", " def run_model(self, local_model, output_weight, output_bias, imgs, labels):\n", " # Execute a model with given output layer weights and inputs\n", " feats = local_model(imgs)\n", " preds = F.linear(feats, output_weight, output_bias)\n", " loss = F.cross_entropy(preds, labels)\n", " acc = (preds.argmax(dim=1) == labels).float()\n", " return loss, preds, acc\n", "\n", " def adapt_few_shot(self, support_imgs, support_targets):\n", " # Determine prototype initialization\n", " support_feats = self.model(support_imgs)\n", " prototypes, classes = ProtoNet.calculate_prototypes(support_feats, support_targets)\n", " support_labels = (classes[None, :] == support_targets[:, None]).long().argmax(dim=-1)\n", " # Create inner-loop model and optimizer\n", " local_model = deepcopy(self.model)\n", " local_model.train()\n", " local_optim = optim.SGD(local_model.parameters(), lr=self.hparams.lr_inner)\n", " local_optim.zero_grad()\n", " # Create output layer weights with prototype-based initialization\n", " init_weight = 2 * prototypes\n", " init_bias = -torch.norm(prototypes, dim=1) ** 2\n", " output_weight = init_weight.detach().requires_grad_()\n", " output_bias = init_bias.detach().requires_grad_()\n", "\n", " # Optimize inner loop model on support set\n", " for _ in range(self.hparams.num_inner_steps):\n", " # Determine loss on the support set\n", " loss, _, _ = self.run_model(local_model, output_weight, output_bias, support_imgs, support_labels)\n", " # Calculate gradients and perform inner loop update\n", " loss.backward()\n", " local_optim.step()\n", " # Update output layer via SGD\n", " output_weight.data -= self.hparams.lr_output * output_weight.grad\n", " output_bias.data -= self.hparams.lr_output * output_bias.grad\n", " # Reset gradients\n", " local_optim.zero_grad()\n", " output_weight.grad.fill_(0)\n", " output_bias.grad.fill_(0)\n", "\n", " # Re-attach computation graph of prototypes\n", " output_weight = (output_weight - init_weight).detach() + init_weight\n", " output_bias = (output_bias - init_bias).detach() + init_bias\n", "\n", " return local_model, output_weight, output_bias, classes\n", "\n", " def outer_loop(self, batch, mode=\"train\"):\n", " accuracies = []\n", " losses = []\n", " self.model.zero_grad()\n", "\n", " # Determine gradients for batch of tasks\n", " for task_batch in batch:\n", " imgs, targets = task_batch\n", " support_imgs, query_imgs, support_targets, query_targets = split_batch(imgs, targets)\n", " # Perform inner loop adaptation\n", " local_model, output_weight, output_bias, classes = self.adapt_few_shot(support_imgs, support_targets)\n", " # Determine loss of query set\n", " query_labels = (classes[None, :] == query_targets[:, None]).long().argmax(dim=-1)\n", " loss, preds, acc = self.run_model(local_model, output_weight, output_bias, query_imgs, query_labels)\n", " # Calculate gradients for query set loss\n", " if mode == \"train\":\n", " loss.backward()\n", "\n", " for p_global, p_local in zip(self.model.parameters(), local_model.parameters()):\n", " p_global.grad += p_local.grad # First-order approx. -> add gradients of finetuned and base model\n", "\n", " accuracies.append(acc.mean().detach())\n", " losses.append(loss.detach())\n", "\n", " # Perform update of base model\n", " if mode == \"train\":\n", " opt = self.optimizers()\n", " opt.step()\n", " opt.zero_grad()\n", "\n", " self.log(\"%s_loss\" % mode, sum(losses) / len(losses))\n", " self.log(\"%s_acc\" % mode, sum(accuracies) / len(accuracies))\n", "\n", " def training_step(self, batch, batch_idx):\n", " self.outer_loop(batch, mode=\"train\")\n", " return None # Returning None means we skip the default training optimizer steps by PyTorch Lightning\n", "\n", " def validation_step(self, batch, batch_idx):\n", " # Validation requires to finetune a model, hence we need to enable gradients\n", " torch.set_grad_enabled(True)\n", " self.outer_loop(batch, mode=\"val\")\n", " torch.set_grad_enabled(False)"]}, {"cell_type": "markdown", "id": "175f6c04", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.049445, "end_time": "2021-10-10T16:37:26.879819", "exception": false, "start_time": "2021-10-10T16:37:26.830374", "status": "completed"}, "tags": []}, "source": ["### Training\n", "\n", "To train ProtoMAML, we need to change our sampling slightly.\n", "Instead of a single support-query set batch, we need to sample multiple.\n", "To implement this, we yet use another Sampler which combines multiple batches from a `FewShotBatchSampler`, and returns it afterwards.\n", "Additionally, we define a `collate_fn` for our data loader which takes the stack of support-query set images, and returns the tasks as a list.\n", "This makes it easier to process in our PyTorch Lightning module before.\n", "The implementation of the sampler can be found below."]}, {"cell_type": "code", "execution_count": 26, "id": "a64ff4e8", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:26.989336Z", "iopub.status.busy": "2021-10-10T16:37:26.988844Z", "iopub.status.idle": "2021-10-10T16:37:26.990910Z", "shell.execute_reply": "2021-10-10T16:37:26.990506Z"}, "papermill": {"duration": 0.059649, "end_time": "2021-10-10T16:37:26.991013", "exception": false, "start_time": "2021-10-10T16:37:26.931364", "status": "completed"}, "tags": []}, "outputs": [], "source": ["class TaskBatchSampler:\n", " def __init__(self, dataset_targets, batch_size, N_way, K_shot, include_query=False, shuffle=True):\n", " \"\"\"\n", " Inputs:\n", " dataset_targets - PyTorch tensor of the labels of the data elements.\n", " batch_size - Number of tasks to aggregate in a batch\n", " N_way - Number of classes to sample per batch.\n", " K_shot - Number of examples to sample per class in the batch.\n", " include_query - If True, returns batch of size N_way*K_shot*2, which\n", " can be split into support and query set. Simplifies\n", " the implementation of sampling the same classes but\n", " distinct examples for support and query set.\n", " shuffle - If True, examples and classes are newly shuffled in each\n", " iteration (for training)\n", " \"\"\"\n", " super().__init__()\n", " self.batch_sampler = FewShotBatchSampler(dataset_targets, N_way, K_shot, include_query, shuffle)\n", " self.task_batch_size = batch_size\n", " self.local_batch_size = self.batch_sampler.batch_size\n", "\n", " def __iter__(self):\n", " # Aggregate multiple batches before returning the indices\n", " batch_list = []\n", " for batch_idx, batch in enumerate(self.batch_sampler):\n", " batch_list.extend(batch)\n", " if (batch_idx + 1) % self.task_batch_size == 0:\n", " yield batch_list\n", " batch_list = []\n", "\n", " def __len__(self):\n", " return len(self.batch_sampler) // self.task_batch_size\n", "\n", " def get_collate_fn(self):\n", " # Returns a collate function that converts one big tensor into a list of task-specific tensors\n", " def collate_fn(item_list):\n", " imgs = torch.stack([img for img, target in item_list], dim=0)\n", " targets = torch.stack([target for img, target in item_list], dim=0)\n", " imgs = imgs.chunk(self.task_batch_size, dim=0)\n", " targets = targets.chunk(self.task_batch_size, dim=0)\n", " return list(zip(imgs, targets))\n", "\n", " return collate_fn"]}, {"cell_type": "markdown", "id": "a8e833ad", "metadata": {"papermill": {"duration": 0.050761, "end_time": "2021-10-10T16:37:27.091732", "exception": false, "start_time": "2021-10-10T16:37:27.040971", "status": "completed"}, "tags": []}, "source": ["The creation of the data loaders is with this sampler straight-forward.\n", "Note that since many images need to loaded for a training batch, it is recommended to use less workers than usual."]}, {"cell_type": "code", "execution_count": 27, "id": "579696ce", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:27.195877Z", "iopub.status.busy": "2021-10-10T16:37:27.195402Z", "iopub.status.idle": "2021-10-10T16:37:27.234232Z", "shell.execute_reply": "2021-10-10T16:37:27.233821Z"}, "papermill": {"duration": 0.092572, "end_time": "2021-10-10T16:37:27.234347", "exception": false, "start_time": "2021-10-10T16:37:27.141775", "status": "completed"}, "tags": []}, "outputs": [], "source": ["# Training constant (same as for ProtoNet)\n", "N_WAY = 5\n", "K_SHOT = 4\n", "\n", "# Training set\n", "train_protomaml_sampler = TaskBatchSampler(\n", " train_set.targets, include_query=True, N_way=N_WAY, K_shot=K_SHOT, batch_size=16\n", ")\n", "train_protomaml_loader = data.DataLoader(\n", " train_set, batch_sampler=train_protomaml_sampler, collate_fn=train_protomaml_sampler.get_collate_fn(), num_workers=2\n", ")\n", "\n", "# Validation set\n", "val_protomaml_sampler = TaskBatchSampler(\n", " val_set.targets,\n", " include_query=True,\n", " N_way=N_WAY,\n", " K_shot=K_SHOT,\n", " batch_size=1, # We do not update the parameters, hence the batch size is irrelevant here\n", " shuffle=False,\n", ")\n", "val_protomaml_loader = data.DataLoader(\n", " val_set, batch_sampler=val_protomaml_sampler, collate_fn=val_protomaml_sampler.get_collate_fn(), num_workers=2\n", ")"]}, {"cell_type": "markdown", "id": "483d09a8", "metadata": {"papermill": {"duration": 0.04969, "end_time": "2021-10-10T16:37:27.335586", "exception": false, "start_time": "2021-10-10T16:37:27.285896", "status": "completed"}, "tags": []}, "source": ["Now, we are ready to train our ProtoMAML.\n", "We use the same feature space size as for ProtoNet, but can use a higher learning rate since the outer loop gradients are accumulated over 16 batches.\n", "The inner loop learning rate is set to 0.1, which is much higher than the outer loop lr because we use SGD in the inner loop instead of Adam.\n", "Commonly, the learning rate for the output layer is higher than the base model is the base model is very deep or pre-trained.\n", "However, for our setup, we observed no noticable impact of using a different learning rate than the base model.\n", "The number of inner loop updates is another crucial hyperparmaeter, and depends on the similarity of our training tasks.\n", "Since all tasks are on images from the same dataset, we notice that a single inner loop update achieves similar performance as 3 or 5 while training considerably faster.\n", "However, especially in RL and NLP, larger number of inner loop steps are often needed."]}, {"cell_type": "code", "execution_count": 28, "id": "f65be6c5", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:27.441153Z", "iopub.status.busy": "2021-10-10T16:37:27.440678Z", "iopub.status.idle": "2021-10-10T16:37:27.503563Z", "shell.execute_reply": "2021-10-10T16:37:27.503082Z"}, "papermill": {"duration": 0.118168, "end_time": "2021-10-10T16:37:27.503674", "exception": false, "start_time": "2021-10-10T16:37:27.385506", "status": "completed"}, "tags": []}, "outputs": [{"name": "stderr", "output_type": "stream", "text": ["GPU available: True, used: True\n"]}, {"name": "stderr", "output_type": "stream", "text": ["TPU available: False, using: 0 TPU cores\n"]}, {"name": "stderr", "output_type": "stream", "text": ["IPU available: False, using: 0 IPUs\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Found pretrained model at saved_models/MetaLearning/ProtoMAML.ckpt, loading...\n"]}], "source": ["protomaml_model = train_model(\n", " ProtoMAML,\n", " proto_dim=64,\n", " lr=1e-3,\n", " lr_inner=0.1,\n", " lr_output=0.1,\n", " num_inner_steps=1, # Often values between 1 and 10\n", " train_loader=train_protomaml_loader,\n", " val_loader=val_protomaml_loader,\n", ")"]}, {"cell_type": "markdown", "id": "8cc7c232", "metadata": {"papermill": {"duration": 0.049852, "end_time": "2021-10-10T16:37:27.604342", "exception": false, "start_time": "2021-10-10T16:37:27.554490", "status": "completed"}, "tags": []}, "source": ["Let's have a look at the training TensorBoard."]}, {"cell_type": "code", "execution_count": 29, "id": "8bdec8ea", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:27.711240Z", "iopub.status.busy": "2021-10-10T16:37:27.710762Z", "iopub.status.idle": "2021-10-10T16:37:27.712848Z", "shell.execute_reply": "2021-10-10T16:37:27.712444Z"}, "papermill": {"duration": 0.05552, "end_time": "2021-10-10T16:37:27.712949", "exception": false, "start_time": "2021-10-10T16:37:27.657429", "status": "completed"}, "tags": []}, "outputs": [], "source": ["# Opens tensorboard in notebook. Adjust the path to your CHECKPOINT_PATH if needed\n", "# # %tensorboard --logdir ../saved_models/tutorial16/tensorboards/ProtoMAML/"]}, {"cell_type": "markdown", "id": "ffa8d4ab", "metadata": {"papermill": {"duration": 0.050609, "end_time": "2021-10-10T16:37:27.813989", "exception": false, "start_time": "2021-10-10T16:37:27.763380", "status": "completed"}, "tags": []}, "source": ["<center width=\"100%\"><img src=\"https://github.com/PyTorchLightning/lightning-tutorials/raw/main/course_UvA-DL/12-meta-learning/tensorboard_screenshot_ProtoMAML.png\" width=\"1100px\"></center>\n", "\n", "One obvious difference to ProtoNet is that the loss curves look much less noisy.\n", "This is because we average the outer loop gradients over multiple tasks, and thus have a smoother training curve.\n", "Additionally, we only have 15k training iterations after 200 epochs.\n", "This is again because of the task batches, which cause 16 times less iterations.\n", "However, each iteration has seen 16 times more data in this experiment.\n", "Thus, we still have a fair comparison between ProtoMAML and ProtoNet.\n", "At first sight on the validation accuracy, one would assume that\n", "ProtoNet performs superior to ProtoMAML, but we have to verify that with\n", "proper testing below."]}, {"cell_type": "markdown", "id": "1ef9ae57", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.051235, "end_time": "2021-10-10T16:37:27.917147", "exception": false, "start_time": "2021-10-10T16:37:27.865912", "status": "completed"}, "tags": []}, "source": ["### Testing\n", "\n", "We test ProtoMAML in the same manner as ProtoNet, namely by picking random examples in the test set as support sets and use the rest of the dataset as query set.\n", "Instead of just calculating the prototypes for all examples, we need to finetune a separate model for each support set.\n", "This is why this process is more expensive than ProtoNet, and in our case, testing $k=\\{2,4,8,16,32\\}$ can take almost an hour.\n", "Hence, we provide evaluation files besides the pretrained models."]}, {"cell_type": "code", "execution_count": 30, "id": "24b90577", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:28.039732Z", "iopub.status.busy": "2021-10-10T16:37:28.039190Z", "iopub.status.idle": "2021-10-10T16:37:28.041339Z", "shell.execute_reply": "2021-10-10T16:37:28.040864Z"}, "papermill": {"duration": 0.070613, "end_time": "2021-10-10T16:37:28.041443", "exception": false, "start_time": "2021-10-10T16:37:27.970830", "status": "completed"}, "tags": []}, "outputs": [], "source": ["def test_protomaml(model, dataset, k_shot=4):\n", " pl.seed_everything(42)\n", " model = model.to(device)\n", " num_classes = dataset.targets.unique().shape[0]\n", "\n", " # Data loader for full test set as query set\n", " full_dataloader = data.DataLoader(dataset, batch_size=128, num_workers=4, shuffle=False, drop_last=False)\n", " # Data loader for sampling support sets\n", " sampler = FewShotBatchSampler(\n", " dataset.targets, include_query=False, N_way=num_classes, K_shot=k_shot, shuffle=False, shuffle_once=False\n", " )\n", " sample_dataloader = data.DataLoader(dataset, batch_sampler=sampler, num_workers=2)\n", "\n", " # We iterate through the full dataset in two manners. First, to select the k-shot batch.\n", " # Second, the evaluate the model on all other examples\n", " accuracies = []\n", " for (support_imgs, support_targets), support_indices in tqdm(\n", " zip(sample_dataloader, sampler), \"Performing few-shot finetuning\"\n", " ):\n", " support_imgs = support_imgs.to(device)\n", " support_targets = support_targets.to(device)\n", " # Finetune new model on support set\n", " local_model, output_weight, output_bias, classes = model.adapt_few_shot(support_imgs, support_targets)\n", " with torch.no_grad(): # No gradients for query set needed\n", " local_model.eval()\n", " batch_acc = torch.zeros((0,), dtype=torch.float32, device=device)\n", " # Evaluate all examples in test dataset\n", " for query_imgs, query_targets in full_dataloader:\n", " query_imgs = query_imgs.to(device)\n", " query_targets = query_targets.to(device)\n", " query_labels = (classes[None, :] == query_targets[:, None]).long().argmax(dim=-1)\n", " _, _, acc = model.run_model(local_model, output_weight, output_bias, query_imgs, query_labels)\n", " batch_acc = torch.cat([batch_acc, acc.detach()], dim=0)\n", " # Exclude support set elements\n", " for s_idx in support_indices:\n", " batch_acc[s_idx] = 0\n", " batch_acc = batch_acc.sum().item() / (batch_acc.shape[0] - len(support_indices))\n", " accuracies.append(batch_acc)\n", " return mean(accuracies), stdev(accuracies)"]}, {"cell_type": "markdown", "id": "d580df69", "metadata": {"papermill": {"duration": 0.051584, "end_time": "2021-10-10T16:37:28.144161", "exception": false, "start_time": "2021-10-10T16:37:28.092577", "status": "completed"}, "tags": []}, "source": ["In contrast to training, it is recommended to use many more inner loop updates during testing.\n", "During training, we are not interested in getting the best model from the inner loop, but the model which can provide the best gradients.\n", "Hence, one update might be already sufficient in training, but for testing, it was often observed that larger number of updates can give a considerable performance boost.\n", "Thus, we change the inner loop updates to 200 before testing."]}, {"cell_type": "code", "execution_count": 31, "id": "a3a77c03", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:28.249335Z", "iopub.status.busy": "2021-10-10T16:37:28.248861Z", "iopub.status.idle": "2021-10-10T16:37:28.251118Z", "shell.execute_reply": "2021-10-10T16:37:28.250650Z"}, "papermill": {"duration": 0.056293, "end_time": "2021-10-10T16:37:28.251218", "exception": false, "start_time": "2021-10-10T16:37:28.194925", "status": "completed"}, "tags": []}, "outputs": [], "source": ["protomaml_model.hparams.num_inner_steps = 200"]}, {"cell_type": "markdown", "id": "5c8e75e8", "metadata": {"papermill": {"duration": 0.050389, "end_time": "2021-10-10T16:37:28.352727", "exception": false, "start_time": "2021-10-10T16:37:28.302338", "status": "completed"}, "tags": []}, "source": ["Now, we can test our model.\n", "For the pre-trained models, we provide a json file with the results to reduce evaluation time."]}, {"cell_type": "code", "execution_count": 32, "id": "a2ec75b4", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:28.464792Z", "iopub.status.busy": "2021-10-10T16:37:28.464316Z", "iopub.status.idle": "2021-10-10T16:37:28.467735Z", "shell.execute_reply": "2021-10-10T16:37:28.467269Z"}, "papermill": {"duration": 0.059702, "end_time": "2021-10-10T16:37:28.467837", "exception": false, "start_time": "2021-10-10T16:37:28.408135", "status": "completed"}, "tags": []}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Accuracy for k=2: 42.89% (+-3.82%)\n", "Accuracy for k=4: 52.27% (+-2.72%)\n", "Accuracy for k=8: 59.23% (+-1.50%)\n", "Accuracy for k=16: 63.94% (+-1.24%)\n", "Accuracy for k=32: 67.57% (+-0.90%)\n"]}], "source": ["protomaml_result_file = os.path.join(CHECKPOINT_PATH, \"protomaml_fewshot.json\")\n", "\n", "if os.path.isfile(protomaml_result_file):\n", " # Load pre-computed results\n", " with open(protomaml_result_file) as f:\n", " protomaml_accuracies = json.load(f)\n", " protomaml_accuracies = {int(k): v for k, v in protomaml_accuracies.items()}\n", "else:\n", " # Perform same experiments as for ProtoNet\n", " protomaml_accuracies = dict()\n", " for k in [2, 4, 8, 16, 32]:\n", " protomaml_accuracies[k] = test_protomaml(protomaml_model, test_set, k_shot=k)\n", " # Export results\n", " with open(protomaml_result_file, \"w\") as f:\n", " json.dump(protomaml_accuracies, f, indent=4)\n", "\n", "for k in protomaml_accuracies:\n", " print(\n", " \"Accuracy for k=%i: %4.2f%% (+-%4.2f%%)\"\n", " % (k, 100.0 * protomaml_accuracies[k][0], 100.0 * protomaml_accuracies[k][1])\n", " )"]}, {"cell_type": "markdown", "id": "a3b76b70", "metadata": {"papermill": {"duration": 0.051095, "end_time": "2021-10-10T16:37:28.569910", "exception": false, "start_time": "2021-10-10T16:37:28.518815", "status": "completed"}, "tags": []}, "source": ["Again, let's plot the results in our plot from before."]}, {"cell_type": "code", "execution_count": 33, "id": "c19a1cd0", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:28.700295Z", "iopub.status.busy": "2021-10-10T16:37:28.688544Z", "iopub.status.idle": "2021-10-10T16:37:28.982037Z", "shell.execute_reply": "2021-10-10T16:37:28.981554Z"}, "papermill": {"duration": 0.36056, "end_time": "2021-10-10T16:37:28.982151", "exception": false, "start_time": "2021-10-10T16:37:28.621591", "status": "completed"}, "tags": []}, "outputs": [{"data": {"application/pdf": "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\n", "image/svg+xml": ["<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n", "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n", " \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n", "<svg height=\"228.357813pt\" version=\"1.1\" viewBox=\"0 0 368.640937 228.357813\" width=\"368.640937pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n", " <metadata>\n", " <rdf:RDF xmlns:cc=\"http://creativecommons.org/ns#\" xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\">\n", " <cc:Work>\n", " <dc:type rdf:resource=\"http://purl.org/dc/dcmitype/StillImage\"/>\n", " <dc:date>2021-10-10T18:37:28.787735</dc:date>\n", " <dc:format>image/svg+xml</dc:format>\n", " <dc:creator>\n", " <cc:Agent>\n", " <dc:title>Matplotlib v3.4.3, https://matplotlib.org/</dc:title>\n", " </cc:Agent>\n", " </dc:creator>\n", " </cc:Work>\n", " </rdf:RDF>\n", " </metadata>\n", " <defs>\n", " <style type=\"text/css\">*{stroke-linecap:butt;stroke-linejoin:round;}</style>\n", " </defs>\n", " <g id=\"figure_1\">\n", " <g id=\"patch_1\">\n", " <path d=\"M 0 228.357813 \n", "L 368.640937 228.357813 \n", "L 368.640937 0 \n", "L 0 0 \n", "z\n", "\" style=\"fill:#ffffff;\"/>\n", " </g>\n", " <g id=\"axes_1\">\n", " <g id=\"patch_2\">\n", " <path d=\"M 56.805937 185.398125 \n", "L 335.805938 185.398125 \n", "L 335.805938 22.318125 \n", "L 56.805937 22.318125 \n", "z\n", "\" style=\"fill:#eaeaf2;\"/>\n", " </g>\n", " <g id=\"matplotlib.axis_1\">\n", " <g id=\"xtick_1\">\n", " <g id=\"line2d_1\">\n", " <path clip-path=\"url(#p92687efc31)\" d=\"M 65.524687 185.398125 \n", "L 65.524687 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_1\">\n", " <!-- 2 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(62.025312 203.256406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 1228 531 \n", "L 3431 531 \n", "L 3431 0 \n", "L 469 0 \n", "L 469 531 \n", "Q 828 903 1448 1529 \n", "Q 2069 2156 2228 2338 \n", "Q 2531 2678 2651 2914 \n", "Q 2772 3150 2772 3378 \n", "Q 2772 3750 2511 3984 \n", "Q 2250 4219 1831 4219 \n", "Q 1534 4219 1204 4116 \n", "Q 875 4013 500 3803 \n", "L 500 4441 \n", "Q 881 4594 1212 4672 \n", "Q 1544 4750 1819 4750 \n", "Q 2544 4750 2975 4387 \n", "Q 3406 4025 3406 3419 \n", "Q 3406 3131 3298 2873 \n", "Q 3191 2616 2906 2266 \n", "Q 2828 2175 2409 1742 \n", "Q 1991 1309 1228 531 \n", "z\n", "\" id=\"DejaVuSans-32\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-32\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_2\">\n", " <g id=\"line2d_2\">\n", " <path clip-path=\"url(#p92687efc31)\" d=\"M 82.962187 185.398125 \n", "L 82.962187 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_2\">\n", " <!-- 4 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(79.462812 203.256406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 2419 4116 \n", "L 825 1625 \n", "L 2419 1625 \n", "L 2419 4116 \n", "z\n", "M 2253 4666 \n", "L 3047 4666 \n", "L 3047 1625 \n", "L 3713 1625 \n", "L 3713 1100 \n", "L 3047 1100 \n", "L 3047 0 \n", "L 2419 0 \n", "L 2419 1100 \n", "L 313 1100 \n", "L 313 1709 \n", "L 2253 4666 \n", "z\n", "\" id=\"DejaVuSans-34\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-34\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_3\">\n", " <g id=\"line2d_3\">\n", " <path clip-path=\"url(#p92687efc31)\" d=\"M 117.837187 185.398125 \n", "L 117.837187 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_3\">\n", " <!-- 8 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(114.337812 203.256406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 2034 2216 \n", "Q 1584 2216 1326 1975 \n", "Q 1069 1734 1069 1313 \n", "Q 1069 891 1326 650 \n", "Q 1584 409 2034 409 \n", "Q 2484 409 2743 651 \n", "Q 3003 894 3003 1313 \n", "Q 3003 1734 2745 1975 \n", "Q 2488 2216 2034 2216 \n", "z\n", "M 1403 2484 \n", "Q 997 2584 770 2862 \n", "Q 544 3141 544 3541 \n", "Q 544 4100 942 4425 \n", "Q 1341 4750 2034 4750 \n", "Q 2731 4750 3128 4425 \n", "Q 3525 4100 3525 3541 \n", "Q 3525 3141 3298 2862 \n", "Q 3072 2584 2669 2484 \n", "Q 3125 2378 3379 2068 \n", "Q 3634 1759 3634 1313 \n", "Q 3634 634 3220 271 \n", "Q 2806 -91 2034 -91 \n", "Q 1263 -91 848 271 \n", "Q 434 634 434 1313 \n", "Q 434 1759 690 2068 \n", "Q 947 2378 1403 2484 \n", "z\n", "M 1172 3481 \n", "Q 1172 3119 1398 2916 \n", "Q 1625 2713 2034 2713 \n", "Q 2441 2713 2670 2916 \n", "Q 2900 3119 2900 3481 \n", "Q 2900 3844 2670 4047 \n", "Q 2441 4250 2034 4250 \n", "Q 1625 4250 1398 4047 \n", "Q 1172 3844 1172 3481 \n", "z\n", "\" id=\"DejaVuSans-38\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-38\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_4\">\n", " <g id=\"line2d_4\">\n", " <path clip-path=\"url(#p92687efc31)\" d=\"M 187.587187 185.398125 \n", "L 187.587187 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_4\">\n", " <!-- 16 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(180.588437 203.256406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 794 531 \n", "L 1825 531 \n", "L 1825 4091 \n", "L 703 3866 \n", "L 703 4441 \n", "L 1819 4666 \n", "L 2450 4666 \n", "L 2450 531 \n", "L 3481 531 \n", "L 3481 0 \n", "L 794 0 \n", "L 794 531 \n", "z\n", "\" id=\"DejaVuSans-31\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2113 2584 \n", "Q 1688 2584 1439 2293 \n", "Q 1191 2003 1191 1497 \n", "Q 1191 994 1439 701 \n", "Q 1688 409 2113 409 \n", "Q 2538 409 2786 701 \n", "Q 3034 994 3034 1497 \n", "Q 3034 2003 2786 2293 \n", "Q 2538 2584 2113 2584 \n", "z\n", "M 3366 4563 \n", "L 3366 3988 \n", "Q 3128 4100 2886 4159 \n", "Q 2644 4219 2406 4219 \n", "Q 1781 4219 1451 3797 \n", "Q 1122 3375 1075 2522 \n", "Q 1259 2794 1537 2939 \n", "Q 1816 3084 2150 3084 \n", "Q 2853 3084 3261 2657 \n", "Q 3669 2231 3669 1497 \n", "Q 3669 778 3244 343 \n", "Q 2819 -91 2113 -91 \n", "Q 1303 -91 875 529 \n", "Q 447 1150 447 2328 \n", "Q 447 3434 972 4092 \n", "Q 1497 4750 2381 4750 \n", "Q 2619 4750 2861 4703 \n", "Q 3103 4656 3366 4563 \n", "z\n", "\" id=\"DejaVuSans-36\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-31\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-36\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_5\">\n", " <g id=\"line2d_5\">\n", " <path clip-path=\"url(#p92687efc31)\" d=\"M 327.087188 185.398125 \n", "L 327.087188 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_5\">\n", " <!-- 32 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(320.088438 203.256406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 2597 2516 \n", "Q 3050 2419 3304 2112 \n", "Q 3559 1806 3559 1356 \n", "Q 3559 666 3084 287 \n", "Q 2609 -91 1734 -91 \n", "Q 1441 -91 1130 -33 \n", "Q 819 25 488 141 \n", "L 488 750 \n", "Q 750 597 1062 519 \n", "Q 1375 441 1716 441 \n", "Q 2309 441 2620 675 \n", "Q 2931 909 2931 1356 \n", "Q 2931 1769 2642 2001 \n", "Q 2353 2234 1838 2234 \n", "L 1294 2234 \n", "L 1294 2753 \n", "L 1863 2753 \n", "Q 2328 2753 2575 2939 \n", "Q 2822 3125 2822 3475 \n", "Q 2822 3834 2567 4026 \n", "Q 2313 4219 1838 4219 \n", "Q 1578 4219 1281 4162 \n", "Q 984 4106 628 3988 \n", "L 628 4550 \n", "Q 988 4650 1302 4700 \n", "Q 1616 4750 1894 4750 \n", "Q 2613 4750 3031 4423 \n", "Q 3450 4097 3450 3541 \n", "Q 3450 3153 3228 2886 \n", "Q 3006 2619 2597 2516 \n", "z\n", "\" id=\"DejaVuSans-33\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-33\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-32\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"text_6\">\n", " <!-- Number of shots per class -->\n", " <g style=\"fill:#262626;\" transform=\"translate(107.82 218.662188)scale(0.12 -0.12)\">\n", " <defs>\n", " <path d=\"M 588 4666 \n", "L 1931 4666 \n", "L 3628 1466 \n", "L 3628 4666 \n", "L 4769 4666 \n", "L 4769 0 \n", "L 3425 0 \n", "L 1728 3200 \n", "L 1728 0 \n", "L 588 0 \n", "L 588 4666 \n", "z\n", "\" id=\"DejaVuSans-Bold-4e\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 500 1363 \n", "L 500 3500 \n", "L 1625 3500 \n", "L 1625 3150 \n", "Q 1625 2866 1622 2436 \n", "Q 1619 2006 1619 1863 \n", "Q 1619 1441 1641 1255 \n", "Q 1663 1069 1716 984 \n", "Q 1784 875 1895 815 \n", "Q 2006 756 2150 756 \n", "Q 2500 756 2700 1025 \n", "Q 2900 1294 2900 1772 \n", "L 2900 3500 \n", "L 4019 3500 \n", "L 4019 0 \n", "L 2900 0 \n", "L 2900 506 \n", "Q 2647 200 2364 54 \n", "Q 2081 -91 1741 -91 \n", "Q 1134 -91 817 281 \n", "Q 500 653 500 1363 \n", "z\n", "\" id=\"DejaVuSans-Bold-75\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3781 2919 \n", "Q 3994 3244 4286 3414 \n", "Q 4578 3584 4928 3584 \n", "Q 5531 3584 5847 3212 \n", "Q 6163 2841 6163 2131 \n", "L 6163 0 \n", "L 5038 0 \n", "L 5038 1825 \n", "Q 5041 1866 5042 1909 \n", "Q 5044 1953 5044 2034 \n", "Q 5044 2406 4934 2573 \n", "Q 4825 2741 4581 2741 \n", "Q 4263 2741 4089 2478 \n", "Q 3916 2216 3909 1719 \n", "L 3909 0 \n", "L 2784 0 \n", "L 2784 1825 \n", "Q 2784 2406 2684 2573 \n", "Q 2584 2741 2328 2741 \n", "Q 2006 2741 1831 2477 \n", "Q 1656 2213 1656 1722 \n", "L 1656 0 \n", "L 531 0 \n", "L 531 3500 \n", "L 1656 3500 \n", "L 1656 2988 \n", "Q 1863 3284 2130 3434 \n", "Q 2397 3584 2719 3584 \n", "Q 3081 3584 3359 3409 \n", "Q 3638 3234 3781 2919 \n", "z\n", "\" id=\"DejaVuSans-Bold-6d\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2400 722 \n", "Q 2759 722 2948 984 \n", "Q 3138 1247 3138 1747 \n", "Q 3138 2247 2948 2509 \n", "Q 2759 2772 2400 2772 \n", "Q 2041 2772 1848 2508 \n", "Q 1656 2244 1656 1747 \n", "Q 1656 1250 1848 986 \n", "Q 2041 722 2400 722 \n", "z\n", "M 1656 2988 \n", "Q 1888 3294 2169 3439 \n", "Q 2450 3584 2816 3584 \n", "Q 3463 3584 3878 3070 \n", "Q 4294 2556 4294 1747 \n", "Q 4294 938 3878 423 \n", "Q 3463 -91 2816 -91 \n", "Q 2450 -91 2169 54 \n", "Q 1888 200 1656 506 \n", "L 1656 0 \n", "L 538 0 \n", "L 538 4863 \n", "L 1656 4863 \n", "L 1656 2988 \n", "z\n", "\" id=\"DejaVuSans-Bold-62\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 4031 1759 \n", "L 4031 1441 \n", "L 1416 1441 \n", "Q 1456 1047 1700 850 \n", "Q 1944 653 2381 653 \n", "Q 2734 653 3104 758 \n", "Q 3475 863 3866 1075 \n", "L 3866 213 \n", "Q 3469 63 3072 -14 \n", "Q 2675 -91 2278 -91 \n", "Q 1328 -91 801 392 \n", "Q 275 875 275 1747 \n", "Q 275 2603 792 3093 \n", "Q 1309 3584 2216 3584 \n", "Q 3041 3584 3536 3087 \n", "Q 4031 2591 4031 1759 \n", "z\n", "M 2881 2131 \n", "Q 2881 2450 2695 2645 \n", "Q 2509 2841 2209 2841 \n", "Q 1884 2841 1681 2658 \n", "Q 1478 2475 1428 2131 \n", "L 2881 2131 \n", "z\n", "\" id=\"DejaVuSans-Bold-65\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3138 2547 \n", "Q 2991 2616 2845 2648 \n", "Q 2700 2681 2553 2681 \n", "Q 2122 2681 1889 2404 \n", "Q 1656 2128 1656 1613 \n", "L 1656 0 \n", "L 538 0 \n", "L 538 3500 \n", "L 1656 3500 \n", "L 1656 2925 \n", "Q 1872 3269 2151 3426 \n", "Q 2431 3584 2822 3584 \n", "Q 2878 3584 2943 3579 \n", "Q 3009 3575 3134 3559 \n", "L 3138 2547 \n", "z\n", "\" id=\"DejaVuSans-Bold-72\" transform=\"scale(0.015625)\"/>\n", " <path id=\"DejaVuSans-Bold-20\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2203 2784 \n", "Q 1831 2784 1636 2517 \n", "Q 1441 2250 1441 1747 \n", "Q 1441 1244 1636 976 \n", "Q 1831 709 2203 709 \n", "Q 2569 709 2762 976 \n", "Q 2956 1244 2956 1747 \n", "Q 2956 2250 2762 2517 \n", "Q 2569 2784 2203 2784 \n", "z\n", "M 2203 3584 \n", "Q 3106 3584 3614 3096 \n", "Q 4122 2609 4122 1747 \n", "Q 4122 884 3614 396 \n", "Q 3106 -91 2203 -91 \n", "Q 1297 -91 786 396 \n", "Q 275 884 275 1747 \n", "Q 275 2609 786 3096 \n", "Q 1297 3584 2203 3584 \n", "z\n", "\" id=\"DejaVuSans-Bold-6f\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2841 4863 \n", "L 2841 4128 \n", "L 2222 4128 \n", "Q 1984 4128 1890 4042 \n", "Q 1797 3956 1797 3744 \n", "L 1797 3500 \n", "L 2753 3500 \n", "L 2753 2700 \n", "L 1797 2700 \n", "L 1797 0 \n", "L 678 0 \n", "L 678 2700 \n", "L 122 2700 \n", "L 122 3500 \n", "L 678 3500 \n", "L 678 3744 \n", "Q 678 4316 997 4589 \n", "Q 1316 4863 1984 4863 \n", "L 2841 4863 \n", "z\n", "\" id=\"DejaVuSans-Bold-66\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3272 3391 \n", "L 3272 2541 \n", "Q 2913 2691 2578 2766 \n", "Q 2244 2841 1947 2841 \n", "Q 1628 2841 1473 2761 \n", "Q 1319 2681 1319 2516 \n", "Q 1319 2381 1436 2309 \n", "Q 1553 2238 1856 2203 \n", "L 2053 2175 \n", "Q 2913 2066 3209 1816 \n", "Q 3506 1566 3506 1031 \n", "Q 3506 472 3093 190 \n", "Q 2681 -91 1863 -91 \n", "Q 1516 -91 1145 -36 \n", "Q 775 19 384 128 \n", "L 384 978 \n", "Q 719 816 1070 734 \n", "Q 1422 653 1784 653 \n", "Q 2113 653 2278 743 \n", "Q 2444 834 2444 1013 \n", "Q 2444 1163 2330 1236 \n", "Q 2216 1309 1875 1350 \n", "L 1678 1375 \n", "Q 931 1469 631 1722 \n", "Q 331 1975 331 2491 \n", "Q 331 3047 712 3315 \n", "Q 1094 3584 1881 3584 \n", "Q 2191 3584 2531 3537 \n", "Q 2872 3491 3272 3391 \n", "z\n", "\" id=\"DejaVuSans-Bold-73\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 4056 2131 \n", "L 4056 0 \n", "L 2931 0 \n", "L 2931 347 \n", "L 2931 1625 \n", "Q 2931 2084 2911 2256 \n", "Q 2891 2428 2841 2509 \n", "Q 2775 2619 2662 2680 \n", "Q 2550 2741 2406 2741 \n", "Q 2056 2741 1856 2470 \n", "Q 1656 2200 1656 1722 \n", "L 1656 0 \n", "L 538 0 \n", "L 538 4863 \n", "L 1656 4863 \n", "L 1656 2988 \n", "Q 1909 3294 2193 3439 \n", "Q 2478 3584 2822 3584 \n", "Q 3428 3584 3742 3212 \n", "Q 4056 2841 4056 2131 \n", "z\n", "\" id=\"DejaVuSans-Bold-68\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1759 4494 \n", "L 1759 3500 \n", "L 2913 3500 \n", "L 2913 2700 \n", "L 1759 2700 \n", "L 1759 1216 \n", "Q 1759 972 1856 886 \n", "Q 1953 800 2241 800 \n", "L 2816 800 \n", "L 2816 0 \n", "L 1856 0 \n", "Q 1194 0 917 276 \n", "Q 641 553 641 1216 \n", "L 641 2700 \n", "L 84 2700 \n", "L 84 3500 \n", "L 641 3500 \n", "L 641 4494 \n", "L 1759 4494 \n", "z\n", "\" id=\"DejaVuSans-Bold-74\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1656 506 \n", "L 1656 -1331 \n", "L 538 -1331 \n", "L 538 3500 \n", "L 1656 3500 \n", "L 1656 2988 \n", "Q 1888 3294 2169 3439 \n", "Q 2450 3584 2816 3584 \n", "Q 3463 3584 3878 3070 \n", "Q 4294 2556 4294 1747 \n", "Q 4294 938 3878 423 \n", "Q 3463 -91 2816 -91 \n", "Q 2450 -91 2169 54 \n", "Q 1888 200 1656 506 \n", "z\n", "M 2400 2772 \n", "Q 2041 2772 1848 2508 \n", "Q 1656 2244 1656 1747 \n", "Q 1656 1250 1848 986 \n", "Q 2041 722 2400 722 \n", "Q 2759 722 2948 984 \n", "Q 3138 1247 3138 1747 \n", "Q 3138 2247 2948 2509 \n", "Q 2759 2772 2400 2772 \n", "z\n", "\" id=\"DejaVuSans-Bold-70\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3366 3391 \n", "L 3366 2478 \n", "Q 3138 2634 2908 2709 \n", "Q 2678 2784 2431 2784 \n", "Q 1963 2784 1702 2511 \n", "Q 1441 2238 1441 1747 \n", "Q 1441 1256 1702 982 \n", "Q 1963 709 2431 709 \n", "Q 2694 709 2930 787 \n", "Q 3166 866 3366 1019 \n", "L 3366 103 \n", "Q 3103 6 2833 -42 \n", "Q 2563 -91 2291 -91 \n", "Q 1344 -91 809 395 \n", "Q 275 881 275 1747 \n", "Q 275 2613 809 3098 \n", "Q 1344 3584 2291 3584 \n", "Q 2566 3584 2833 3536 \n", "Q 3100 3488 3366 3391 \n", "z\n", "\" id=\"DejaVuSans-Bold-63\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 538 4863 \n", "L 1656 4863 \n", "L 1656 0 \n", "L 538 0 \n", "L 538 4863 \n", "z\n", "\" id=\"DejaVuSans-Bold-6c\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2106 1575 \n", "Q 1756 1575 1579 1456 \n", "Q 1403 1338 1403 1106 \n", "Q 1403 894 1545 773 \n", "Q 1688 653 1941 653 \n", "Q 2256 653 2472 879 \n", "Q 2688 1106 2688 1447 \n", "L 2688 1575 \n", "L 2106 1575 \n", "z\n", "M 3816 1997 \n", "L 3816 0 \n", "L 2688 0 \n", "L 2688 519 \n", "Q 2463 200 2181 54 \n", "Q 1900 -91 1497 -91 \n", "Q 953 -91 614 226 \n", "Q 275 544 275 1050 \n", "Q 275 1666 698 1953 \n", "Q 1122 2241 2028 2241 \n", "L 2688 2241 \n", "L 2688 2328 \n", "Q 2688 2594 2478 2717 \n", "Q 2269 2841 1825 2841 \n", "Q 1466 2841 1156 2769 \n", "Q 847 2697 581 2553 \n", "L 581 3406 \n", "Q 941 3494 1303 3539 \n", "Q 1666 3584 2028 3584 \n", "Q 2975 3584 3395 3211 \n", "Q 3816 2838 3816 1997 \n", "z\n", "\" id=\"DejaVuSans-Bold-61\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-Bold-4e\"/>\n", " <use x=\"83.691406\" xlink:href=\"#DejaVuSans-Bold-75\"/>\n", " <use x=\"154.882812\" xlink:href=\"#DejaVuSans-Bold-6d\"/>\n", " <use x=\"259.082031\" xlink:href=\"#DejaVuSans-Bold-62\"/>\n", " <use x=\"330.664062\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"398.486328\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"447.802734\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"482.617188\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"551.318359\" xlink:href=\"#DejaVuSans-Bold-66\"/>\n", " <use x=\"594.824219\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"629.638672\" xlink:href=\"#DejaVuSans-Bold-73\"/>\n", " <use x=\"689.160156\" xlink:href=\"#DejaVuSans-Bold-68\"/>\n", " <use x=\"760.351562\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"829.052734\" xlink:href=\"#DejaVuSans-Bold-74\"/>\n", " <use x=\"876.855469\" xlink:href=\"#DejaVuSans-Bold-73\"/>\n", " <use x=\"936.376953\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"971.191406\" xlink:href=\"#DejaVuSans-Bold-70\"/>\n", " <use x=\"1042.773438\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"1110.595703\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"1159.912109\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"1194.726562\" xlink:href=\"#DejaVuSans-Bold-63\"/>\n", " <use x=\"1254.003906\" xlink:href=\"#DejaVuSans-Bold-6c\"/>\n", " <use x=\"1288.28125\" xlink:href=\"#DejaVuSans-Bold-61\"/>\n", " <use x=\"1355.761719\" xlink:href=\"#DejaVuSans-Bold-73\"/>\n", " <use x=\"1415.283203\" xlink:href=\"#DejaVuSans-Bold-73\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"matplotlib.axis_2\">\n", " <g id=\"ytick_1\">\n", " <g id=\"line2d_6\">\n", " <path clip-path=\"url(#p92687efc31)\" d=\"M 56.805937 173.33061 \n", "L 335.805938 173.33061 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_7\">\n", " <!-- 0.40 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 177.509751)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 2034 4250 \n", "Q 1547 4250 1301 3770 \n", "Q 1056 3291 1056 2328 \n", "Q 1056 1369 1301 889 \n", "Q 1547 409 2034 409 \n", "Q 2525 409 2770 889 \n", "Q 3016 1369 3016 2328 \n", "Q 3016 3291 2770 3770 \n", "Q 2525 4250 2034 4250 \n", "z\n", "M 2034 4750 \n", "Q 2819 4750 3233 4129 \n", "Q 3647 3509 3647 2328 \n", "Q 3647 1150 3233 529 \n", "Q 2819 -91 2034 -91 \n", "Q 1250 -91 836 529 \n", "Q 422 1150 422 2328 \n", "Q 422 3509 836 4129 \n", "Q 1250 4750 2034 4750 \n", "z\n", "\" id=\"DejaVuSans-30\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 684 794 \n", "L 1344 794 \n", "L 1344 0 \n", "L 684 0 \n", "L 684 794 \n", "z\n", "\" id=\"DejaVuSans-2e\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-34\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_2\">\n", " <g id=\"line2d_7\">\n", " <path clip-path=\"url(#p92687efc31)\" d=\"M 56.805937 148.115424 \n", "L 335.805938 148.115424 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_8\">\n", " <!-- 0.45 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 152.294564)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 691 4666 \n", "L 3169 4666 \n", "L 3169 4134 \n", "L 1269 4134 \n", "L 1269 2991 \n", "Q 1406 3038 1543 3061 \n", "Q 1681 3084 1819 3084 \n", "Q 2600 3084 3056 2656 \n", "Q 3513 2228 3513 1497 \n", "Q 3513 744 3044 326 \n", "Q 2575 -91 1722 -91 \n", "Q 1428 -91 1123 -41 \n", "Q 819 9 494 109 \n", "L 494 744 \n", "Q 775 591 1075 516 \n", "Q 1375 441 1709 441 \n", "Q 2250 441 2565 725 \n", "Q 2881 1009 2881 1497 \n", "Q 2881 1984 2565 2268 \n", "Q 2250 2553 1709 2553 \n", "Q 1456 2553 1204 2497 \n", "Q 953 2441 691 2322 \n", "L 691 4666 \n", "z\n", "\" id=\"DejaVuSans-35\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-34\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-35\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_3\">\n", " <g id=\"line2d_8\">\n", " <path clip-path=\"url(#p92687efc31)\" d=\"M 56.805937 122.900237 \n", "L 335.805938 122.900237 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_9\">\n", " <!-- 0.50 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 127.079377)scale(0.11 -0.11)\">\n", " <use xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-35\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_4\">\n", " <g id=\"line2d_9\">\n", " <path clip-path=\"url(#p92687efc31)\" d=\"M 56.805937 97.68505 \n", "L 335.805938 97.68505 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_10\">\n", " <!-- 0.55 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 101.864191)scale(0.11 -0.11)\">\n", " <use xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-35\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-35\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_5\">\n", " <g id=\"line2d_10\">\n", " <path clip-path=\"url(#p92687efc31)\" d=\"M 56.805937 72.469863 \n", "L 335.805938 72.469863 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_11\">\n", " <!-- 0.60 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 76.649004)scale(0.11 -0.11)\">\n", " <use xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-36\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_6\">\n", " <g id=\"line2d_11\">\n", " <path clip-path=\"url(#p92687efc31)\" d=\"M 56.805937 47.254676 \n", "L 335.805938 47.254676 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_12\">\n", " <!-- 0.65 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 51.433817)scale(0.11 -0.11)\">\n", " <use xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-36\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-35\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"text_13\">\n", " <!-- Accuracy -->\n", " <g style=\"fill:#262626;\" transform=\"translate(16.224375 134.3625)rotate(-90)scale(0.12 -0.12)\">\n", " <defs>\n", " <path d=\"M 3419 850 \n", "L 1538 850 \n", "L 1241 0 \n", "L 31 0 \n", "L 1759 4666 \n", "L 3194 4666 \n", "L 4922 0 \n", "L 3713 0 \n", "L 3419 850 \n", "z\n", "M 1838 1716 \n", "L 3116 1716 \n", "L 2478 3572 \n", "L 1838 1716 \n", "z\n", "\" id=\"DejaVuSans-Bold-41\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 78 3500 \n", "L 1197 3500 \n", "L 2138 1125 \n", "L 2938 3500 \n", "L 4056 3500 \n", "L 2584 -331 \n", "Q 2363 -916 2067 -1148 \n", "Q 1772 -1381 1288 -1381 \n", "L 641 -1381 \n", "L 641 -647 \n", "L 991 -647 \n", "Q 1275 -647 1404 -556 \n", "Q 1534 -466 1606 -231 \n", "L 1638 -134 \n", "L 78 3500 \n", "z\n", "\" id=\"DejaVuSans-Bold-79\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-Bold-41\"/>\n", " <use x=\"77.392578\" xlink:href=\"#DejaVuSans-Bold-63\"/>\n", " <use x=\"136.669922\" xlink:href=\"#DejaVuSans-Bold-63\"/>\n", " <use x=\"195.947266\" xlink:href=\"#DejaVuSans-Bold-75\"/>\n", " <use x=\"267.138672\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"316.455078\" xlink:href=\"#DejaVuSans-Bold-61\"/>\n", " <use x=\"383.935547\" xlink:href=\"#DejaVuSans-Bold-63\"/>\n", " <use x=\"443.212891\" xlink:href=\"#DejaVuSans-Bold-79\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"PolyCollection_1\">\n", " <defs>\n", " <path d=\"M 65.524687 -95.000425 \n", "L 65.524687 -58.386996 \n", "L 82.962187 -104.434875 \n", "L 117.837187 -137.149541 \n", "L 187.587187 -163.650778 \n", "L 327.087188 -184.239685 \n", "L 327.087188 -193.02349 \n", "L 327.087188 -193.02349 \n", "L 187.587187 -173.976217 \n", "L 117.837187 -150.299381 \n", "L 82.962187 -127.360931 \n", "L 65.524687 -95.000425 \n", "z\n", "\" id=\"mfc64e6cc06\" style=\"stroke:#dd8452;stroke-opacity:0.2;\"/>\n", " </defs>\n", " <g clip-path=\"url(#p92687efc31)\">\n", " <use style=\"fill:#dd8452;fill-opacity:0.2;stroke:#dd8452;stroke-opacity:0.2;\" x=\"0\" xlink:href=\"#mfc64e6cc06\" y=\"228.357813\"/>\n", " </g>\n", " </g>\n", " <g id=\"PolyCollection_2\">\n", " <defs>\n", " <path d=\"M 65.524687 -88.870325 \n", "L 65.524687 -50.372415 \n", "L 82.962187 -103.212239 \n", "L 117.837187 -144.451463 \n", "L 187.587187 -169.508746 \n", "L 327.087188 -189.504786 \n", "L 327.087188 -198.62696 \n", "L 327.087188 -198.62696 \n", "L 187.587187 -182.02705 \n", "L 117.837187 -159.58042 \n", "L 82.962187 -130.618835 \n", "L 65.524687 -88.870325 \n", "z\n", "\" id=\"maf871740bd\" style=\"stroke:#55a868;stroke-opacity:0.2;\"/>\n", " </defs>\n", " <g clip-path=\"url(#p92687efc31)\">\n", " <use style=\"fill:#55a868;fill-opacity:0.2;stroke:#55a868;stroke-opacity:0.2;\" x=\"0\" xlink:href=\"#maf871740bd\" y=\"228.357813\"/>\n", " </g>\n", " </g>\n", " <g id=\"line2d_12\">\n", " <path clip-path=\"url(#p92687efc31)\" d=\"M 65.524687 151.664102 \n", "L 82.962187 112.45991 \n", "L 117.837187 84.633351 \n", "L 187.587187 59.544315 \n", "L 327.087188 39.726225 \n", "\" style=\"fill:none;stroke:#dd8452;stroke-linecap:round;stroke-width:1.5;\"/>\n", " <defs>\n", " <path d=\"M 0 3 \n", "C 0.795609 3 1.55874 2.683901 2.12132 2.12132 \n", "C 2.683901 1.55874 3 0.795609 3 0 \n", "C 3 -0.795609 2.683901 -1.55874 2.12132 -2.12132 \n", "C 1.55874 -2.683901 0.795609 -3 0 -3 \n", "C -0.795609 -3 -1.55874 -2.683901 -2.12132 -2.12132 \n", "C -2.683901 -1.55874 -3 -0.795609 -3 0 \n", "C -3 0.795609 -2.683901 1.55874 -2.12132 2.12132 \n", "C -1.55874 2.683901 -0.795609 3 0 3 \n", "z\n", "\" id=\"mde61e087a1\" style=\"stroke:#1a1a1a;\"/>\n", " </defs>\n", " <g clip-path=\"url(#p92687efc31)\">\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"65.524687\" xlink:href=\"#mde61e087a1\" y=\"151.664102\"/>\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"82.962187\" xlink:href=\"#mde61e087a1\" y=\"112.45991\"/>\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"117.837187\" xlink:href=\"#mde61e087a1\" y=\"84.633351\"/>\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"187.587187\" xlink:href=\"#mde61e087a1\" y=\"59.544315\"/>\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"327.087188\" xlink:href=\"#mde61e087a1\" y=\"39.726225\"/>\n", " </g>\n", " </g>\n", " <g id=\"line2d_13\">\n", " <path clip-path=\"url(#p92687efc31)\" d=\"M 65.524687 158.736443 \n", "L 82.962187 111.442275 \n", "L 117.837187 76.341871 \n", "L 187.587187 52.589915 \n", "L 327.087188 34.29194 \n", "\" style=\"fill:none;stroke:#55a868;stroke-linecap:round;stroke-width:1.5;\"/>\n", " <defs>\n", " <path d=\"M 0 3 \n", "C 0.795609 3 1.55874 2.683901 2.12132 2.12132 \n", "C 2.683901 1.55874 3 0.795609 3 0 \n", "C 3 -0.795609 2.683901 -1.55874 2.12132 -2.12132 \n", "C 1.55874 -2.683901 0.795609 -3 0 -3 \n", "C -0.795609 -3 -1.55874 -2.683901 -2.12132 -2.12132 \n", "C -2.683901 -1.55874 -3 -0.795609 -3 0 \n", "C -3 0.795609 -2.683901 1.55874 -2.12132 2.12132 \n", "C -1.55874 2.683901 -0.795609 3 0 3 \n", "z\n", "\" id=\"mb7bbc98dea\" style=\"stroke:#1a1a1a;\"/>\n", " </defs>\n", " <g clip-path=\"url(#p92687efc31)\">\n", " <use style=\"fill:#55a868;stroke:#1a1a1a;\" x=\"65.524687\" xlink:href=\"#mb7bbc98dea\" y=\"158.736443\"/>\n", " <use style=\"fill:#55a868;stroke:#1a1a1a;\" x=\"82.962187\" xlink:href=\"#mb7bbc98dea\" y=\"111.442275\"/>\n", " <use style=\"fill:#55a868;stroke:#1a1a1a;\" x=\"117.837187\" xlink:href=\"#mb7bbc98dea\" y=\"76.341871\"/>\n", " <use style=\"fill:#55a868;stroke:#1a1a1a;\" x=\"187.587187\" xlink:href=\"#mb7bbc98dea\" y=\"52.589915\"/>\n", " <use style=\"fill:#55a868;stroke:#1a1a1a;\" x=\"327.087188\" xlink:href=\"#mb7bbc98dea\" y=\"34.29194\"/>\n", " </g>\n", " </g>\n", " <g id=\"patch_3\">\n", " <path d=\"M 56.805937 185.398125 \n", "L 56.805937 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:square;stroke-linejoin:miter;stroke-width:1.25;\"/>\n", " </g>\n", " <g id=\"patch_4\">\n", " <path d=\"M 335.805938 185.398125 \n", "L 335.805938 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:square;stroke-linejoin:miter;stroke-width:1.25;\"/>\n", " </g>\n", " <g id=\"patch_5\">\n", " <path d=\"M 56.805937 185.398125 \n", "L 335.805938 185.398125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:square;stroke-linejoin:miter;stroke-width:1.25;\"/>\n", " </g>\n", " <g id=\"patch_6\">\n", " <path d=\"M 56.805937 22.318125 \n", "L 335.805938 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:square;stroke-linejoin:miter;stroke-width:1.25;\"/>\n", " </g>\n", " <g id=\"text_14\">\n", " <!-- Few-Shot Performance ProtoNet and ProtoMAML -->\n", " <g style=\"fill:#262626;\" transform=\"translate(31.170938 16.318125)scale(0.12 -0.12)\">\n", " <defs>\n", " <path d=\"M 588 4666 \n", "L 3834 4666 \n", "L 3834 3756 \n", "L 1791 3756 \n", "L 1791 2888 \n", "L 3713 2888 \n", "L 3713 1978 \n", "L 1791 1978 \n", "L 1791 0 \n", "L 588 0 \n", "L 588 4666 \n", "z\n", "\" id=\"DejaVuSans-Bold-46\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 225 3500 \n", "L 1313 3500 \n", "L 1900 1088 \n", "L 2491 3500 \n", "L 3425 3500 \n", "L 4013 1113 \n", "L 4603 3500 \n", "L 5691 3500 \n", "L 4769 0 \n", "L 3547 0 \n", "L 2956 2406 \n", "L 2369 0 \n", "L 1147 0 \n", "L 225 3500 \n", "z\n", "\" id=\"DejaVuSans-Bold-77\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 347 2297 \n", "L 2309 2297 \n", "L 2309 1388 \n", "L 347 1388 \n", "L 347 2297 \n", "z\n", "\" id=\"DejaVuSans-Bold-2d\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3834 4519 \n", "L 3834 3531 \n", "Q 3450 3703 3084 3790 \n", "Q 2719 3878 2394 3878 \n", "Q 1963 3878 1756 3759 \n", "Q 1550 3641 1550 3391 \n", "Q 1550 3203 1689 3098 \n", "Q 1828 2994 2194 2919 \n", "L 2706 2816 \n", "Q 3484 2659 3812 2340 \n", "Q 4141 2022 4141 1434 \n", "Q 4141 663 3683 286 \n", "Q 3225 -91 2284 -91 \n", "Q 1841 -91 1394 -6 \n", "Q 947 78 500 244 \n", "L 500 1259 \n", "Q 947 1022 1364 901 \n", "Q 1781 781 2169 781 \n", "Q 2563 781 2772 912 \n", "Q 2981 1044 2981 1288 \n", "Q 2981 1506 2839 1625 \n", "Q 2697 1744 2272 1838 \n", "L 1806 1941 \n", "Q 1106 2091 782 2419 \n", "Q 459 2747 459 3303 \n", "Q 459 4000 909 4375 \n", "Q 1359 4750 2203 4750 \n", "Q 2588 4750 2994 4692 \n", "Q 3400 4634 3834 4519 \n", "z\n", "\" id=\"DejaVuSans-Bold-53\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 588 4666 \n", "L 2584 4666 \n", "Q 3475 4666 3951 4270 \n", "Q 4428 3875 4428 3144 \n", "Q 4428 2409 3951 2014 \n", "Q 3475 1619 2584 1619 \n", "L 1791 1619 \n", "L 1791 0 \n", "L 588 0 \n", "L 588 4666 \n", "z\n", "M 1791 3794 \n", "L 1791 2491 \n", "L 2456 2491 \n", "Q 2806 2491 2997 2661 \n", "Q 3188 2831 3188 3144 \n", "Q 3188 3456 2997 3625 \n", "Q 2806 3794 2456 3794 \n", "L 1791 3794 \n", "z\n", "\" id=\"DejaVuSans-Bold-50\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 4056 2131 \n", "L 4056 0 \n", "L 2931 0 \n", "L 2931 347 \n", "L 2931 1631 \n", "Q 2931 2084 2911 2256 \n", "Q 2891 2428 2841 2509 \n", "Q 2775 2619 2662 2680 \n", "Q 2550 2741 2406 2741 \n", "Q 2056 2741 1856 2470 \n", "Q 1656 2200 1656 1722 \n", "L 1656 0 \n", "L 538 0 \n", "L 538 3500 \n", "L 1656 3500 \n", "L 1656 2988 \n", "Q 1909 3294 2193 3439 \n", "Q 2478 3584 2822 3584 \n", "Q 3428 3584 3742 3212 \n", "Q 4056 2841 4056 2131 \n", "z\n", "\" id=\"DejaVuSans-Bold-6e\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2919 2988 \n", "L 2919 4863 \n", "L 4044 4863 \n", "L 4044 0 \n", "L 2919 0 \n", "L 2919 506 \n", "Q 2688 197 2409 53 \n", "Q 2131 -91 1766 -91 \n", "Q 1119 -91 703 423 \n", "Q 288 938 288 1747 \n", "Q 288 2556 703 3070 \n", "Q 1119 3584 1766 3584 \n", "Q 2128 3584 2408 3439 \n", "Q 2688 3294 2919 2988 \n", "z\n", "M 2181 722 \n", "Q 2541 722 2730 984 \n", "Q 2919 1247 2919 1747 \n", "Q 2919 2247 2730 2509 \n", "Q 2541 2772 2181 2772 \n", "Q 1825 2772 1636 2509 \n", "Q 1447 2247 1447 1747 \n", "Q 1447 1247 1636 984 \n", "Q 1825 722 2181 722 \n", "z\n", "\" id=\"DejaVuSans-Bold-64\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 588 4666 \n", "L 2119 4666 \n", "L 3181 2169 \n", "L 4250 4666 \n", "L 5778 4666 \n", "L 5778 0 \n", "L 4641 0 \n", "L 4641 3413 \n", "L 3566 897 \n", "L 2803 897 \n", "L 1728 3413 \n", "L 1728 0 \n", "L 588 0 \n", "L 588 4666 \n", "z\n", "\" id=\"DejaVuSans-Bold-4d\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 588 4666 \n", "L 1791 4666 \n", "L 1791 909 \n", "L 3903 909 \n", "L 3903 0 \n", "L 588 0 \n", "L 588 4666 \n", "z\n", "\" id=\"DejaVuSans-Bold-4c\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-Bold-46\"/>\n", " <use x=\"64.310547\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"132.132812\" xlink:href=\"#DejaVuSans-Bold-77\"/>\n", " <use x=\"224.515625\" xlink:href=\"#DejaVuSans-Bold-2d\"/>\n", " <use x=\"266.019531\" xlink:href=\"#DejaVuSans-Bold-53\"/>\n", " <use x=\"338.041016\" xlink:href=\"#DejaVuSans-Bold-68\"/>\n", " <use x=\"409.232422\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"477.933594\" xlink:href=\"#DejaVuSans-Bold-74\"/>\n", " <use x=\"525.736328\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"560.550781\" xlink:href=\"#DejaVuSans-Bold-50\"/>\n", " <use x=\"633.841797\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"701.664062\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"750.980469\" xlink:href=\"#DejaVuSans-Bold-66\"/>\n", " <use x=\"794.486328\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"863.1875\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"912.503906\" xlink:href=\"#DejaVuSans-Bold-6d\"/>\n", " <use x=\"1016.703125\" xlink:href=\"#DejaVuSans-Bold-61\"/>\n", " <use x=\"1084.183594\" xlink:href=\"#DejaVuSans-Bold-6e\"/>\n", " <use x=\"1155.375\" xlink:href=\"#DejaVuSans-Bold-63\"/>\n", " <use x=\"1214.652344\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"1282.474609\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"1317.289062\" xlink:href=\"#DejaVuSans-Bold-50\"/>\n", " <use x=\"1390.580078\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"1439.896484\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"1508.597656\" xlink:href=\"#DejaVuSans-Bold-74\"/>\n", " <use x=\"1556.400391\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"1625.101562\" xlink:href=\"#DejaVuSans-Bold-4e\"/>\n", " <use x=\"1708.792969\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"1776.615234\" xlink:href=\"#DejaVuSans-Bold-74\"/>\n", " <use x=\"1824.417969\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"1859.232422\" xlink:href=\"#DejaVuSans-Bold-61\"/>\n", " <use x=\"1926.712891\" xlink:href=\"#DejaVuSans-Bold-6e\"/>\n", " <use x=\"1997.904297\" xlink:href=\"#DejaVuSans-Bold-64\"/>\n", " <use x=\"2069.486328\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"2104.300781\" xlink:href=\"#DejaVuSans-Bold-50\"/>\n", " <use x=\"2177.591797\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"2226.908203\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"2295.609375\" xlink:href=\"#DejaVuSans-Bold-74\"/>\n", " <use x=\"2343.412109\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"2412.113281\" xlink:href=\"#DejaVuSans-Bold-4d\"/>\n", " <use x=\"2511.625\" xlink:href=\"#DejaVuSans-Bold-41\"/>\n", " <use x=\"2589.017578\" xlink:href=\"#DejaVuSans-Bold-4d\"/>\n", " <use x=\"2688.529297\" xlink:href=\"#DejaVuSans-Bold-4c\"/>\n", " </g>\n", " </g>\n", " <g id=\"legend_1\">\n", " <g id=\"patch_7\">\n", " <path d=\"M 231.782031 179.898125 \n", "L 328.105938 179.898125 \n", "Q 330.305938 179.898125 330.305938 177.698125 \n", "L 330.305938 146.50625 \n", "Q 330.305938 144.30625 328.105938 144.30625 \n", "L 231.782031 144.30625 \n", "Q 229.582031 144.30625 229.582031 146.50625 \n", "L 229.582031 177.698125 \n", "Q 229.582031 179.898125 231.782031 179.898125 \n", "z\n", "\" style=\"fill:#eaeaf2;opacity:0.8;stroke:#cccccc;stroke-linejoin:miter;\"/>\n", " </g>\n", " <g id=\"line2d_14\">\n", " <path d=\"M 233.982031 153.214531 \n", "L 255.982031 153.214531 \n", "\" style=\"fill:none;stroke:#dd8452;stroke-linecap:round;stroke-width:1.5;\"/>\n", " </g>\n", " <g id=\"line2d_15\">\n", " <g>\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"244.982031\" xlink:href=\"#mde61e087a1\" y=\"153.214531\"/>\n", " </g>\n", " </g>\n", " <g id=\"text_15\">\n", " <!-- ProtoNet -->\n", " <g style=\"fill:#262626;\" transform=\"translate(264.782031 157.064531)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 1259 4147 \n", "L 1259 2394 \n", "L 2053 2394 \n", "Q 2494 2394 2734 2622 \n", "Q 2975 2850 2975 3272 \n", "Q 2975 3691 2734 3919 \n", "Q 2494 4147 2053 4147 \n", "L 1259 4147 \n", "z\n", "M 628 4666 \n", "L 2053 4666 \n", "Q 2838 4666 3239 4311 \n", "Q 3641 3956 3641 3272 \n", "Q 3641 2581 3239 2228 \n", "Q 2838 1875 2053 1875 \n", "L 1259 1875 \n", "L 1259 0 \n", "L 628 0 \n", "L 628 4666 \n", "z\n", "\" id=\"DejaVuSans-50\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2631 2963 \n", "Q 2534 3019 2420 3045 \n", "Q 2306 3072 2169 3072 \n", "Q 1681 3072 1420 2755 \n", "Q 1159 2438 1159 1844 \n", "L 1159 0 \n", "L 581 0 \n", "L 581 3500 \n", "L 1159 3500 \n", "L 1159 2956 \n", "Q 1341 3275 1631 3429 \n", "Q 1922 3584 2338 3584 \n", "Q 2397 3584 2469 3576 \n", "Q 2541 3569 2628 3553 \n", "L 2631 2963 \n", "z\n", "\" id=\"DejaVuSans-72\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1959 3097 \n", "Q 1497 3097 1228 2736 \n", "Q 959 2375 959 1747 \n", "Q 959 1119 1226 758 \n", "Q 1494 397 1959 397 \n", "Q 2419 397 2687 759 \n", "Q 2956 1122 2956 1747 \n", "Q 2956 2369 2687 2733 \n", "Q 2419 3097 1959 3097 \n", "z\n", "M 1959 3584 \n", "Q 2709 3584 3137 3096 \n", "Q 3566 2609 3566 1747 \n", "Q 3566 888 3137 398 \n", "Q 2709 -91 1959 -91 \n", "Q 1206 -91 779 398 \n", "Q 353 888 353 1747 \n", "Q 353 2609 779 3096 \n", "Q 1206 3584 1959 3584 \n", "z\n", "\" id=\"DejaVuSans-6f\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1172 4494 \n", "L 1172 3500 \n", "L 2356 3500 \n", "L 2356 3053 \n", "L 1172 3053 \n", "L 1172 1153 \n", "Q 1172 725 1289 603 \n", "Q 1406 481 1766 481 \n", "L 2356 481 \n", "L 2356 0 \n", "L 1766 0 \n", "Q 1100 0 847 248 \n", "Q 594 497 594 1153 \n", "L 594 3053 \n", "L 172 3053 \n", "L 172 3500 \n", "L 594 3500 \n", "L 594 4494 \n", "L 1172 4494 \n", "z\n", "\" id=\"DejaVuSans-74\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 628 4666 \n", "L 1478 4666 \n", "L 3547 763 \n", "L 3547 4666 \n", "L 4159 4666 \n", "L 4159 0 \n", "L 3309 0 \n", "L 1241 3903 \n", "L 1241 0 \n", "L 628 0 \n", "L 628 4666 \n", "z\n", "\" id=\"DejaVuSans-4e\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3597 1894 \n", "L 3597 1613 \n", "L 953 1613 \n", "Q 991 1019 1311 708 \n", "Q 1631 397 2203 397 \n", "Q 2534 397 2845 478 \n", "Q 3156 559 3463 722 \n", "L 3463 178 \n", "Q 3153 47 2828 -22 \n", "Q 2503 -91 2169 -91 \n", "Q 1331 -91 842 396 \n", "Q 353 884 353 1716 \n", "Q 353 2575 817 3079 \n", "Q 1281 3584 2069 3584 \n", "Q 2775 3584 3186 3129 \n", "Q 3597 2675 3597 1894 \n", "z\n", "M 3022 2063 \n", "Q 3016 2534 2758 2815 \n", "Q 2500 3097 2075 3097 \n", "Q 1594 3097 1305 2825 \n", "Q 1016 2553 972 2059 \n", "L 3022 2063 \n", "z\n", "\" id=\"DejaVuSans-65\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-50\"/>\n", " <use x=\"58.552734\" xlink:href=\"#DejaVuSans-72\"/>\n", " <use x=\"97.416016\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"158.597656\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"197.806641\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"258.988281\" xlink:href=\"#DejaVuSans-4e\"/>\n", " <use x=\"333.792969\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"395.316406\" xlink:href=\"#DejaVuSans-74\"/>\n", " </g>\n", " </g>\n", " <g id=\"line2d_16\">\n", " <path d=\"M 233.982031 169.360469 \n", "L 255.982031 169.360469 \n", "\" style=\"fill:none;stroke:#55a868;stroke-linecap:round;stroke-width:1.5;\"/>\n", " </g>\n", " <g id=\"line2d_17\">\n", " <g>\n", " <use style=\"fill:#55a868;stroke:#1a1a1a;\" x=\"244.982031\" xlink:href=\"#mb7bbc98dea\" y=\"169.360469\"/>\n", " </g>\n", " </g>\n", " <g id=\"text_16\">\n", " <!-- ProtoMAML -->\n", " <g style=\"fill:#262626;\" transform=\"translate(264.782031 173.210469)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 628 4666 \n", "L 1569 4666 \n", "L 2759 1491 \n", "L 3956 4666 \n", "L 4897 4666 \n", "L 4897 0 \n", "L 4281 0 \n", "L 4281 4097 \n", "L 3078 897 \n", "L 2444 897 \n", "L 1241 4097 \n", "L 1241 0 \n", "L 628 0 \n", "L 628 4666 \n", "z\n", "\" id=\"DejaVuSans-4d\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2188 4044 \n", "L 1331 1722 \n", "L 3047 1722 \n", "L 2188 4044 \n", "z\n", "M 1831 4666 \n", "L 2547 4666 \n", "L 4325 0 \n", "L 3669 0 \n", "L 3244 1197 \n", "L 1141 1197 \n", "L 716 0 \n", "L 50 0 \n", "L 1831 4666 \n", "z\n", "\" id=\"DejaVuSans-41\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 628 4666 \n", "L 1259 4666 \n", "L 1259 531 \n", "L 3531 531 \n", "L 3531 0 \n", "L 628 0 \n", "L 628 4666 \n", "z\n", "\" id=\"DejaVuSans-4c\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-50\"/>\n", " <use x=\"58.552734\" xlink:href=\"#DejaVuSans-72\"/>\n", " <use x=\"97.416016\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"158.597656\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"197.806641\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"258.988281\" xlink:href=\"#DejaVuSans-4d\"/>\n", " <use x=\"345.267578\" xlink:href=\"#DejaVuSans-41\"/>\n", " <use x=\"413.675781\" xlink:href=\"#DejaVuSans-4d\"/>\n", " <use x=\"499.955078\" xlink:href=\"#DejaVuSans-4c\"/>\n", " </g>\n", " </g>\n", " </g>\n", " </g>\n", " </g>\n", " <defs>\n", " <clipPath id=\"p92687efc31\">\n", " <rect height=\"163.08\" width=\"279\" x=\"56.805937\" y=\"22.318125\"/>\n", " </clipPath>\n", " </defs>\n", "</svg>\n"], "text/plain": ["<Figure size 360x216 with 1 Axes>"]}, "metadata": {}, "output_type": "display_data"}], "source": ["ax = plot_few_shot(protonet_accuracies, name=\"ProtoNet\", color=\"C1\")\n", "plot_few_shot(protomaml_accuracies, name=\"ProtoMAML\", color=\"C2\", ax=ax)\n", "plt.show()\n", "plt.close()"]}, {"cell_type": "markdown", "id": "b631ffc3", "metadata": {"papermill": {"duration": 0.053734, "end_time": "2021-10-10T16:37:29.090435", "exception": false, "start_time": "2021-10-10T16:37:29.036701", "status": "completed"}, "tags": []}, "source": ["We can observe that ProtoMAML is indeed able to outperform ProtoNet for $k>4$.\n", "This is because with more samples, it becomes more relevant to also adapt the base model's parameters.\n", "Meanwhile, for $k=2$, ProtoMAML achieves lower performance than ProtoNet.\n", "This is likely also related to choosing 200 inner loop updates since with more updates, there exists the risk of overfitting.\n", "Nonetheless, the high standard deviation for $k=2$ makes it hard to take any statistically valid conclusion.\n", "\n", "Overall, we can conclude that ProtoMAML slightly outperforms ProtoNet for larger shot counts.\n", "However, one disadvantage of ProtoMAML is its much longer training and testing time.\n", "ProtoNet provides a simple, efficient, yet strong baseline for\n", "ProtoMAML, and might be the better solution in situations where limited\n", "resources are available."]}, {"cell_type": "markdown", "id": "6d158afa", "metadata": {"papermill": {"duration": 0.055343, "end_time": "2021-10-10T16:37:29.202908", "exception": false, "start_time": "2021-10-10T16:37:29.147565", "status": "completed"}, "tags": []}, "source": ["## Domain adaptation\n", "\n", "So far, we have evaluated our meta-learning algorithms on the same dataset on which we have trained them.\n", "However, meta-learning algorithms are especially interesting when we want to move from one to another dataset.\n", "So, what happens if we apply them on a quite different dataset than CIFAR?\n", "This is what we try out below, and evaluate ProtoNet and ProtoMAML on the SVHN dataset."]}, {"cell_type": "markdown", "id": "71c4f38f", "metadata": {"papermill": {"duration": 0.054154, "end_time": "2021-10-10T16:37:29.316416", "exception": false, "start_time": "2021-10-10T16:37:29.262262", "status": "completed"}, "tags": []}, "source": ["### SVHN dataset\n", "\n", "The Street View House Numbers (SVHN) dataset is a real-world image dataset for house number detection.\n", "It is similar to MNIST by having the classes 0 to 9, but is more difficult due to its real-world setting and possible distracting numbers left and right.\n", "Let's first load the dataset, and visualize some images to get an impression of the dataset."]}, {"cell_type": "code", "execution_count": 34, "id": "74228693", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:29.435411Z", "iopub.status.busy": "2021-10-10T16:37:29.434935Z", "iopub.status.idle": "2021-10-10T16:37:34.722837Z", "shell.execute_reply": "2021-10-10T16:37:34.722322Z"}, "papermill": {"duration": 5.346857, "end_time": "2021-10-10T16:37:34.722956", "exception": false, "start_time": "2021-10-10T16:37:29.376099", "status": "completed"}, "tags": []}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Downloading http://ufldl.stanford.edu/housenumbers/test_32x32.mat to /__w/1/s/.datasets/test_32x32.mat\n"]}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "04c241d2abd34caa8d271a853e8f6a74", "version_major": 2, "version_minor": 0}, "text/plain": [" 0%| | 0/64275384 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}], "source": ["SVHN_test_dataset = SVHN(root=DATASET_PATH, split=\"test\", download=True, transform=transforms.ToTensor())"]}, {"cell_type": "code", "execution_count": 35, "id": "6b1d0ccf", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:34.838934Z", "iopub.status.busy": "2021-10-10T16:37:34.838460Z", "iopub.status.idle": "2021-10-10T16:37:35.077125Z", "shell.execute_reply": "2021-10-10T16:37:35.077513Z"}, "papermill": {"duration": 0.298826, "end_time": "2021-10-10T16:37:35.077658", "exception": false, "start_time": "2021-10-10T16:37:34.778832", "status": "completed"}, "tags": []}, "outputs": [{"data": {"application/pdf": "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\n", "image/svg+xml": ["<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n", "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n", " \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n", "<svg height=\"181.207445pt\" version=\"1.1\" viewBox=\"0 0 460.8 181.207445\" width=\"460.8pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n", " <metadata>\n", " <rdf:RDF xmlns:cc=\"http://creativecommons.org/ns#\" xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\">\n", " <cc:Work>\n", " <dc:type rdf:resource=\"http://purl.org/dc/dcmitype/StillImage\"/>\n", " <dc:date>2021-10-10T18:37:34.921312</dc:date>\n", " <dc:format>image/svg+xml</dc:format>\n", " <dc:creator>\n", " <cc:Agent>\n", " <dc:title>Matplotlib v3.4.3, https://matplotlib.org/</dc:title>\n", " </cc:Agent>\n", " </dc:creator>\n", " </cc:Work>\n", " </rdf:RDF>\n", " </metadata>\n", " <defs>\n", " <style type=\"text/css\">*{stroke-linecap:butt;stroke-linejoin:round;}</style>\n", " </defs>\n", " <g id=\"figure_1\">\n", " <g id=\"patch_1\">\n", " <path d=\"M 0 181.207445 \n", "L 460.8 181.207445 \n", "L 460.8 0 \n", "L 0 0 \n", "z\n", "\" style=\"fill:#ffffff;\"/>\n", " </g>\n", " <g id=\"axes_1\">\n", " <g clip-path=\"url(#p4f7828dbe3)\">\n", " <image height=\"152\" id=\"imagecbcbcff731\" transform=\"scale(1 -1)translate(0 -152)\" width=\"447\" x=\"7.2\" xlink:href=\"data:image/png;base64,\n", "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\" y=\"-22.007445\"/>\n", " </g>\n", " <g id=\"text_1\">\n", " <!-- Image examples of the SVHN dataset -->\n", " <g style=\"fill:#262626;\" transform=\"translate(117.891562 16.318125)scale(0.12 -0.12)\">\n", " <defs>\n", " <path d=\"M 628 4666 \n", "L 1259 4666 \n", "L 1259 0 \n", "L 628 0 \n", "L 628 4666 \n", "z\n", "\" id=\"DejaVuSans-49\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3328 2828 \n", "Q 3544 3216 3844 3400 \n", "Q 4144 3584 4550 3584 \n", "Q 5097 3584 5394 3201 \n", "Q 5691 2819 5691 2113 \n", "L 5691 0 \n", "L 5113 0 \n", "L 5113 2094 \n", "Q 5113 2597 4934 2840 \n", "Q 4756 3084 4391 3084 \n", "Q 3944 3084 3684 2787 \n", "Q 3425 2491 3425 1978 \n", "L 3425 0 \n", "L 2847 0 \n", "L 2847 2094 \n", "Q 2847 2600 2669 2842 \n", "Q 2491 3084 2119 3084 \n", "Q 1678 3084 1418 2786 \n", "Q 1159 2488 1159 1978 \n", "L 1159 0 \n", "L 581 0 \n", "L 581 3500 \n", "L 1159 3500 \n", "L 1159 2956 \n", "Q 1356 3278 1631 3431 \n", "Q 1906 3584 2284 3584 \n", "Q 2666 3584 2933 3390 \n", "Q 3200 3197 3328 2828 \n", "z\n", "\" id=\"DejaVuSans-6d\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2194 1759 \n", "Q 1497 1759 1228 1600 \n", "Q 959 1441 959 1056 \n", "Q 959 750 1161 570 \n", "Q 1363 391 1709 391 \n", "Q 2188 391 2477 730 \n", "Q 2766 1069 2766 1631 \n", "L 2766 1759 \n", "L 2194 1759 \n", "z\n", "M 3341 1997 \n", "L 3341 0 \n", "L 2766 0 \n", "L 2766 531 \n", "Q 2569 213 2275 61 \n", "Q 1981 -91 1556 -91 \n", "Q 1019 -91 701 211 \n", "Q 384 513 384 1019 \n", "Q 384 1609 779 1909 \n", "Q 1175 2209 1959 2209 \n", "L 2766 2209 \n", "L 2766 2266 \n", "Q 2766 2663 2505 2880 \n", "Q 2244 3097 1772 3097 \n", "Q 1472 3097 1187 3025 \n", "Q 903 2953 641 2809 \n", "L 641 3341 \n", "Q 956 3463 1253 3523 \n", "Q 1550 3584 1831 3584 \n", "Q 2591 3584 2966 3190 \n", "Q 3341 2797 3341 1997 \n", "z\n", "\" id=\"DejaVuSans-61\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2906 1791 \n", "Q 2906 2416 2648 2759 \n", "Q 2391 3103 1925 3103 \n", "Q 1463 3103 1205 2759 \n", "Q 947 2416 947 1791 \n", "Q 947 1169 1205 825 \n", "Q 1463 481 1925 481 \n", "Q 2391 481 2648 825 \n", "Q 2906 1169 2906 1791 \n", "z\n", "M 3481 434 \n", "Q 3481 -459 3084 -895 \n", "Q 2688 -1331 1869 -1331 \n", "Q 1566 -1331 1297 -1286 \n", "Q 1028 -1241 775 -1147 \n", "L 775 -588 \n", "Q 1028 -725 1275 -790 \n", "Q 1522 -856 1778 -856 \n", "Q 2344 -856 2625 -561 \n", "Q 2906 -266 2906 331 \n", "L 2906 616 \n", "Q 2728 306 2450 153 \n", "Q 2172 0 1784 0 \n", "Q 1141 0 747 490 \n", "Q 353 981 353 1791 \n", "Q 353 2603 747 3093 \n", "Q 1141 3584 1784 3584 \n", "Q 2172 3584 2450 3431 \n", "Q 2728 3278 2906 2969 \n", "L 2906 3500 \n", "L 3481 3500 \n", "L 3481 434 \n", "z\n", "\" id=\"DejaVuSans-67\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3597 1894 \n", "L 3597 1613 \n", "L 953 1613 \n", "Q 991 1019 1311 708 \n", "Q 1631 397 2203 397 \n", "Q 2534 397 2845 478 \n", "Q 3156 559 3463 722 \n", "L 3463 178 \n", "Q 3153 47 2828 -22 \n", "Q 2503 -91 2169 -91 \n", "Q 1331 -91 842 396 \n", "Q 353 884 353 1716 \n", "Q 353 2575 817 3079 \n", "Q 1281 3584 2069 3584 \n", "Q 2775 3584 3186 3129 \n", "Q 3597 2675 3597 1894 \n", "z\n", "M 3022 2063 \n", "Q 3016 2534 2758 2815 \n", "Q 2500 3097 2075 3097 \n", "Q 1594 3097 1305 2825 \n", "Q 1016 2553 972 2059 \n", "L 3022 2063 \n", "z\n", "\" id=\"DejaVuSans-65\" transform=\"scale(0.015625)\"/>\n", " <path id=\"DejaVuSans-20\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3513 3500 \n", "L 2247 1797 \n", "L 3578 0 \n", "L 2900 0 \n", "L 1881 1375 \n", "L 863 0 \n", "L 184 0 \n", "L 1544 1831 \n", "L 300 3500 \n", "L 978 3500 \n", "L 1906 2253 \n", "L 2834 3500 \n", "L 3513 3500 \n", "z\n", "\" id=\"DejaVuSans-78\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1159 525 \n", "L 1159 -1331 \n", "L 581 -1331 \n", "L 581 3500 \n", "L 1159 3500 \n", "L 1159 2969 \n", "Q 1341 3281 1617 3432 \n", "Q 1894 3584 2278 3584 \n", "Q 2916 3584 3314 3078 \n", "Q 3713 2572 3713 1747 \n", "Q 3713 922 3314 415 \n", "Q 2916 -91 2278 -91 \n", "Q 1894 -91 1617 61 \n", "Q 1341 213 1159 525 \n", "z\n", "M 3116 1747 \n", "Q 3116 2381 2855 2742 \n", "Q 2594 3103 2138 3103 \n", "Q 1681 3103 1420 2742 \n", "Q 1159 2381 1159 1747 \n", "Q 1159 1113 1420 752 \n", "Q 1681 391 2138 391 \n", "Q 2594 391 2855 752 \n", "Q 3116 1113 3116 1747 \n", "z\n", "\" id=\"DejaVuSans-70\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 603 4863 \n", "L 1178 4863 \n", "L 1178 0 \n", "L 603 0 \n", "L 603 4863 \n", "z\n", "\" id=\"DejaVuSans-6c\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2834 3397 \n", "L 2834 2853 \n", "Q 2591 2978 2328 3040 \n", "Q 2066 3103 1784 3103 \n", "Q 1356 3103 1142 2972 \n", "Q 928 2841 928 2578 \n", "Q 928 2378 1081 2264 \n", "Q 1234 2150 1697 2047 \n", "L 1894 2003 \n", "Q 2506 1872 2764 1633 \n", "Q 3022 1394 3022 966 \n", "Q 3022 478 2636 193 \n", "Q 2250 -91 1575 -91 \n", "Q 1294 -91 989 -36 \n", "Q 684 19 347 128 \n", "L 347 722 \n", "Q 666 556 975 473 \n", "Q 1284 391 1588 391 \n", "Q 1994 391 2212 530 \n", "Q 2431 669 2431 922 \n", "Q 2431 1156 2273 1281 \n", "Q 2116 1406 1581 1522 \n", "L 1381 1569 \n", "Q 847 1681 609 1914 \n", "Q 372 2147 372 2553 \n", "Q 372 3047 722 3315 \n", "Q 1072 3584 1716 3584 \n", "Q 2034 3584 2315 3537 \n", "Q 2597 3491 2834 3397 \n", "z\n", "\" id=\"DejaVuSans-73\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1959 3097 \n", "Q 1497 3097 1228 2736 \n", "Q 959 2375 959 1747 \n", "Q 959 1119 1226 758 \n", "Q 1494 397 1959 397 \n", "Q 2419 397 2687 759 \n", "Q 2956 1122 2956 1747 \n", "Q 2956 2369 2687 2733 \n", "Q 2419 3097 1959 3097 \n", "z\n", "M 1959 3584 \n", "Q 2709 3584 3137 3096 \n", "Q 3566 2609 3566 1747 \n", "Q 3566 888 3137 398 \n", "Q 2709 -91 1959 -91 \n", "Q 1206 -91 779 398 \n", "Q 353 888 353 1747 \n", "Q 353 2609 779 3096 \n", "Q 1206 3584 1959 3584 \n", "z\n", "\" id=\"DejaVuSans-6f\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2375 4863 \n", "L 2375 4384 \n", "L 1825 4384 \n", "Q 1516 4384 1395 4259 \n", "Q 1275 4134 1275 3809 \n", "L 1275 3500 \n", "L 2222 3500 \n", "L 2222 3053 \n", "L 1275 3053 \n", "L 1275 0 \n", "L 697 0 \n", "L 697 3053 \n", "L 147 3053 \n", "L 147 3500 \n", "L 697 3500 \n", "L 697 3744 \n", "Q 697 4328 969 4595 \n", "Q 1241 4863 1831 4863 \n", "L 2375 4863 \n", "z\n", "\" id=\"DejaVuSans-66\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1172 4494 \n", "L 1172 3500 \n", "L 2356 3500 \n", "L 2356 3053 \n", "L 1172 3053 \n", "L 1172 1153 \n", "Q 1172 725 1289 603 \n", "Q 1406 481 1766 481 \n", "L 2356 481 \n", "L 2356 0 \n", "L 1766 0 \n", "Q 1100 0 847 248 \n", "Q 594 497 594 1153 \n", "L 594 3053 \n", "L 172 3053 \n", "L 172 3500 \n", "L 594 3500 \n", "L 594 4494 \n", "L 1172 4494 \n", "z\n", "\" id=\"DejaVuSans-74\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3513 2113 \n", "L 3513 0 \n", "L 2938 0 \n", "L 2938 2094 \n", "Q 2938 2591 2744 2837 \n", "Q 2550 3084 2163 3084 \n", "Q 1697 3084 1428 2787 \n", "Q 1159 2491 1159 1978 \n", "L 1159 0 \n", "L 581 0 \n", "L 581 4863 \n", "L 1159 4863 \n", "L 1159 2956 \n", "Q 1366 3272 1645 3428 \n", "Q 1925 3584 2291 3584 \n", "Q 2894 3584 3203 3211 \n", "Q 3513 2838 3513 2113 \n", "z\n", "\" id=\"DejaVuSans-68\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3425 4513 \n", "L 3425 3897 \n", "Q 3066 4069 2747 4153 \n", "Q 2428 4238 2131 4238 \n", "Q 1616 4238 1336 4038 \n", "Q 1056 3838 1056 3469 \n", "Q 1056 3159 1242 3001 \n", "Q 1428 2844 1947 2747 \n", "L 2328 2669 \n", "Q 3034 2534 3370 2195 \n", "Q 3706 1856 3706 1288 \n", "Q 3706 609 3251 259 \n", "Q 2797 -91 1919 -91 \n", "Q 1588 -91 1214 -16 \n", "Q 841 59 441 206 \n", "L 441 856 \n", "Q 825 641 1194 531 \n", "Q 1563 422 1919 422 \n", "Q 2459 422 2753 634 \n", "Q 3047 847 3047 1241 \n", "Q 3047 1584 2836 1778 \n", "Q 2625 1972 2144 2069 \n", "L 1759 2144 \n", "Q 1053 2284 737 2584 \n", "Q 422 2884 422 3419 \n", "Q 422 4038 858 4394 \n", "Q 1294 4750 2059 4750 \n", "Q 2388 4750 2728 4690 \n", "Q 3069 4631 3425 4513 \n", "z\n", "\" id=\"DejaVuSans-53\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1831 0 \n", "L 50 4666 \n", "L 709 4666 \n", "L 2188 738 \n", "L 3669 4666 \n", "L 4325 4666 \n", "L 2547 0 \n", "L 1831 0 \n", "z\n", "\" id=\"DejaVuSans-56\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 628 4666 \n", "L 1259 4666 \n", "L 1259 2753 \n", "L 3553 2753 \n", "L 3553 4666 \n", "L 4184 4666 \n", "L 4184 0 \n", "L 3553 0 \n", "L 3553 2222 \n", "L 1259 2222 \n", "L 1259 0 \n", "L 628 0 \n", "L 628 4666 \n", "z\n", "\" id=\"DejaVuSans-48\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 628 4666 \n", "L 1478 4666 \n", "L 3547 763 \n", "L 3547 4666 \n", "L 4159 4666 \n", "L 4159 0 \n", "L 3309 0 \n", "L 1241 3903 \n", "L 1241 0 \n", "L 628 0 \n", "L 628 4666 \n", "z\n", "\" id=\"DejaVuSans-4e\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2906 2969 \n", "L 2906 4863 \n", "L 3481 4863 \n", "L 3481 0 \n", "L 2906 0 \n", "L 2906 525 \n", "Q 2725 213 2448 61 \n", "Q 2172 -91 1784 -91 \n", "Q 1150 -91 751 415 \n", "Q 353 922 353 1747 \n", "Q 353 2572 751 3078 \n", "Q 1150 3584 1784 3584 \n", "Q 2172 3584 2448 3432 \n", "Q 2725 3281 2906 2969 \n", "z\n", "M 947 1747 \n", "Q 947 1113 1208 752 \n", "Q 1469 391 1925 391 \n", "Q 2381 391 2643 752 \n", "Q 2906 1113 2906 1747 \n", "Q 2906 2381 2643 2742 \n", "Q 2381 3103 1925 3103 \n", "Q 1469 3103 1208 2742 \n", "Q 947 2381 947 1747 \n", "z\n", "\" id=\"DejaVuSans-64\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-49\"/>\n", " <use x=\"29.492188\" xlink:href=\"#DejaVuSans-6d\"/>\n", " <use x=\"126.904297\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"188.183594\" xlink:href=\"#DejaVuSans-67\"/>\n", " <use x=\"251.660156\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"313.183594\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"344.970703\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"404.744141\" xlink:href=\"#DejaVuSans-78\"/>\n", " <use x=\"463.923828\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"525.203125\" xlink:href=\"#DejaVuSans-6d\"/>\n", " <use x=\"622.615234\" xlink:href=\"#DejaVuSans-70\"/>\n", " <use x=\"686.091797\" xlink:href=\"#DejaVuSans-6c\"/>\n", " <use x=\"713.875\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"775.398438\" xlink:href=\"#DejaVuSans-73\"/>\n", " <use x=\"827.498047\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"859.285156\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"920.466797\" xlink:href=\"#DejaVuSans-66\"/>\n", " <use x=\"955.671875\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"987.458984\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"1026.667969\" xlink:href=\"#DejaVuSans-68\"/>\n", " <use x=\"1090.046875\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"1151.570312\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"1183.357422\" xlink:href=\"#DejaVuSans-53\"/>\n", " <use x=\"1246.833984\" xlink:href=\"#DejaVuSans-56\"/>\n", " <use x=\"1315.242188\" xlink:href=\"#DejaVuSans-48\"/>\n", " <use x=\"1390.4375\" xlink:href=\"#DejaVuSans-4e\"/>\n", " <use x=\"1465.242188\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"1497.029297\" xlink:href=\"#DejaVuSans-64\"/>\n", " <use x=\"1560.505859\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"1621.785156\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"1660.994141\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"1722.273438\" xlink:href=\"#DejaVuSans-73\"/>\n", " <use x=\"1774.373047\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"1835.896484\" xlink:href=\"#DejaVuSans-74\"/>\n", " </g>\n", " </g>\n", " </g>\n", " </g>\n", " <defs>\n", " <clipPath id=\"p4f7828dbe3\">\n", " <rect height=\"151.68932\" width=\"446.4\" x=\"7.2\" y=\"22.318125\"/>\n", " </clipPath>\n", " </defs>\n", "</svg>\n"], "text/plain": ["<Figure size 576x576 with 1 Axes>"]}, "metadata": {}, "output_type": "display_data"}], "source": ["# Visualize some examples\n", "NUM_IMAGES = 12\n", "SVHN_images = [SVHN_test_dataset[np.random.randint(len(SVHN_test_dataset))][0] for idx in range(NUM_IMAGES)]\n", "SVHN_images = torch.stack(SVHN_images, dim=0)\n", "img_grid = torchvision.utils.make_grid(SVHN_images, nrow=6, normalize=True, pad_value=0.9)\n", "img_grid = img_grid.permute(1, 2, 0)\n", "\n", "plt.figure(figsize=(8, 8))\n", "plt.title(\"Image examples of the SVHN dataset\")\n", "plt.imshow(img_grid)\n", "plt.axis(\"off\")\n", "plt.show()\n", "plt.close()"]}, {"cell_type": "markdown", "id": "65604d6b", "metadata": {"papermill": {"duration": 0.057271, "end_time": "2021-10-10T16:37:35.195031", "exception": false, "start_time": "2021-10-10T16:37:35.137760", "status": "completed"}, "tags": []}, "source": ["Each image is labeled with one class between 0 and 9 representing the main digit in the image.\n", "Can our ProtoNet and ProtoMAML learn to classify the digits from only a few examples?\n", "This is what we will test out below.\n", "The images have the same size as CIFAR, so that we can use the images without changes.\n", "We first prepare the dataset, for which we take the first 500 images per class.\n", "For this dataset, we use our test functions as before to get an estimated performance for different number of shots."]}, {"cell_type": "code", "execution_count": 36, "id": "0de00f6d", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:35.315332Z", "iopub.status.busy": "2021-10-10T16:37:35.314823Z", "iopub.status.idle": "2021-10-10T16:37:35.326321Z", "shell.execute_reply": "2021-10-10T16:37:35.326709Z"}, "papermill": {"duration": 0.07457, "end_time": "2021-10-10T16:37:35.326849", "exception": false, "start_time": "2021-10-10T16:37:35.252279", "status": "completed"}, "tags": []}, "outputs": [{"data": {"text/plain": ["(5000, 32, 32, 3)"]}, "execution_count": 36, "metadata": {}, "output_type": "execute_result"}], "source": ["imgs = np.transpose(SVHN_test_dataset.data, (0, 2, 3, 1))\n", "targets = SVHN_test_dataset.labels\n", "# Limit number of examples to 500 to reduce test time\n", "min_label_count = min(500, np.bincount(SVHN_test_dataset.labels).min())\n", "\n", "idxs = np.concatenate([np.where(targets == c)[0][:min_label_count] for c in range(1 + targets.max())], axis=0)\n", "imgs = imgs[idxs]\n", "targets = torch.from_numpy(targets[idxs]).long()\n", "\n", "svhn_fewshot_dataset = ImageDataset(imgs, targets, img_transform=test_transform)\n", "svhn_fewshot_dataset.imgs.shape"]}, {"cell_type": "markdown", "id": "761db618", "metadata": {"papermill": {"duration": 0.059836, "end_time": "2021-10-10T16:37:35.446022", "exception": false, "start_time": "2021-10-10T16:37:35.386186", "status": "completed"}, "tags": []}, "source": ["### Experiments\n", "\n", "First, we can apply ProtoNet to the SVHN dataset:"]}, {"cell_type": "code", "execution_count": 37, "id": "443d295e", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:35.566197Z", "iopub.status.busy": "2021-10-10T16:37:35.565609Z", "iopub.status.idle": "2021-10-10T16:37:49.932486Z", "shell.execute_reply": "2021-10-10T16:37:49.932000Z"}, "papermill": {"duration": 14.429039, "end_time": "2021-10-10T16:37:49.932629", "exception": false, "start_time": "2021-10-10T16:37:35.503590", "status": "completed"}, "tags": []}, "outputs": [{"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "6ae81549f8a343a2985e8fbdd3e6cfce", "version_major": 2, "version_minor": 0}, "text/plain": ["Extracting image features: 0%| | 0/40 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "93c64b6a35e441bf9a79602a829a41d7", "version_major": 2, "version_minor": 0}, "text/plain": ["Evaluating prototype classification: 0%| | 0/250 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"name": "stdout", "output_type": "stream", "text": ["Accuracy for k=2: 18.82% (+-2.28%)\n"]}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "e9c2476de61b41c78b739b3465029786", "version_major": 2, "version_minor": 0}, "text/plain": ["Evaluating prototype classification: 0%| | 0/125 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"name": "stdout", "output_type": "stream", "text": ["Accuracy for k=4: 21.94% (+-2.09%)\n"]}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "84a6abc3c3d54dd7a08fbc7b8dfd07f3", "version_major": 2, "version_minor": 0}, "text/plain": ["Evaluating prototype classification: 0%| | 0/63 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"name": "stdout", "output_type": "stream", "text": ["Accuracy for k=8: 25.59% (+-1.76%)\n"]}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "820542f219d34da6af0d83ed20f6756d", "version_major": 2, "version_minor": 0}, "text/plain": ["Evaluating prototype classification: 0%| | 0/32 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"name": "stdout", "output_type": "stream", "text": ["Accuracy for k=16: 29.06% (+-1.84%)\n"]}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "074a0b76522b4e2ab81b2abed09f23a3", "version_major": 2, "version_minor": 0}, "text/plain": ["Evaluating prototype classification: 0%| | 0/16 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"name": "stdout", "output_type": "stream", "text": ["Accuracy for k=32: 32.93% (+-1.33%)\n"]}], "source": ["protonet_svhn_accuracies = dict()\n", "data_feats = None\n", "for k in [2, 4, 8, 16, 32]:\n", " protonet_svhn_accuracies[k], data_feats = test_proto_net(\n", " protonet_model, svhn_fewshot_dataset, data_feats=data_feats, k_shot=k\n", " )\n", " print(\n", " \"Accuracy for k=%i: %4.2f%% (+-%4.2f%%)\"\n", " % (k, 100.0 * protonet_svhn_accuracies[k][0], 100 * protonet_svhn_accuracies[k][1])\n", " )"]}, {"cell_type": "markdown", "id": "8c171ffc", "metadata": {"papermill": {"duration": 0.060736, "end_time": "2021-10-10T16:37:50.056050", "exception": false, "start_time": "2021-10-10T16:37:49.995314", "status": "completed"}, "tags": []}, "source": ["It becomes clear that the results are much lower than the ones on CIFAR, and just slightly above random for $k=2$.\n", "How about ProtoMAML?\n", "We provide again evaluation files since the evaluation can take several minutes to complete."]}, {"cell_type": "code", "execution_count": 38, "id": "ca0e6799", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:50.188670Z", "iopub.status.busy": "2021-10-10T16:37:50.188177Z", "iopub.status.idle": "2021-10-10T16:37:50.191641Z", "shell.execute_reply": "2021-10-10T16:37:50.191230Z"}, "papermill": {"duration": 0.072963, "end_time": "2021-10-10T16:37:50.191749", "exception": false, "start_time": "2021-10-10T16:37:50.118786", "status": "completed"}, "tags": []}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Accuracy for k=2: 17.11% (+-1.95%)\n", "Accuracy for k=4: 21.29% (+-1.92%)\n", "Accuracy for k=8: 27.62% (+-1.84%)\n", "Accuracy for k=16: 36.17% (+-1.80%)\n", "Accuracy for k=32: 46.03% (+-1.65%)\n"]}], "source": ["protomaml_result_file = os.path.join(CHECKPOINT_PATH, \"protomaml_svhn_fewshot.json\")\n", "\n", "if os.path.isfile(protomaml_result_file):\n", " # Load pre-computed results\n", " with open(protomaml_result_file) as f:\n", " protomaml_svhn_accuracies = json.load(f)\n", " protomaml_svhn_accuracies = {int(k): v for k, v in protomaml_svhn_accuracies.items()}\n", "else:\n", " # Perform same experiments as for ProtoNet\n", " protomaml_svhn_accuracies = dict()\n", " for k in [2, 4, 8, 16, 32]:\n", " protomaml_svhn_accuracies[k] = test_protomaml(protomaml_model, svhn_fewshot_dataset, k_shot=k)\n", " # Export results\n", " with open(protomaml_result_file, \"w\") as f:\n", " json.dump(protomaml_svhn_accuracies, f, indent=4)\n", "\n", "for k in protomaml_svhn_accuracies:\n", " print(\n", " \"Accuracy for k=%i: %4.2f%% (+-%4.2f%%)\"\n", " % (k, 100.0 * protomaml_svhn_accuracies[k][0], 100.0 * protomaml_svhn_accuracies[k][1])\n", " )"]}, {"cell_type": "markdown", "id": "c0811d85", "metadata": {"papermill": {"duration": 0.061563, "end_time": "2021-10-10T16:37:50.315577", "exception": false, "start_time": "2021-10-10T16:37:50.254014", "status": "completed"}, "tags": []}, "source": ["While ProtoMAML shows similar performance than ProtoNet for $k\\leq 4$, it considerably outperforms ProtoNet for more than 8 shots.\n", "This is because we can adapt the base model, which is crucial when the data does not fit the original training data.\n", "For $k=32$, ProtoMAML achieves $13\\%$ higher classification accuracy than ProtoNet which already starts to flatten out.\n", "We can see the trend more clearly in our plot below."]}, {"cell_type": "code", "execution_count": 39, "id": "ea20f91d", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:37:50.478877Z", "iopub.status.busy": "2021-10-10T16:37:50.464114Z", "iopub.status.idle": "2021-10-10T16:38:10.765687Z", "shell.execute_reply": "2021-10-10T16:38:10.766092Z"}, "papermill": {"duration": 20.387402, "end_time": "2021-10-10T16:38:10.766241", "exception": false, "start_time": "2021-10-10T16:37:50.378839", "status": "completed"}, "tags": []}, "outputs": [{"data": {"application/pdf": "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\n", "image/svg+xml": ["<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n", "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n", " \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n", "<svg height=\"228.357813pt\" version=\"1.1\" viewBox=\"0 0 361.642187 228.357813\" width=\"361.642187pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n", " <metadata>\n", " <rdf:RDF xmlns:cc=\"http://creativecommons.org/ns#\" xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\">\n", " <cc:Work>\n", " <dc:type rdf:resource=\"http://purl.org/dc/dcmitype/StillImage\"/>\n", " <dc:date>2021-10-10T18:37:50.563371</dc:date>\n", " <dc:format>image/svg+xml</dc:format>\n", " <dc:creator>\n", " <cc:Agent>\n", " <dc:title>Matplotlib v3.4.3, https://matplotlib.org/</dc:title>\n", " </cc:Agent>\n", " </dc:creator>\n", " </cc:Work>\n", " </rdf:RDF>\n", " </metadata>\n", " <defs>\n", " <style type=\"text/css\">*{stroke-linecap:butt;stroke-linejoin:round;}</style>\n", " </defs>\n", " <g id=\"figure_1\">\n", " <g id=\"patch_1\">\n", " <path d=\"M 0 228.357813 \n", "L 361.642187 228.357813 \n", "L 361.642187 0 \n", "L 0 0 \n", "z\n", "\" style=\"fill:#ffffff;\"/>\n", " </g>\n", " <g id=\"axes_1\">\n", " <g id=\"patch_2\">\n", " <path d=\"M 49.807187 185.398125 \n", "L 328.807187 185.398125 \n", "L 328.807187 22.318125 \n", "L 49.807187 22.318125 \n", "z\n", "\" style=\"fill:#eaeaf2;\"/>\n", " </g>\n", " <g id=\"matplotlib.axis_1\">\n", " <g id=\"xtick_1\">\n", " <g id=\"line2d_1\">\n", " <path clip-path=\"url(#p55277b8759)\" d=\"M 58.525937 185.398125 \n", "L 58.525937 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_1\">\n", " <!-- 2 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(55.026562 203.256406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 1228 531 \n", "L 3431 531 \n", "L 3431 0 \n", "L 469 0 \n", "L 469 531 \n", "Q 828 903 1448 1529 \n", "Q 2069 2156 2228 2338 \n", "Q 2531 2678 2651 2914 \n", "Q 2772 3150 2772 3378 \n", "Q 2772 3750 2511 3984 \n", "Q 2250 4219 1831 4219 \n", "Q 1534 4219 1204 4116 \n", "Q 875 4013 500 3803 \n", "L 500 4441 \n", "Q 881 4594 1212 4672 \n", "Q 1544 4750 1819 4750 \n", "Q 2544 4750 2975 4387 \n", "Q 3406 4025 3406 3419 \n", "Q 3406 3131 3298 2873 \n", "Q 3191 2616 2906 2266 \n", "Q 2828 2175 2409 1742 \n", "Q 1991 1309 1228 531 \n", "z\n", "\" id=\"DejaVuSans-32\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-32\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_2\">\n", " <g id=\"line2d_2\">\n", " <path clip-path=\"url(#p55277b8759)\" d=\"M 75.963437 185.398125 \n", "L 75.963437 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_2\">\n", " <!-- 4 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(72.464062 203.256406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 2419 4116 \n", "L 825 1625 \n", "L 2419 1625 \n", "L 2419 4116 \n", "z\n", "M 2253 4666 \n", "L 3047 4666 \n", "L 3047 1625 \n", "L 3713 1625 \n", "L 3713 1100 \n", "L 3047 1100 \n", "L 3047 0 \n", "L 2419 0 \n", "L 2419 1100 \n", "L 313 1100 \n", "L 313 1709 \n", "L 2253 4666 \n", "z\n", "\" id=\"DejaVuSans-34\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-34\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_3\">\n", " <g id=\"line2d_3\">\n", " <path clip-path=\"url(#p55277b8759)\" d=\"M 110.838437 185.398125 \n", "L 110.838437 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_3\">\n", " <!-- 8 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(107.339062 203.256406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 2034 2216 \n", "Q 1584 2216 1326 1975 \n", "Q 1069 1734 1069 1313 \n", "Q 1069 891 1326 650 \n", "Q 1584 409 2034 409 \n", "Q 2484 409 2743 651 \n", "Q 3003 894 3003 1313 \n", "Q 3003 1734 2745 1975 \n", "Q 2488 2216 2034 2216 \n", "z\n", "M 1403 2484 \n", "Q 997 2584 770 2862 \n", "Q 544 3141 544 3541 \n", "Q 544 4100 942 4425 \n", "Q 1341 4750 2034 4750 \n", "Q 2731 4750 3128 4425 \n", "Q 3525 4100 3525 3541 \n", "Q 3525 3141 3298 2862 \n", "Q 3072 2584 2669 2484 \n", "Q 3125 2378 3379 2068 \n", "Q 3634 1759 3634 1313 \n", "Q 3634 634 3220 271 \n", "Q 2806 -91 2034 -91 \n", "Q 1263 -91 848 271 \n", "Q 434 634 434 1313 \n", "Q 434 1759 690 2068 \n", "Q 947 2378 1403 2484 \n", "z\n", "M 1172 3481 \n", "Q 1172 3119 1398 2916 \n", "Q 1625 2713 2034 2713 \n", "Q 2441 2713 2670 2916 \n", "Q 2900 3119 2900 3481 \n", "Q 2900 3844 2670 4047 \n", "Q 2441 4250 2034 4250 \n", "Q 1625 4250 1398 4047 \n", "Q 1172 3844 1172 3481 \n", "z\n", "\" id=\"DejaVuSans-38\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-38\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_4\">\n", " <g id=\"line2d_4\">\n", " <path clip-path=\"url(#p55277b8759)\" d=\"M 180.588437 185.398125 \n", "L 180.588437 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_4\">\n", " <!-- 16 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(173.589687 203.256406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 794 531 \n", "L 1825 531 \n", "L 1825 4091 \n", "L 703 3866 \n", "L 703 4441 \n", "L 1819 4666 \n", "L 2450 4666 \n", "L 2450 531 \n", "L 3481 531 \n", "L 3481 0 \n", "L 794 0 \n", "L 794 531 \n", "z\n", "\" id=\"DejaVuSans-31\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2113 2584 \n", "Q 1688 2584 1439 2293 \n", "Q 1191 2003 1191 1497 \n", "Q 1191 994 1439 701 \n", "Q 1688 409 2113 409 \n", "Q 2538 409 2786 701 \n", "Q 3034 994 3034 1497 \n", "Q 3034 2003 2786 2293 \n", "Q 2538 2584 2113 2584 \n", "z\n", "M 3366 4563 \n", "L 3366 3988 \n", "Q 3128 4100 2886 4159 \n", "Q 2644 4219 2406 4219 \n", "Q 1781 4219 1451 3797 \n", "Q 1122 3375 1075 2522 \n", "Q 1259 2794 1537 2939 \n", "Q 1816 3084 2150 3084 \n", "Q 2853 3084 3261 2657 \n", "Q 3669 2231 3669 1497 \n", "Q 3669 778 3244 343 \n", "Q 2819 -91 2113 -91 \n", "Q 1303 -91 875 529 \n", "Q 447 1150 447 2328 \n", "Q 447 3434 972 4092 \n", "Q 1497 4750 2381 4750 \n", "Q 2619 4750 2861 4703 \n", "Q 3103 4656 3366 4563 \n", "z\n", "\" id=\"DejaVuSans-36\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-31\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-36\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_5\">\n", " <g id=\"line2d_5\">\n", " <path clip-path=\"url(#p55277b8759)\" d=\"M 320.088437 185.398125 \n", "L 320.088437 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_5\">\n", " <!-- 32 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(313.089688 203.256406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 2597 2516 \n", "Q 3050 2419 3304 2112 \n", "Q 3559 1806 3559 1356 \n", "Q 3559 666 3084 287 \n", "Q 2609 -91 1734 -91 \n", "Q 1441 -91 1130 -33 \n", "Q 819 25 488 141 \n", "L 488 750 \n", "Q 750 597 1062 519 \n", "Q 1375 441 1716 441 \n", "Q 2309 441 2620 675 \n", "Q 2931 909 2931 1356 \n", "Q 2931 1769 2642 2001 \n", "Q 2353 2234 1838 2234 \n", "L 1294 2234 \n", "L 1294 2753 \n", "L 1863 2753 \n", "Q 2328 2753 2575 2939 \n", "Q 2822 3125 2822 3475 \n", "Q 2822 3834 2567 4026 \n", "Q 2313 4219 1838 4219 \n", "Q 1578 4219 1281 4162 \n", "Q 984 4106 628 3988 \n", "L 628 4550 \n", "Q 988 4650 1302 4700 \n", "Q 1616 4750 1894 4750 \n", "Q 2613 4750 3031 4423 \n", "Q 3450 4097 3450 3541 \n", "Q 3450 3153 3228 2886 \n", "Q 3006 2619 2597 2516 \n", "z\n", "\" id=\"DejaVuSans-33\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-33\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-32\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"text_6\">\n", " <!-- Number of shots per class -->\n", " <g style=\"fill:#262626;\" transform=\"translate(100.82125 218.662188)scale(0.12 -0.12)\">\n", " <defs>\n", " <path d=\"M 588 4666 \n", "L 1931 4666 \n", "L 3628 1466 \n", "L 3628 4666 \n", "L 4769 4666 \n", "L 4769 0 \n", "L 3425 0 \n", "L 1728 3200 \n", "L 1728 0 \n", "L 588 0 \n", "L 588 4666 \n", "z\n", "\" id=\"DejaVuSans-Bold-4e\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 500 1363 \n", "L 500 3500 \n", "L 1625 3500 \n", "L 1625 3150 \n", "Q 1625 2866 1622 2436 \n", "Q 1619 2006 1619 1863 \n", "Q 1619 1441 1641 1255 \n", "Q 1663 1069 1716 984 \n", "Q 1784 875 1895 815 \n", "Q 2006 756 2150 756 \n", "Q 2500 756 2700 1025 \n", "Q 2900 1294 2900 1772 \n", "L 2900 3500 \n", "L 4019 3500 \n", "L 4019 0 \n", "L 2900 0 \n", "L 2900 506 \n", "Q 2647 200 2364 54 \n", "Q 2081 -91 1741 -91 \n", "Q 1134 -91 817 281 \n", "Q 500 653 500 1363 \n", "z\n", "\" id=\"DejaVuSans-Bold-75\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3781 2919 \n", "Q 3994 3244 4286 3414 \n", "Q 4578 3584 4928 3584 \n", "Q 5531 3584 5847 3212 \n", "Q 6163 2841 6163 2131 \n", "L 6163 0 \n", "L 5038 0 \n", "L 5038 1825 \n", "Q 5041 1866 5042 1909 \n", "Q 5044 1953 5044 2034 \n", "Q 5044 2406 4934 2573 \n", "Q 4825 2741 4581 2741 \n", "Q 4263 2741 4089 2478 \n", "Q 3916 2216 3909 1719 \n", "L 3909 0 \n", "L 2784 0 \n", "L 2784 1825 \n", "Q 2784 2406 2684 2573 \n", "Q 2584 2741 2328 2741 \n", "Q 2006 2741 1831 2477 \n", "Q 1656 2213 1656 1722 \n", "L 1656 0 \n", "L 531 0 \n", "L 531 3500 \n", "L 1656 3500 \n", "L 1656 2988 \n", "Q 1863 3284 2130 3434 \n", "Q 2397 3584 2719 3584 \n", "Q 3081 3584 3359 3409 \n", "Q 3638 3234 3781 2919 \n", "z\n", "\" id=\"DejaVuSans-Bold-6d\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2400 722 \n", "Q 2759 722 2948 984 \n", "Q 3138 1247 3138 1747 \n", "Q 3138 2247 2948 2509 \n", "Q 2759 2772 2400 2772 \n", "Q 2041 2772 1848 2508 \n", "Q 1656 2244 1656 1747 \n", "Q 1656 1250 1848 986 \n", "Q 2041 722 2400 722 \n", "z\n", "M 1656 2988 \n", "Q 1888 3294 2169 3439 \n", "Q 2450 3584 2816 3584 \n", "Q 3463 3584 3878 3070 \n", "Q 4294 2556 4294 1747 \n", "Q 4294 938 3878 423 \n", "Q 3463 -91 2816 -91 \n", "Q 2450 -91 2169 54 \n", "Q 1888 200 1656 506 \n", "L 1656 0 \n", "L 538 0 \n", "L 538 4863 \n", "L 1656 4863 \n", "L 1656 2988 \n", "z\n", "\" id=\"DejaVuSans-Bold-62\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 4031 1759 \n", "L 4031 1441 \n", "L 1416 1441 \n", "Q 1456 1047 1700 850 \n", "Q 1944 653 2381 653 \n", "Q 2734 653 3104 758 \n", "Q 3475 863 3866 1075 \n", "L 3866 213 \n", "Q 3469 63 3072 -14 \n", "Q 2675 -91 2278 -91 \n", "Q 1328 -91 801 392 \n", "Q 275 875 275 1747 \n", "Q 275 2603 792 3093 \n", "Q 1309 3584 2216 3584 \n", "Q 3041 3584 3536 3087 \n", "Q 4031 2591 4031 1759 \n", "z\n", "M 2881 2131 \n", "Q 2881 2450 2695 2645 \n", "Q 2509 2841 2209 2841 \n", "Q 1884 2841 1681 2658 \n", "Q 1478 2475 1428 2131 \n", "L 2881 2131 \n", "z\n", "\" id=\"DejaVuSans-Bold-65\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3138 2547 \n", "Q 2991 2616 2845 2648 \n", "Q 2700 2681 2553 2681 \n", "Q 2122 2681 1889 2404 \n", "Q 1656 2128 1656 1613 \n", "L 1656 0 \n", "L 538 0 \n", "L 538 3500 \n", "L 1656 3500 \n", "L 1656 2925 \n", "Q 1872 3269 2151 3426 \n", "Q 2431 3584 2822 3584 \n", "Q 2878 3584 2943 3579 \n", "Q 3009 3575 3134 3559 \n", "L 3138 2547 \n", "z\n", "\" id=\"DejaVuSans-Bold-72\" transform=\"scale(0.015625)\"/>\n", " <path id=\"DejaVuSans-Bold-20\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2203 2784 \n", "Q 1831 2784 1636 2517 \n", "Q 1441 2250 1441 1747 \n", "Q 1441 1244 1636 976 \n", "Q 1831 709 2203 709 \n", "Q 2569 709 2762 976 \n", "Q 2956 1244 2956 1747 \n", "Q 2956 2250 2762 2517 \n", "Q 2569 2784 2203 2784 \n", "z\n", "M 2203 3584 \n", "Q 3106 3584 3614 3096 \n", "Q 4122 2609 4122 1747 \n", "Q 4122 884 3614 396 \n", "Q 3106 -91 2203 -91 \n", "Q 1297 -91 786 396 \n", "Q 275 884 275 1747 \n", "Q 275 2609 786 3096 \n", "Q 1297 3584 2203 3584 \n", "z\n", "\" id=\"DejaVuSans-Bold-6f\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2841 4863 \n", "L 2841 4128 \n", "L 2222 4128 \n", "Q 1984 4128 1890 4042 \n", "Q 1797 3956 1797 3744 \n", "L 1797 3500 \n", "L 2753 3500 \n", "L 2753 2700 \n", "L 1797 2700 \n", "L 1797 0 \n", "L 678 0 \n", "L 678 2700 \n", "L 122 2700 \n", "L 122 3500 \n", "L 678 3500 \n", "L 678 3744 \n", "Q 678 4316 997 4589 \n", "Q 1316 4863 1984 4863 \n", "L 2841 4863 \n", "z\n", "\" id=\"DejaVuSans-Bold-66\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3272 3391 \n", "L 3272 2541 \n", "Q 2913 2691 2578 2766 \n", "Q 2244 2841 1947 2841 \n", "Q 1628 2841 1473 2761 \n", "Q 1319 2681 1319 2516 \n", "Q 1319 2381 1436 2309 \n", "Q 1553 2238 1856 2203 \n", "L 2053 2175 \n", "Q 2913 2066 3209 1816 \n", "Q 3506 1566 3506 1031 \n", "Q 3506 472 3093 190 \n", "Q 2681 -91 1863 -91 \n", "Q 1516 -91 1145 -36 \n", "Q 775 19 384 128 \n", "L 384 978 \n", "Q 719 816 1070 734 \n", "Q 1422 653 1784 653 \n", "Q 2113 653 2278 743 \n", "Q 2444 834 2444 1013 \n", "Q 2444 1163 2330 1236 \n", "Q 2216 1309 1875 1350 \n", "L 1678 1375 \n", "Q 931 1469 631 1722 \n", "Q 331 1975 331 2491 \n", "Q 331 3047 712 3315 \n", "Q 1094 3584 1881 3584 \n", "Q 2191 3584 2531 3537 \n", "Q 2872 3491 3272 3391 \n", "z\n", "\" id=\"DejaVuSans-Bold-73\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 4056 2131 \n", "L 4056 0 \n", "L 2931 0 \n", "L 2931 347 \n", "L 2931 1625 \n", "Q 2931 2084 2911 2256 \n", "Q 2891 2428 2841 2509 \n", "Q 2775 2619 2662 2680 \n", "Q 2550 2741 2406 2741 \n", "Q 2056 2741 1856 2470 \n", "Q 1656 2200 1656 1722 \n", "L 1656 0 \n", "L 538 0 \n", "L 538 4863 \n", "L 1656 4863 \n", "L 1656 2988 \n", "Q 1909 3294 2193 3439 \n", "Q 2478 3584 2822 3584 \n", "Q 3428 3584 3742 3212 \n", "Q 4056 2841 4056 2131 \n", "z\n", "\" id=\"DejaVuSans-Bold-68\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1759 4494 \n", "L 1759 3500 \n", "L 2913 3500 \n", "L 2913 2700 \n", "L 1759 2700 \n", "L 1759 1216 \n", "Q 1759 972 1856 886 \n", "Q 1953 800 2241 800 \n", "L 2816 800 \n", "L 2816 0 \n", "L 1856 0 \n", "Q 1194 0 917 276 \n", "Q 641 553 641 1216 \n", "L 641 2700 \n", "L 84 2700 \n", "L 84 3500 \n", "L 641 3500 \n", "L 641 4494 \n", "L 1759 4494 \n", "z\n", "\" id=\"DejaVuSans-Bold-74\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1656 506 \n", "L 1656 -1331 \n", "L 538 -1331 \n", "L 538 3500 \n", "L 1656 3500 \n", "L 1656 2988 \n", "Q 1888 3294 2169 3439 \n", "Q 2450 3584 2816 3584 \n", "Q 3463 3584 3878 3070 \n", "Q 4294 2556 4294 1747 \n", "Q 4294 938 3878 423 \n", "Q 3463 -91 2816 -91 \n", "Q 2450 -91 2169 54 \n", "Q 1888 200 1656 506 \n", "z\n", "M 2400 2772 \n", "Q 2041 2772 1848 2508 \n", "Q 1656 2244 1656 1747 \n", "Q 1656 1250 1848 986 \n", "Q 2041 722 2400 722 \n", "Q 2759 722 2948 984 \n", "Q 3138 1247 3138 1747 \n", "Q 3138 2247 2948 2509 \n", "Q 2759 2772 2400 2772 \n", "z\n", "\" id=\"DejaVuSans-Bold-70\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3366 3391 \n", "L 3366 2478 \n", "Q 3138 2634 2908 2709 \n", "Q 2678 2784 2431 2784 \n", "Q 1963 2784 1702 2511 \n", "Q 1441 2238 1441 1747 \n", "Q 1441 1256 1702 982 \n", "Q 1963 709 2431 709 \n", "Q 2694 709 2930 787 \n", "Q 3166 866 3366 1019 \n", "L 3366 103 \n", "Q 3103 6 2833 -42 \n", "Q 2563 -91 2291 -91 \n", "Q 1344 -91 809 395 \n", "Q 275 881 275 1747 \n", "Q 275 2613 809 3098 \n", "Q 1344 3584 2291 3584 \n", "Q 2566 3584 2833 3536 \n", "Q 3100 3488 3366 3391 \n", "z\n", "\" id=\"DejaVuSans-Bold-63\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 538 4863 \n", "L 1656 4863 \n", "L 1656 0 \n", "L 538 0 \n", "L 538 4863 \n", "z\n", "\" id=\"DejaVuSans-Bold-6c\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2106 1575 \n", "Q 1756 1575 1579 1456 \n", "Q 1403 1338 1403 1106 \n", "Q 1403 894 1545 773 \n", "Q 1688 653 1941 653 \n", "Q 2256 653 2472 879 \n", "Q 2688 1106 2688 1447 \n", "L 2688 1575 \n", "L 2106 1575 \n", "z\n", "M 3816 1997 \n", "L 3816 0 \n", "L 2688 0 \n", "L 2688 519 \n", "Q 2463 200 2181 54 \n", "Q 1900 -91 1497 -91 \n", "Q 953 -91 614 226 \n", "Q 275 544 275 1050 \n", "Q 275 1666 698 1953 \n", "Q 1122 2241 2028 2241 \n", "L 2688 2241 \n", "L 2688 2328 \n", "Q 2688 2594 2478 2717 \n", "Q 2269 2841 1825 2841 \n", "Q 1466 2841 1156 2769 \n", "Q 847 2697 581 2553 \n", "L 581 3406 \n", "Q 941 3494 1303 3539 \n", "Q 1666 3584 2028 3584 \n", "Q 2975 3584 3395 3211 \n", "Q 3816 2838 3816 1997 \n", "z\n", "\" id=\"DejaVuSans-Bold-61\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-Bold-4e\"/>\n", " <use x=\"83.691406\" xlink:href=\"#DejaVuSans-Bold-75\"/>\n", " <use x=\"154.882812\" xlink:href=\"#DejaVuSans-Bold-6d\"/>\n", " <use x=\"259.082031\" xlink:href=\"#DejaVuSans-Bold-62\"/>\n", " <use x=\"330.664062\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"398.486328\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"447.802734\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"482.617188\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"551.318359\" xlink:href=\"#DejaVuSans-Bold-66\"/>\n", " <use x=\"594.824219\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"629.638672\" xlink:href=\"#DejaVuSans-Bold-73\"/>\n", " <use x=\"689.160156\" xlink:href=\"#DejaVuSans-Bold-68\"/>\n", " <use x=\"760.351562\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"829.052734\" xlink:href=\"#DejaVuSans-Bold-74\"/>\n", " <use x=\"876.855469\" xlink:href=\"#DejaVuSans-Bold-73\"/>\n", " <use x=\"936.376953\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"971.191406\" xlink:href=\"#DejaVuSans-Bold-70\"/>\n", " <use x=\"1042.773438\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"1110.595703\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"1159.912109\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"1194.726562\" xlink:href=\"#DejaVuSans-Bold-63\"/>\n", " <use x=\"1254.003906\" xlink:href=\"#DejaVuSans-Bold-6c\"/>\n", " <use x=\"1288.28125\" xlink:href=\"#DejaVuSans-Bold-61\"/>\n", " <use x=\"1355.761719\" xlink:href=\"#DejaVuSans-Bold-73\"/>\n", " <use x=\"1415.283203\" xlink:href=\"#DejaVuSans-Bold-73\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"matplotlib.axis_2\">\n", " <g id=\"ytick_1\">\n", " <g id=\"line2d_6\">\n", " <path clip-path=\"url(#p55277b8759)\" d=\"M 49.807187 155.920453 \n", "L 328.807187 155.920453 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_7\">\n", " <!-- 0.2 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 160.099594)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 2034 4250 \n", "Q 1547 4250 1301 3770 \n", "Q 1056 3291 1056 2328 \n", "Q 1056 1369 1301 889 \n", "Q 1547 409 2034 409 \n", "Q 2525 409 2770 889 \n", "Q 3016 1369 3016 2328 \n", "Q 3016 3291 2770 3770 \n", "Q 2525 4250 2034 4250 \n", "z\n", "M 2034 4750 \n", "Q 2819 4750 3233 4129 \n", "Q 3647 3509 3647 2328 \n", "Q 3647 1150 3233 529 \n", "Q 2819 -91 2034 -91 \n", "Q 1250 -91 836 529 \n", "Q 422 1150 422 2328 \n", "Q 422 3509 836 4129 \n", "Q 1250 4750 2034 4750 \n", "z\n", "\" id=\"DejaVuSans-30\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 684 794 \n", "L 1344 794 \n", "L 1344 0 \n", "L 684 0 \n", "L 684 794 \n", "z\n", "\" id=\"DejaVuSans-2e\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-32\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_2\">\n", " <g id=\"line2d_7\">\n", " <path clip-path=\"url(#p55277b8759)\" d=\"M 49.807187 110.331724 \n", "L 328.807187 110.331724 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_8\">\n", " <!-- 0.3 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 114.510865)scale(0.11 -0.11)\">\n", " <use xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-33\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_3\">\n", " <g id=\"line2d_8\">\n", " <path clip-path=\"url(#p55277b8759)\" d=\"M 49.807187 64.742996 \n", "L 328.807187 64.742996 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_9\">\n", " <!-- 0.4 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 68.922136)scale(0.11 -0.11)\">\n", " <use xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-34\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"text_10\">\n", " <!-- Accuracy -->\n", " <g style=\"fill:#262626;\" transform=\"translate(16.224375 134.3625)rotate(-90)scale(0.12 -0.12)\">\n", " <defs>\n", " <path d=\"M 3419 850 \n", "L 1538 850 \n", "L 1241 0 \n", "L 31 0 \n", "L 1759 4666 \n", "L 3194 4666 \n", "L 4922 0 \n", "L 3713 0 \n", "L 3419 850 \n", "z\n", "M 1838 1716 \n", "L 3116 1716 \n", "L 2478 3572 \n", "L 1838 1716 \n", "z\n", "\" id=\"DejaVuSans-Bold-41\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 78 3500 \n", "L 1197 3500 \n", "L 2138 1125 \n", "L 2938 3500 \n", "L 4056 3500 \n", "L 2584 -331 \n", "Q 2363 -916 2067 -1148 \n", "Q 1772 -1381 1288 -1381 \n", "L 641 -1381 \n", "L 641 -647 \n", "L 991 -647 \n", "Q 1275 -647 1404 -556 \n", "Q 1534 -466 1606 -231 \n", "L 1638 -134 \n", "L 78 3500 \n", "z\n", "\" id=\"DejaVuSans-Bold-79\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-Bold-41\"/>\n", " <use x=\"77.392578\" xlink:href=\"#DejaVuSans-Bold-63\"/>\n", " <use x=\"136.669922\" xlink:href=\"#DejaVuSans-Bold-63\"/>\n", " <use x=\"195.947266\" xlink:href=\"#DejaVuSans-Bold-75\"/>\n", " <use x=\"267.138672\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"316.455078\" xlink:href=\"#DejaVuSans-Bold-61\"/>\n", " <use x=\"383.935547\" xlink:href=\"#DejaVuSans-Bold-63\"/>\n", " <use x=\"443.212891\" xlink:href=\"#DejaVuSans-Bold-79\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"PolyCollection_1\">\n", " <defs>\n", " <path d=\"M 58.525937 -77.428041 \n", "L 58.525937 -56.67822 \n", "L 75.963437 -71.755422 \n", "L 110.838437 -89.91554 \n", "L 180.588437 -105.335317 \n", "L 320.088437 -125.29792 \n", "L 320.088437 -137.425697 \n", "L 320.088437 -137.425697 \n", "L 180.588437 -122.157101 \n", "L 110.838437 -105.960308 \n", "L 75.963437 -90.825372 \n", "L 58.525937 -77.428041 \n", "z\n", "\" id=\"medb9d5a3e0\" style=\"stroke:#dd8452;stroke-opacity:0.2;\"/>\n", " </defs>\n", " <g clip-path=\"url(#p55277b8759)\">\n", " <use style=\"fill:#dd8452;fill-opacity:0.2;stroke:#dd8452;stroke-opacity:0.2;\" x=\"0\" xlink:href=\"#medb9d5a3e0\" y=\"228.357813\"/>\n", " </g>\n", " </g>\n", " <g id=\"PolyCollection_2\">\n", " <defs>\n", " <path d=\"M 58.525937 -68.152019 \n", "L 58.525937 -50.372415 \n", "L 75.963437 -69.56527 \n", "L 110.838437 -98.787645 \n", "L 180.588437 -137.948362 \n", "L 320.088437 -183.58268 \n", "L 320.088437 -198.62696 \n", "L 320.088437 -198.62696 \n", "L 180.588437 -154.360305 \n", "L 110.838437 -115.564297 \n", "L 75.963437 -87.071341 \n", "L 58.525937 -68.152019 \n", "z\n", "\" id=\"m40e0046914\" style=\"stroke:#55a868;stroke-opacity:0.2;\"/>\n", " </defs>\n", " <g clip-path=\"url(#p55277b8759)\">\n", " <use style=\"fill:#55a868;fill-opacity:0.2;stroke:#55a868;stroke-opacity:0.2;\" x=\"0\" xlink:href=\"#m40e0046914\" y=\"228.357813\"/>\n", " </g>\n", " </g>\n", " <g id=\"line2d_9\">\n", " <path clip-path=\"url(#p55277b8759)\" d=\"M 58.525937 161.304682 \n", "L 75.963437 147.067416 \n", "L 110.838437 130.419889 \n", "L 180.588437 114.611604 \n", "L 320.088437 96.996004 \n", "\" style=\"fill:none;stroke:#dd8452;stroke-linecap:round;stroke-width:1.5;\"/>\n", " <defs>\n", " <path d=\"M 0 3 \n", "C 0.795609 3 1.55874 2.683901 2.12132 2.12132 \n", "C 2.683901 1.55874 3 0.795609 3 0 \n", "C 3 -0.795609 2.683901 -1.55874 2.12132 -2.12132 \n", "C 1.55874 -2.683901 0.795609 -3 0 -3 \n", "C -0.795609 -3 -1.55874 -2.683901 -2.12132 -2.12132 \n", "C -2.683901 -1.55874 -3 -0.795609 -3 0 \n", "C -3 0.795609 -2.683901 1.55874 -2.12132 2.12132 \n", "C -1.55874 2.683901 -0.795609 3 0 3 \n", "z\n", "\" id=\"m5623936e1d\" style=\"stroke:#1a1a1a;\"/>\n", " </defs>\n", " <g clip-path=\"url(#p55277b8759)\">\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"58.525937\" xlink:href=\"#m5623936e1d\" y=\"161.304682\"/>\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"75.963437\" xlink:href=\"#m5623936e1d\" y=\"147.067416\"/>\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"110.838437\" xlink:href=\"#m5623936e1d\" y=\"130.419889\"/>\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"180.588437\" xlink:href=\"#m5623936e1d\" y=\"114.611604\"/>\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"320.088437\" xlink:href=\"#m5623936e1d\" y=\"96.996004\"/>\n", " </g>\n", " </g>\n", " <g id=\"line2d_10\">\n", " <path clip-path=\"url(#p55277b8759)\" d=\"M 58.525937 169.095596 \n", "L 75.963437 150.039507 \n", "L 110.838437 121.181842 \n", "L 180.588437 82.203479 \n", "L 320.088437 37.252992 \n", "\" style=\"fill:none;stroke:#55a868;stroke-linecap:round;stroke-width:1.5;\"/>\n", " <defs>\n", " <path d=\"M 0 3 \n", "C 0.795609 3 1.55874 2.683901 2.12132 2.12132 \n", "C 2.683901 1.55874 3 0.795609 3 0 \n", "C 3 -0.795609 2.683901 -1.55874 2.12132 -2.12132 \n", "C 1.55874 -2.683901 0.795609 -3 0 -3 \n", "C -0.795609 -3 -1.55874 -2.683901 -2.12132 -2.12132 \n", "C -2.683901 -1.55874 -3 -0.795609 -3 0 \n", "C -3 0.795609 -2.683901 1.55874 -2.12132 2.12132 \n", "C -1.55874 2.683901 -0.795609 3 0 3 \n", "z\n", "\" id=\"ma4a34fdb24\" style=\"stroke:#1a1a1a;\"/>\n", " </defs>\n", " <g clip-path=\"url(#p55277b8759)\">\n", " <use style=\"fill:#55a868;stroke:#1a1a1a;\" x=\"58.525937\" xlink:href=\"#ma4a34fdb24\" y=\"169.095596\"/>\n", " <use style=\"fill:#55a868;stroke:#1a1a1a;\" x=\"75.963437\" xlink:href=\"#ma4a34fdb24\" y=\"150.039507\"/>\n", " <use style=\"fill:#55a868;stroke:#1a1a1a;\" x=\"110.838437\" xlink:href=\"#ma4a34fdb24\" y=\"121.181842\"/>\n", " <use style=\"fill:#55a868;stroke:#1a1a1a;\" x=\"180.588437\" xlink:href=\"#ma4a34fdb24\" y=\"82.203479\"/>\n", " <use style=\"fill:#55a868;stroke:#1a1a1a;\" x=\"320.088437\" xlink:href=\"#ma4a34fdb24\" y=\"37.252992\"/>\n", " </g>\n", " </g>\n", " <g id=\"patch_3\">\n", " <path d=\"M 49.807187 185.398125 \n", "L 49.807187 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:square;stroke-linejoin:miter;stroke-width:1.25;\"/>\n", " </g>\n", " <g id=\"patch_4\">\n", " <path d=\"M 328.807187 185.398125 \n", "L 328.807187 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:square;stroke-linejoin:miter;stroke-width:1.25;\"/>\n", " </g>\n", " <g id=\"patch_5\">\n", " <path d=\"M 49.807187 185.398125 \n", "L 328.807187 185.398125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:square;stroke-linejoin:miter;stroke-width:1.25;\"/>\n", " </g>\n", " <g id=\"patch_6\">\n", " <path d=\"M 49.807187 22.318125 \n", "L 328.807187 22.318125 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:square;stroke-linejoin:miter;stroke-width:1.25;\"/>\n", " </g>\n", " <g id=\"text_11\">\n", " <!-- Few-Shot Performance ProtoNet and ProtoMAML -->\n", " <g style=\"fill:#262626;\" transform=\"translate(24.172188 16.318125)scale(0.12 -0.12)\">\n", " <defs>\n", " <path d=\"M 588 4666 \n", "L 3834 4666 \n", "L 3834 3756 \n", "L 1791 3756 \n", "L 1791 2888 \n", "L 3713 2888 \n", "L 3713 1978 \n", "L 1791 1978 \n", "L 1791 0 \n", "L 588 0 \n", "L 588 4666 \n", "z\n", "\" id=\"DejaVuSans-Bold-46\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 225 3500 \n", "L 1313 3500 \n", "L 1900 1088 \n", "L 2491 3500 \n", "L 3425 3500 \n", "L 4013 1113 \n", "L 4603 3500 \n", "L 5691 3500 \n", "L 4769 0 \n", "L 3547 0 \n", "L 2956 2406 \n", "L 2369 0 \n", "L 1147 0 \n", "L 225 3500 \n", "z\n", "\" id=\"DejaVuSans-Bold-77\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 347 2297 \n", "L 2309 2297 \n", "L 2309 1388 \n", "L 347 1388 \n", "L 347 2297 \n", "z\n", "\" id=\"DejaVuSans-Bold-2d\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3834 4519 \n", "L 3834 3531 \n", "Q 3450 3703 3084 3790 \n", "Q 2719 3878 2394 3878 \n", "Q 1963 3878 1756 3759 \n", "Q 1550 3641 1550 3391 \n", "Q 1550 3203 1689 3098 \n", "Q 1828 2994 2194 2919 \n", "L 2706 2816 \n", "Q 3484 2659 3812 2340 \n", "Q 4141 2022 4141 1434 \n", "Q 4141 663 3683 286 \n", "Q 3225 -91 2284 -91 \n", "Q 1841 -91 1394 -6 \n", "Q 947 78 500 244 \n", "L 500 1259 \n", "Q 947 1022 1364 901 \n", "Q 1781 781 2169 781 \n", "Q 2563 781 2772 912 \n", "Q 2981 1044 2981 1288 \n", "Q 2981 1506 2839 1625 \n", "Q 2697 1744 2272 1838 \n", "L 1806 1941 \n", "Q 1106 2091 782 2419 \n", "Q 459 2747 459 3303 \n", "Q 459 4000 909 4375 \n", "Q 1359 4750 2203 4750 \n", "Q 2588 4750 2994 4692 \n", "Q 3400 4634 3834 4519 \n", "z\n", "\" id=\"DejaVuSans-Bold-53\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 588 4666 \n", "L 2584 4666 \n", "Q 3475 4666 3951 4270 \n", "Q 4428 3875 4428 3144 \n", "Q 4428 2409 3951 2014 \n", "Q 3475 1619 2584 1619 \n", "L 1791 1619 \n", "L 1791 0 \n", "L 588 0 \n", "L 588 4666 \n", "z\n", "M 1791 3794 \n", "L 1791 2491 \n", "L 2456 2491 \n", "Q 2806 2491 2997 2661 \n", "Q 3188 2831 3188 3144 \n", "Q 3188 3456 2997 3625 \n", "Q 2806 3794 2456 3794 \n", "L 1791 3794 \n", "z\n", "\" id=\"DejaVuSans-Bold-50\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 4056 2131 \n", "L 4056 0 \n", "L 2931 0 \n", "L 2931 347 \n", "L 2931 1631 \n", "Q 2931 2084 2911 2256 \n", "Q 2891 2428 2841 2509 \n", "Q 2775 2619 2662 2680 \n", "Q 2550 2741 2406 2741 \n", "Q 2056 2741 1856 2470 \n", "Q 1656 2200 1656 1722 \n", "L 1656 0 \n", "L 538 0 \n", "L 538 3500 \n", "L 1656 3500 \n", "L 1656 2988 \n", "Q 1909 3294 2193 3439 \n", "Q 2478 3584 2822 3584 \n", "Q 3428 3584 3742 3212 \n", "Q 4056 2841 4056 2131 \n", "z\n", "\" id=\"DejaVuSans-Bold-6e\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2919 2988 \n", "L 2919 4863 \n", "L 4044 4863 \n", "L 4044 0 \n", "L 2919 0 \n", "L 2919 506 \n", "Q 2688 197 2409 53 \n", "Q 2131 -91 1766 -91 \n", "Q 1119 -91 703 423 \n", "Q 288 938 288 1747 \n", "Q 288 2556 703 3070 \n", "Q 1119 3584 1766 3584 \n", "Q 2128 3584 2408 3439 \n", "Q 2688 3294 2919 2988 \n", "z\n", "M 2181 722 \n", "Q 2541 722 2730 984 \n", "Q 2919 1247 2919 1747 \n", "Q 2919 2247 2730 2509 \n", "Q 2541 2772 2181 2772 \n", "Q 1825 2772 1636 2509 \n", "Q 1447 2247 1447 1747 \n", "Q 1447 1247 1636 984 \n", "Q 1825 722 2181 722 \n", "z\n", "\" id=\"DejaVuSans-Bold-64\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 588 4666 \n", "L 2119 4666 \n", "L 3181 2169 \n", "L 4250 4666 \n", "L 5778 4666 \n", "L 5778 0 \n", "L 4641 0 \n", "L 4641 3413 \n", "L 3566 897 \n", "L 2803 897 \n", "L 1728 3413 \n", "L 1728 0 \n", "L 588 0 \n", "L 588 4666 \n", "z\n", "\" id=\"DejaVuSans-Bold-4d\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 588 4666 \n", "L 1791 4666 \n", "L 1791 909 \n", "L 3903 909 \n", "L 3903 0 \n", "L 588 0 \n", "L 588 4666 \n", "z\n", "\" id=\"DejaVuSans-Bold-4c\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-Bold-46\"/>\n", " <use x=\"64.310547\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"132.132812\" xlink:href=\"#DejaVuSans-Bold-77\"/>\n", " <use x=\"224.515625\" xlink:href=\"#DejaVuSans-Bold-2d\"/>\n", " <use x=\"266.019531\" xlink:href=\"#DejaVuSans-Bold-53\"/>\n", " <use x=\"338.041016\" xlink:href=\"#DejaVuSans-Bold-68\"/>\n", " <use x=\"409.232422\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"477.933594\" xlink:href=\"#DejaVuSans-Bold-74\"/>\n", " <use x=\"525.736328\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"560.550781\" xlink:href=\"#DejaVuSans-Bold-50\"/>\n", " <use x=\"633.841797\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"701.664062\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"750.980469\" xlink:href=\"#DejaVuSans-Bold-66\"/>\n", " <use x=\"794.486328\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"863.1875\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"912.503906\" xlink:href=\"#DejaVuSans-Bold-6d\"/>\n", " <use x=\"1016.703125\" xlink:href=\"#DejaVuSans-Bold-61\"/>\n", " <use x=\"1084.183594\" xlink:href=\"#DejaVuSans-Bold-6e\"/>\n", " <use x=\"1155.375\" xlink:href=\"#DejaVuSans-Bold-63\"/>\n", " <use x=\"1214.652344\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"1282.474609\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"1317.289062\" xlink:href=\"#DejaVuSans-Bold-50\"/>\n", " <use x=\"1390.580078\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"1439.896484\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"1508.597656\" xlink:href=\"#DejaVuSans-Bold-74\"/>\n", " <use x=\"1556.400391\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"1625.101562\" xlink:href=\"#DejaVuSans-Bold-4e\"/>\n", " <use x=\"1708.792969\" xlink:href=\"#DejaVuSans-Bold-65\"/>\n", " <use x=\"1776.615234\" xlink:href=\"#DejaVuSans-Bold-74\"/>\n", " <use x=\"1824.417969\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"1859.232422\" xlink:href=\"#DejaVuSans-Bold-61\"/>\n", " <use x=\"1926.712891\" xlink:href=\"#DejaVuSans-Bold-6e\"/>\n", " <use x=\"1997.904297\" xlink:href=\"#DejaVuSans-Bold-64\"/>\n", " <use x=\"2069.486328\" xlink:href=\"#DejaVuSans-Bold-20\"/>\n", " <use x=\"2104.300781\" xlink:href=\"#DejaVuSans-Bold-50\"/>\n", " <use x=\"2177.591797\" xlink:href=\"#DejaVuSans-Bold-72\"/>\n", " <use x=\"2226.908203\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"2295.609375\" xlink:href=\"#DejaVuSans-Bold-74\"/>\n", " <use x=\"2343.412109\" xlink:href=\"#DejaVuSans-Bold-6f\"/>\n", " <use x=\"2412.113281\" xlink:href=\"#DejaVuSans-Bold-4d\"/>\n", " <use x=\"2511.625\" xlink:href=\"#DejaVuSans-Bold-41\"/>\n", " <use x=\"2589.017578\" xlink:href=\"#DejaVuSans-Bold-4d\"/>\n", " <use x=\"2688.529297\" xlink:href=\"#DejaVuSans-Bold-4c\"/>\n", " </g>\n", " </g>\n", " <g id=\"legend_1\">\n", " <g id=\"patch_7\">\n", " <path d=\"M 57.507188 63.41 \n", "L 153.831094 63.41 \n", "Q 156.031094 63.41 156.031094 61.21 \n", "L 156.031094 30.018125 \n", "Q 156.031094 27.818125 153.831094 27.818125 \n", "L 57.507188 27.818125 \n", "Q 55.307187 27.818125 55.307187 30.018125 \n", "L 55.307187 61.21 \n", "Q 55.307187 63.41 57.507188 63.41 \n", "z\n", "\" style=\"fill:#eaeaf2;opacity:0.8;stroke:#cccccc;stroke-linejoin:miter;\"/>\n", " </g>\n", " <g id=\"line2d_11\">\n", " <path d=\"M 59.707187 36.726406 \n", "L 81.707188 36.726406 \n", "\" style=\"fill:none;stroke:#dd8452;stroke-linecap:round;stroke-width:1.5;\"/>\n", " </g>\n", " <g id=\"line2d_12\">\n", " <g>\n", " <use style=\"fill:#dd8452;stroke:#1a1a1a;\" x=\"70.707188\" xlink:href=\"#m5623936e1d\" y=\"36.726406\"/>\n", " </g>\n", " </g>\n", " <g id=\"text_12\">\n", " <!-- ProtoNet -->\n", " <g style=\"fill:#262626;\" transform=\"translate(90.507188 40.576406)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 1259 4147 \n", "L 1259 2394 \n", "L 2053 2394 \n", "Q 2494 2394 2734 2622 \n", "Q 2975 2850 2975 3272 \n", "Q 2975 3691 2734 3919 \n", "Q 2494 4147 2053 4147 \n", "L 1259 4147 \n", "z\n", "M 628 4666 \n", "L 2053 4666 \n", "Q 2838 4666 3239 4311 \n", "Q 3641 3956 3641 3272 \n", "Q 3641 2581 3239 2228 \n", "Q 2838 1875 2053 1875 \n", "L 1259 1875 \n", "L 1259 0 \n", "L 628 0 \n", "L 628 4666 \n", "z\n", "\" id=\"DejaVuSans-50\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2631 2963 \n", "Q 2534 3019 2420 3045 \n", "Q 2306 3072 2169 3072 \n", "Q 1681 3072 1420 2755 \n", "Q 1159 2438 1159 1844 \n", "L 1159 0 \n", "L 581 0 \n", "L 581 3500 \n", "L 1159 3500 \n", "L 1159 2956 \n", "Q 1341 3275 1631 3429 \n", "Q 1922 3584 2338 3584 \n", "Q 2397 3584 2469 3576 \n", "Q 2541 3569 2628 3553 \n", "L 2631 2963 \n", "z\n", "\" id=\"DejaVuSans-72\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1959 3097 \n", "Q 1497 3097 1228 2736 \n", "Q 959 2375 959 1747 \n", "Q 959 1119 1226 758 \n", "Q 1494 397 1959 397 \n", "Q 2419 397 2687 759 \n", "Q 2956 1122 2956 1747 \n", "Q 2956 2369 2687 2733 \n", "Q 2419 3097 1959 3097 \n", "z\n", "M 1959 3584 \n", "Q 2709 3584 3137 3096 \n", "Q 3566 2609 3566 1747 \n", "Q 3566 888 3137 398 \n", "Q 2709 -91 1959 -91 \n", "Q 1206 -91 779 398 \n", "Q 353 888 353 1747 \n", "Q 353 2609 779 3096 \n", "Q 1206 3584 1959 3584 \n", "z\n", "\" id=\"DejaVuSans-6f\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 1172 4494 \n", "L 1172 3500 \n", "L 2356 3500 \n", "L 2356 3053 \n", "L 1172 3053 \n", "L 1172 1153 \n", "Q 1172 725 1289 603 \n", "Q 1406 481 1766 481 \n", "L 2356 481 \n", "L 2356 0 \n", "L 1766 0 \n", "Q 1100 0 847 248 \n", "Q 594 497 594 1153 \n", "L 594 3053 \n", "L 172 3053 \n", "L 172 3500 \n", "L 594 3500 \n", "L 594 4494 \n", "L 1172 4494 \n", "z\n", "\" id=\"DejaVuSans-74\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 628 4666 \n", "L 1478 4666 \n", "L 3547 763 \n", "L 3547 4666 \n", "L 4159 4666 \n", "L 4159 0 \n", "L 3309 0 \n", "L 1241 3903 \n", "L 1241 0 \n", "L 628 0 \n", "L 628 4666 \n", "z\n", "\" id=\"DejaVuSans-4e\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 3597 1894 \n", "L 3597 1613 \n", "L 953 1613 \n", "Q 991 1019 1311 708 \n", "Q 1631 397 2203 397 \n", "Q 2534 397 2845 478 \n", "Q 3156 559 3463 722 \n", "L 3463 178 \n", "Q 3153 47 2828 -22 \n", "Q 2503 -91 2169 -91 \n", "Q 1331 -91 842 396 \n", "Q 353 884 353 1716 \n", "Q 353 2575 817 3079 \n", "Q 1281 3584 2069 3584 \n", "Q 2775 3584 3186 3129 \n", "Q 3597 2675 3597 1894 \n", "z\n", "M 3022 2063 \n", "Q 3016 2534 2758 2815 \n", "Q 2500 3097 2075 3097 \n", "Q 1594 3097 1305 2825 \n", "Q 1016 2553 972 2059 \n", "L 3022 2063 \n", "z\n", "\" id=\"DejaVuSans-65\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-50\"/>\n", " <use x=\"58.552734\" xlink:href=\"#DejaVuSans-72\"/>\n", " <use x=\"97.416016\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"158.597656\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"197.806641\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"258.988281\" xlink:href=\"#DejaVuSans-4e\"/>\n", " <use x=\"333.792969\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"395.316406\" xlink:href=\"#DejaVuSans-74\"/>\n", " </g>\n", " </g>\n", " <g id=\"line2d_13\">\n", " <path d=\"M 59.707187 52.872344 \n", "L 81.707188 52.872344 \n", "\" style=\"fill:none;stroke:#55a868;stroke-linecap:round;stroke-width:1.5;\"/>\n", " </g>\n", " <g id=\"line2d_14\">\n", " <g>\n", " <use style=\"fill:#55a868;stroke:#1a1a1a;\" x=\"70.707188\" xlink:href=\"#ma4a34fdb24\" y=\"52.872344\"/>\n", " </g>\n", " </g>\n", " <g id=\"text_13\">\n", " <!-- ProtoMAML -->\n", " <g style=\"fill:#262626;\" transform=\"translate(90.507188 56.722344)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 628 4666 \n", "L 1569 4666 \n", "L 2759 1491 \n", "L 3956 4666 \n", "L 4897 4666 \n", "L 4897 0 \n", "L 4281 0 \n", "L 4281 4097 \n", "L 3078 897 \n", "L 2444 897 \n", "L 1241 4097 \n", "L 1241 0 \n", "L 628 0 \n", "L 628 4666 \n", "z\n", "\" id=\"DejaVuSans-4d\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 2188 4044 \n", "L 1331 1722 \n", "L 3047 1722 \n", "L 2188 4044 \n", "z\n", "M 1831 4666 \n", "L 2547 4666 \n", "L 4325 0 \n", "L 3669 0 \n", "L 3244 1197 \n", "L 1141 1197 \n", "L 716 0 \n", "L 50 0 \n", "L 1831 4666 \n", "z\n", "\" id=\"DejaVuSans-41\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 628 4666 \n", "L 1259 4666 \n", "L 1259 531 \n", "L 3531 531 \n", "L 3531 0 \n", "L 628 0 \n", "L 628 4666 \n", "z\n", "\" id=\"DejaVuSans-4c\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-50\"/>\n", " <use x=\"58.552734\" xlink:href=\"#DejaVuSans-72\"/>\n", " <use x=\"97.416016\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"158.597656\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"197.806641\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"258.988281\" xlink:href=\"#DejaVuSans-4d\"/>\n", " <use x=\"345.267578\" xlink:href=\"#DejaVuSans-41\"/>\n", " <use x=\"413.675781\" xlink:href=\"#DejaVuSans-4d\"/>\n", " <use x=\"499.955078\" xlink:href=\"#DejaVuSans-4c\"/>\n", " </g>\n", " </g>\n", " </g>\n", " </g>\n", " </g>\n", " <defs>\n", " <clipPath id=\"p55277b8759\">\n", " <rect height=\"163.08\" width=\"279\" x=\"49.807187\" y=\"22.318125\"/>\n", " </clipPath>\n", " </defs>\n", "</svg>\n"], "text/plain": ["<Figure size 360x216 with 1 Axes>"]}, "metadata": {}, "output_type": "display_data"}], "source": ["ax = plot_few_shot(protonet_svhn_accuracies, name=\"ProtoNet\", color=\"C1\")\n", "plot_few_shot(protomaml_svhn_accuracies, name=\"ProtoMAML\", color=\"C2\", ax=ax)\n", "plt.show()\n", "plt.close()"]}, {"cell_type": "markdown", "id": "81b31ea2", "metadata": {"papermill": {"duration": 0.064936, "end_time": "2021-10-10T16:38:10.896748", "exception": false, "start_time": "2021-10-10T16:38:10.831812", "status": "completed"}, "tags": []}, "source": ["## Conclusion\n", "\n", "In this notebook, we have discussed meta-learning algorithms that learn to adapt to new classes and/or tasks with just a few samples.\n", "We have discussed three popular algorithms, namely ProtoNet, MAML and ProtoMAML.\n", "On the few-shot image classification task of CIFAR100, ProtoNet and ProtoMAML showed to perform similarly well, with slight benefits of ProtoMAML for larger shot sizes.\n", "However, for out-of-distribution data (SVHN), the ability to optimize the base model showed to be crucial and gave ProtoMAML considerable performance gains over ProtoNet.\n", "Nonetheless, ProtoNet offers other advantages compared to ProtoMAML, namely a very cheap training and test cost as well as a simpler implementation.\n", "Hence, it is recommended to consider whether the additionally complexity\n", "of ProtoMAML is worth the extra training computation cost, or whether\n", "ProtoNet is already sufficient for the task at hand."]}, {"cell_type": "markdown", "id": "e546b5d0", "metadata": {"papermill": {"duration": 0.064218, "end_time": "2021-10-10T16:38:11.027954", "exception": false, "start_time": "2021-10-10T16:38:10.963736", "status": "completed"}, "tags": []}, "source": ["### References\n", "\n", "[1] Snell, Jake, Kevin Swersky, and Richard S. Zemel.\n", "\"Prototypical networks for few-shot learning.\"\n", "NeurIPS 2017.\n", "([link](https://arxiv.org/pdf/1703.05175.pdf))\n", "\n", "[2] Chelsea Finn, Pieter Abbeel, Sergey Levine.\n", "\"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks.\"\n", "ICML 2017.\n", "([link](http://proceedings.mlr.press/v70/finn17a.html))\n", "\n", "[3] Triantafillou, Eleni, Tyler Zhu, Vincent Dumoulin, Pascal Lamblin, Utku Evci, Kelvin Xu, Ross Goroshin et al.\n", "\"Meta-dataset: A dataset of datasets for learning to learn from few examples.\"\n", "ICLR 2020.\n", "([link](https://openreview.net/pdf?id=rkgAGAVKPr))"]}, {"cell_type": "markdown", "id": "468b2212", "metadata": {"papermill": {"duration": 0.062817, "end_time": "2021-10-10T16:38:11.155742", "exception": false, "start_time": "2021-10-10T16:38:11.092925", "status": "completed"}, "tags": []}, "source": ["## Congratulations - Time to Join the Community!\n", "\n", "Congratulations on completing this notebook tutorial! If you enjoyed this and would like to join the Lightning\n", "movement, you can do so in the following ways!\n", "\n", "### Star [Lightning](https://github.com/PyTorchLightning/pytorch-lightning) on GitHub\n", "The easiest way to help our community is just by starring the GitHub repos! This helps raise awareness of the cool\n", "tools we're building.\n", "\n", "### Join our [Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-pw5v393p-qRaDgEk24~EjiZNBpSQFgQ)!\n", "The best way to keep up to date on the latest advancements is to join our community! Make sure to introduce yourself\n", "and share your interests in `#general` channel\n", "\n", "\n", "### Contributions !\n", "The best way to contribute to our community is to become a code contributor! At any time you can go to\n", "[Lightning](https://github.com/PyTorchLightning/pytorch-lightning) or [Bolt](https://github.com/PyTorchLightning/lightning-bolts)\n", "GitHub Issues page and filter for \"good first issue\".\n", "\n", "* [Lightning good first issue](https://github.com/PyTorchLightning/pytorch-lightning/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", "* [Bolt good first issue](https://github.com/PyTorchLightning/lightning-bolts/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n", "* You can also contribute your own notebooks with useful examples !\n", "\n", "### Great thanks from the entire Pytorch Lightning Team for your interest !\n", "\n", "{height=\"60px\" width=\"240px\"}"]}, {"cell_type": "raw", "metadata": {"raw_mimetype": "text/restructuredtext"}, "source": [".. customcarditem::\n", " :header: Tutorial 12: Meta-Learning - Learning to Learn\n", " :card_description: In this tutorial, we will discuss algorithms that learn models which can quickly adapt to new classes and/or tasks with few samples. This area of machine learning is called...\n", " :tags: Few-shot-learning,MAML,ProtoNet,GPU/TPU,UvA-DL-Course\n", " :image: _static/images/course_UvA-DL/12-meta-learning.jpg"]}], "metadata": {"jupytext": {"cell_metadata_filter": "id,colab,colab_type,-all", "formats": "ipynb,py:percent", "main_language": "python"}, "language_info": {"codemirror_mode": {"name": "ipython", "version": 3}, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.7"}, "papermill": {"default_parameters": {}, "duration": 106.820185, "end_time": "2021-10-10T16:38:11.928740", "environment_variables": {}, "exception": null, "input_path": "course_UvA-DL/12-meta-learning/Meta_Learning.ipynb", "output_path": ".notebooks/course_UvA-DL/12-meta-learning.ipynb", "parameters": {}, "start_time": "2021-10-10T16:36:25.108555", "version": "2.3.3"}, "widgets": {"application/vnd.jupyter.widget-state+json": {"state": {"02efcb1a6aa4448eb2be5597b7229117": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": ""}}, "04c241d2abd34caa8d271a853e8f6a74": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": ["IPY_MODEL_94a0798591274c8b8b0011603eb7638f", "IPY_MODEL_b0685ba39080452fa095a152855ce3f5", "IPY_MODEL_df741ff3bf654a9b8b7a024c14f54f61"], "layout": "IPY_MODEL_5643ce9402954952881a5eb9119ff556"}}, "05eeda38820a4700b6808a22c087f854": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "06dabf4f2d724f2e855a18452a421901": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "0748cb2c03654ebebcdbf1bec54ef2a6": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_72ff32b019be4252b3a9736e42d05257", "placeholder": "\u200b", "style": "IPY_MODEL_693e0990c811418d8be6f20a3c613f3e", "value": " 42/47 [00:00<00:00, 83.87it/s]"}}, "074a0b76522b4e2ab81b2abed09f23a3": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": ["IPY_MODEL_bffa3c9c26424621a044f35fc72dc03f", "IPY_MODEL_65f3907fd55c4b4dbd91642a08fd39d9", "IPY_MODEL_4ea0e80530d34d4f8d8485c83df9da16"], "layout": "IPY_MODEL_cb0c7957cd344fd5b8e229b443f1640d"}}, "08d9ec62524244f1872cdb20191f3be7": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": ""}}, "0a0c945ddb6546be814dab292cf61c4e": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "0a2fabd9ce614e4ab1700634bc17e28e": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "1357795e20b8457abe5ee3078efe3ca7": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "136db4bc997541c5b3123895b1746e5e": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "16b537a4cb21479fa2564472a850f609": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "18aca4955a7a4c64a8eb12925d3704d7": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": ["IPY_MODEL_b380f61e129140fcb2daf6c273570e16", "IPY_MODEL_b7d2cb428c5c4272a094846477794af9", "IPY_MODEL_509d1c763a634f83b7fba1ad9494dc02"], "layout": "IPY_MODEL_74c3e37ba7ac43019562374aae3f8c4e"}}, "1984df6019f34935a0d89f8f0cc9c549": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": ""}}, "19f3640a3b6f411984df19dd9b9f2536": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "1b10c53ce772446d99285a37607ef5e3": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_f6e7ccff3f3f4b87983f1603bf0b3547", "placeholder": "\u200b", "style": "IPY_MODEL_241f1955c2624d60b29151d36487ef5e", "value": " 298/300 [00:13<00:00, 22.45it/s]"}}, "219937af24194529826e86cbeaa92dc1": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": ["IPY_MODEL_45c4fd2d576f4ecaa4df4aca60ed4377", "IPY_MODEL_5fa0132632af4e80b186723f1a5c9667", "IPY_MODEL_43bf706a87a74c8c903431b130a3b7cd"], "layout": "IPY_MODEL_314d69183852488f8d2526db24356295"}}, "241f1955c2624d60b29151d36487ef5e": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "25be42641c3c4d3abe06f325f7e5707c": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": ""}}, "26bde6db982d430988ad5224841c46b6": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "29ac64c53e904692b4e1bcacd235cb15": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "2cc8415ac50d463e9eb6eba8bd7441dd": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "2e1ac83c3a2b4bda89b392a3b2795d7d": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_842078486c2c449786473d055756c9f3", "placeholder": "\u200b", "style": "IPY_MODEL_fca8ada280ae405ab7fc84a435653757", "value": " 124/125 [00:02<00:00, 44.61it/s]"}}, "314d69183852488f8d2526db24356295": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "33082c5ed1d04d52bc8bf407f24b6cd2": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "3545a43fc2ba428b8b8c312ecdb91469": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_36c6f2b6dcba4d0386076ed767d9c503", "max": 300.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_441a767165c641359c9955258a379f90", "value": 300.0}}, "36c6f2b6dcba4d0386076ed767d9c503": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "3ae54407f35e4135929978d9d2889764": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e08469460c584a789dd3516b7d78ae77", "placeholder": "\u200b", "style": "IPY_MODEL_e46fb7aeb83b4002bdd245d9c6f731e3", "value": "Evaluating prototype classification: 99%"}}, "3c728764f18c47bc8b94ff75bfdde4f4": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "3d2ebb08ff2f4bdbacdb096b84f1ec09": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "3e6e0061bdc745beaac7f83f84327df4": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "3e99426778d245cbbafb04d6f52c153e": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": ""}}, "3ec9165e19ed46f8b78dfdfd0adc8ccf": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "4281b262e4a544969139ae166f292c37": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_cb1d437a4c354907bc26e5c54ca76168", "max": 47.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_ea8059402deb40659f77d6c63d7f8d09", "value": 47.0}}, "43bbd6d914404eb7be1ccc7417e0c882": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "43bf706a87a74c8c903431b130a3b7cd": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_1357795e20b8457abe5ee3078efe3ca7", "placeholder": "\u200b", "style": "IPY_MODEL_4b795244ba454b47bca4061ab2fc69a7", "value": " 34/38 [00:00<00:00, 52.34it/s]"}}, "441a767165c641359c9955258a379f90": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": ""}}, "447d64a260fa4e579069160a3d9460de": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "45c4fd2d576f4ecaa4df4aca60ed4377": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_cc4167da1b794828ab4eb0679922efe1", "placeholder": "\u200b", "style": "IPY_MODEL_48a737ec864a4e288e6cf338e313bf74", "value": "Evaluating prototype classification: 89%"}}, "461f881689924b8e82af3e96a920be27": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_3c728764f18c47bc8b94ff75bfdde4f4", "placeholder": "\u200b", "style": "IPY_MODEL_d939ed1df36b4c5db18f4b0496ee48de", "value": " 72/75 [00:22<00:00, 17.74it/s]"}}, "467e71f262cf432fba62ed8d75effd3a": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "48a737ec864a4e288e6cf338e313bf74": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "495f557ce24948f0968a8e77cc121b55": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d2c2b819979a476a8482e9d67ebab1a7", "placeholder": "\u200b", "style": "IPY_MODEL_557662d2d3e3487cbedd294325df6f31", "value": ""}}, "4b795244ba454b47bca4061ab2fc69a7": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "4c13f424d1bb4cf0a44284e678229cf7": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "4d5211d9d6e24a2cb1baa906ffa8dac2": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": ""}}, "4ea0e80530d34d4f8d8485c83df9da16": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_29ac64c53e904692b4e1bcacd235cb15", "placeholder": "\u200b", "style": "IPY_MODEL_a37e0600abe64891ba7bad38e42cae86", "value": " 12/16 [00:00<00:00, 117.22it/s]"}}, "4fd996b6dd534694b6413f376e6be22c": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "509d1c763a634f83b7fba1ad9494dc02": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_b19b954922464bc3ae7a287ae8e7ba36", "placeholder": "\u200b", "style": "IPY_MODEL_f4334aa28f094684884cba73f70d9539", "value": " 148/150 [00:04<00:00, 37.03it/s]"}}, "557662d2d3e3487cbedd294325df6f31": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "5643ce9402954952881a5eb9119ff556": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "59b3b0d90a7548ae8ec79d1fb1aa783e": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": ["IPY_MODEL_fc0cd3a5fceb46438c8831f7ace96e8e", "IPY_MODEL_4281b262e4a544969139ae166f292c37", "IPY_MODEL_0748cb2c03654ebebcdbf1bec54ef2a6"], "layout": "IPY_MODEL_5c60626bcc1c4a56a49881ed8afd804c"}}, "5b9c06753fca42ca89e480bfe3de1b06": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_eae30ee4b8e54cfbafa7a73ac8c3720d", "max": 250.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_02efcb1a6aa4448eb2be5597b7229117", "value": 250.0}}, "5c60626bcc1c4a56a49881ed8afd804c": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "5fa0132632af4e80b186723f1a5c9667": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_2cc8415ac50d463e9eb6eba8bd7441dd", "max": 38.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_b4923b5857b447e2aca7a73524cbb3bb", "value": 38.0}}, "6051618a7e8943ce91d14f6a31a0f679": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "65f3907fd55c4b4dbd91642a08fd39d9": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_c39a5cb98e1644529c1364704681c37d", "max": 16.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_7b48347de2bd47e88549b165c7af8d90", "value": 16.0}}, "66330b6ebefe44c7906d3e6e5fd221c6": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "693e0990c811418d8be6f20a3c613f3e": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "69f9bf1e8e3c43d0a2225f3c3d6cf91d": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "6ae81549f8a343a2985e8fbdd3e6cfce": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": ["IPY_MODEL_9643addbcabd45b48bba6f84b24900f2", "IPY_MODEL_d022e70ba7ff4133a278315f4cabdec8", "IPY_MODEL_f69a45ea7e884b48bc7e22af83113f6d"], "layout": "IPY_MODEL_3ec9165e19ed46f8b78dfdfd0adc8ccf"}}, "6b6ae741f4c442b5bcccfbb60ea48963": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "6e439485ca4e47de8597c3af51ac4d8a": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_dee61b262f264abe9c8f19123bb21078", "max": 32.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_90ce08a097804618b4b4aa29e00c2221", "value": 32.0}}, "72ff32b019be4252b3a9736e42d05257": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "738ae6a5004b4fcd8e1acf8973c7fcf6": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "7427ffde194a471bb68404b98bba5521": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_6b6ae741f4c442b5bcccfbb60ea48963", "placeholder": "\u200b", "style": "IPY_MODEL_4c13f424d1bb4cf0a44284e678229cf7", "value": " 169001984/? [00:01<00:00, 116158853.76it/s]"}}, "74c3e37ba7ac43019562374aae3f8c4e": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "77ca484b49b447dc9c081a459a84ab3b": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "783a9fed2b1a4153869348f1b4cd9bdf": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "7b48347de2bd47e88549b165c7af8d90": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": ""}}, "7f28b92e80274d7f9b778bfb634ac8db": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_3e6e0061bdc745beaac7f83f84327df4", "max": 75.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_3e99426778d245cbbafb04d6f52c153e", "value": 75.0}}, "8058b34966e64a54a236152f5de30268": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "820542f219d34da6af0d83ed20f6756d": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": ["IPY_MODEL_a38734b949f0443fae617d76a196b40f", "IPY_MODEL_6e439485ca4e47de8597c3af51ac4d8a", "IPY_MODEL_84f66ce16b0a435eb9746909f90b69b5"], "layout": "IPY_MODEL_cac735df1f3544b0a8a2c89d88e27d1c"}}, "8352a72f638049be98819a832027cb10": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "842078486c2c449786473d055756c9f3": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "84a6abc3c3d54dd7a08fbc7b8dfd07f3": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": ["IPY_MODEL_97e410e1d6a245009d4f410fbf407f2a", "IPY_MODEL_f5f64e7b652046608b09e1865fc8929c", "IPY_MODEL_ae07625fe7bd4a2cbbbf1d0890d6df36"], "layout": "IPY_MODEL_cc5e5ce694504583a2d4dcaf311d80c2"}}, "84f66ce16b0a435eb9746909f90b69b5": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_738ae6a5004b4fcd8e1acf8973c7fcf6", "placeholder": "\u200b", "style": "IPY_MODEL_0a0c945ddb6546be814dab292cf61c4e", "value": " 31/32 [00:00<00:00, 97.75it/s]"}}, "8a82349f3b624433926ed46218343ef9": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "90ce08a097804618b4b4aa29e00c2221": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": ""}}, "93c64b6a35e441bf9a79602a829a41d7": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": ["IPY_MODEL_b35a4714ac784c49970726e49084c08b", "IPY_MODEL_5b9c06753fca42ca89e480bfe3de1b06", "IPY_MODEL_b81a79f5481446ad9a9ef8597cc47731"], "layout": "IPY_MODEL_b6c8207aebc64e519f57ea458016b8d8"}}, "94a0798591274c8b8b0011603eb7638f": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_b8d61566453f40a8a10086d9159efd3f", "placeholder": "\u200b", "style": "IPY_MODEL_467e71f262cf432fba62ed8d75effd3a", "value": ""}}, "9643addbcabd45b48bba6f84b24900f2": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_efed4fdf79514ceabb9b9762cc24d4a2", "placeholder": "\u200b", "style": "IPY_MODEL_c0993cf20a304d07b41e2a11fa17f1ef", "value": "Extracting image features: 78%"}}, "97e410e1d6a245009d4f410fbf407f2a": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_136db4bc997541c5b3123895b1746e5e", "placeholder": "\u200b", "style": "IPY_MODEL_783a9fed2b1a4153869348f1b4cd9bdf", "value": "Evaluating prototype classification: 97%"}}, "9a243670d2374f4ca046908284044ab5": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "9dc8c432361347f482dc1fbac96f1ec5": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "a09bea6c4bec4d14b6ac5fc81cf9461a": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": ""}}, "a0ee70498fb94ecc9c39238ad029ae29": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_26bde6db982d430988ad5224841c46b6", "max": 125.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_4d5211d9d6e24a2cb1baa906ffa8dac2", "value": 125.0}}, "a28f68eaf131448ebb0bc0fb801bfd0b": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_ef2a48d284cd4a8b99863c678d1eff1f", "placeholder": "\u200b", "style": "IPY_MODEL_e67ab28b10924b64a5d18ea090aa87e8", "value": "Evaluating prototype classification: 53%"}}, "a37e0600abe64891ba7bad38e42cae86": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "a38734b949f0443fae617d76a196b40f": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_69f9bf1e8e3c43d0a2225f3c3d6cf91d", "placeholder": "\u200b", "style": "IPY_MODEL_3d2ebb08ff2f4bdbacdb096b84f1ec09", "value": "Evaluating prototype classification: 97%"}}, "a4f9318e26d847d394ca5e252d5bbaf4": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_8058b34966e64a54a236152f5de30268", "max": 19.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_08d9ec62524244f1872cdb20191f3be7", "value": 19.0}}, "a878ed48e3e745238604dc0491a31f1e": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "acb6f2dd23f94af091e7ed4aa1b7a3de": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_8a82349f3b624433926ed46218343ef9", "placeholder": "\u200b", "style": "IPY_MODEL_fb4936f8301947a686a8c8fe1df1eb27", "value": "Evaluating prototype classification: 99%"}}, "ae07625fe7bd4a2cbbbf1d0890d6df36": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_eda1ed0aecca4420a13f2ac4cc2475a3", "placeholder": "\u200b", "style": "IPY_MODEL_d36132a1ac6044e08ce39355ab0e24c0", "value": " 61/63 [00:00<00:00, 64.84it/s]"}}, "b0685ba39080452fa095a152855ce3f5": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d388d078f57a4be6a40dfb1d09fcdb68", "max": 64275384.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_a09bea6c4bec4d14b6ac5fc81cf9461a", "value": 64275384.0}}, "b19b954922464bc3ae7a287ae8e7ba36": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "b35a4714ac784c49970726e49084c08b": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_9a243670d2374f4ca046908284044ab5", "placeholder": "\u200b", "style": "IPY_MODEL_e79716d59af843ae8291b7d25d7afa97", "value": "Evaluating prototype classification: 100%"}}, "b380f61e129140fcb2daf6c273570e16": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_a878ed48e3e745238604dc0491a31f1e", "placeholder": "\u200b", "style": "IPY_MODEL_f449bfa0562f46dd9d166a6667df8ce2", "value": "Evaluating prototype classification: 99%"}}, "b46d974e72914b52bd20ced66ed6fcd3": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "b4923b5857b447e2aca7a73524cbb3bb": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": ""}}, "b6767d1462de4f8b8eb018e9f51ef402": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": ["IPY_MODEL_e8f08f9a11444d0fbdfeaeebcdc3ac7a", "IPY_MODEL_7f28b92e80274d7f9b778bfb634ac8db", "IPY_MODEL_461f881689924b8e82af3e96a920be27"], "layout": "IPY_MODEL_c0922c095d624b36adfc21be13d915e9"}}, "b6c8207aebc64e519f57ea458016b8d8": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "b7d2cb428c5c4272a094846477794af9": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_16b537a4cb21479fa2564472a850f609", "max": 150.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_1984df6019f34935a0d89f8f0cc9c549", "value": 150.0}}, "b81a79f5481446ad9a9ef8597cc47731": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_be1415cbc6e14d888ea2e0f649648c2a", "placeholder": "\u200b", "style": "IPY_MODEL_447d64a260fa4e579069160a3d9460de", "value": " 249/250 [00:09<00:00, 26.83it/s]"}}, "b8d61566453f40a8a10086d9159efd3f": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "bcd5770b13c540db929b606eb7518b21": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "be1415cbc6e14d888ea2e0f649648c2a": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "bffa3c9c26424621a044f35fc72dc03f": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_66330b6ebefe44c7906d3e6e5fd221c6", "placeholder": "\u200b", "style": "IPY_MODEL_c3f25997fc9b49649de9d4690d00ba4d", "value": "Evaluating prototype classification: 75%"}}, "c0922c095d624b36adfc21be13d915e9": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "c0993cf20a304d07b41e2a11fa17f1ef": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "c2ce51ed3ad643b2b521e696f82af495": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": ["IPY_MODEL_3ae54407f35e4135929978d9d2889764", "IPY_MODEL_3545a43fc2ba428b8b8c312ecdb91469", "IPY_MODEL_1b10c53ce772446d99285a37607ef5e3"], "layout": "IPY_MODEL_8352a72f638049be98819a832027cb10"}}, "c39a5cb98e1644529c1364704681c37d": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "c3f25997fc9b49649de9d4690d00ba4d": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "c40fd99740dc4dd5980ca6537e42c5d0": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "cac735df1f3544b0a8a2c89d88e27d1c": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "cb0c7957cd344fd5b8e229b443f1640d": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "cb1d437a4c354907bc26e5c54ca76168": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "cc4167da1b794828ab4eb0679922efe1": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "cc5e5ce694504583a2d4dcaf311d80c2": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "cd0b594802d34dd58532e00bad4a7397": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "ceabb6b1df1d4a1284de89bb635533c0": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_4fd996b6dd534694b6413f376e6be22c", "max": 169001437.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_e7e09bfea2384e90951c090fc2a680e7", "value": 169001437.0}}, "d022e70ba7ff4133a278315f4cabdec8": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_05eeda38820a4700b6808a22c087f854", "max": 40.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_dfd6e04d1360446d9ef1db11256ebe69", "value": 40.0}}, "d2c2b819979a476a8482e9d67ebab1a7": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "d36132a1ac6044e08ce39355ab0e24c0": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "d388d078f57a4be6a40dfb1d09fcdb68": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "d939ed1df36b4c5db18f4b0496ee48de": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "db308fcc8f994e4aabcd079e27a47da6": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "de8827ff3a9b4e519927fb64aa069b4d": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "dee61b262f264abe9c8f19123bb21078": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "df741ff3bf654a9b8b7a024c14f54f61": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_77ca484b49b447dc9c081a459a84ab3b", "placeholder": "\u200b", "style": "IPY_MODEL_b46d974e72914b52bd20ced66ed6fcd3", "value": " 64275456/? [00:04<00:00, 21648157.34it/s]"}}, "dfd6e04d1360446d9ef1db11256ebe69": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": ""}}, "e08469460c584a789dd3516b7d78ae77": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "e46fb7aeb83b4002bdd245d9c6f731e3": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "e67ab28b10924b64a5d18ea090aa87e8": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "e79716d59af843ae8291b7d25d7afa97": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "e7e09bfea2384e90951c090fc2a680e7": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": ""}}, "e8f08f9a11444d0fbdfeaeebcdc3ac7a": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_9dc8c432361347f482dc1fbac96f1ec5", "placeholder": "\u200b", "style": "IPY_MODEL_bcd5770b13c540db929b606eb7518b21", "value": "Evaluating prototype classification: 96%"}}, "e9c2476de61b41c78b739b3465029786": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": ["IPY_MODEL_acb6f2dd23f94af091e7ed4aa1b7a3de", "IPY_MODEL_a0ee70498fb94ecc9c39238ad029ae29", "IPY_MODEL_2e1ac83c3a2b4bda89b392a3b2795d7d"], "layout": "IPY_MODEL_6051618a7e8943ce91d14f6a31a0f679"}}, "ea8059402deb40659f77d6c63d7f8d09": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": ""}}, "eae30ee4b8e54cfbafa7a73ac8c3720d": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "ed46b8de7055431dafc7c8dbf5aede81": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_43bbd6d914404eb7be1ccc7417e0c882", "placeholder": "\u200b", "style": "IPY_MODEL_19f3640a3b6f411984df19dd9b9f2536", "value": " 10/19 [00:00<00:00, 97.06it/s]"}}, "eda1ed0aecca4420a13f2ac4cc2475a3": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "ef2a48d284cd4a8b99863c678d1eff1f": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "efed4fdf79514ceabb9b9762cc24d4a2": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "f4334aa28f094684884cba73f70d9539": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "f449bfa0562f46dd9d166a6667df8ce2": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "f523d40c013f4da7bc639dc9291509e8": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": ["IPY_MODEL_495f557ce24948f0968a8e77cc121b55", "IPY_MODEL_ceabb6b1df1d4a1284de89bb635533c0", "IPY_MODEL_7427ffde194a471bb68404b98bba5521"], "layout": "IPY_MODEL_33082c5ed1d04d52bc8bf407f24b6cd2"}}, "f5f64e7b652046608b09e1865fc8929c": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_cd0b594802d34dd58532e00bad4a7397", "max": 63.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_25be42641c3c4d3abe06f325f7e5707c", "value": 63.0}}, "f69a45ea7e884b48bc7e22af83113f6d": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_0a2fabd9ce614e4ab1700634bc17e28e", "placeholder": "\u200b", "style": "IPY_MODEL_c40fd99740dc4dd5980ca6537e42c5d0", "value": " 31/40 [00:00<00:00, 74.38it/s]"}}, "f6e7ccff3f3f4b87983f1603bf0b3547": {"model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {"_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null}}, "fb4936f8301947a686a8c8fe1df1eb27": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "fc0cd3a5fceb46438c8831f7ace96e8e": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_db308fcc8f994e4aabcd079e27a47da6", "placeholder": "\u200b", "style": "IPY_MODEL_de8827ff3a9b4e519927fb64aa069b4d", "value": "Extracting image features: 89%"}}, "fca8ada280ae405ab7fc84a435653757": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": {"_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": ""}}, "ffaf8189884a44548efd49c252a85a7a": {"model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": {"_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": ["IPY_MODEL_a28f68eaf131448ebb0bc0fb801bfd0b", "IPY_MODEL_a4f9318e26d847d394ca5e252d5bbaf4", "IPY_MODEL_ed46b8de7055431dafc7c8dbf5aede81"], "layout": "IPY_MODEL_06dabf4f2d724f2e855a18452a421901"}}}, "version_major": 2, "version_minor": 0}}}, "nbformat": 4, "nbformat_minor": 5}