{"cells": [{"cell_type": "markdown", "id": "6000551a", "metadata": {"papermill": {"duration": 0.030399, "end_time": "2021-10-10T16:38:20.779892", "exception": false, "start_time": "2021-10-10T16:38:20.749493", "status": "completed"}, "tags": []}, "source": ["\n", "# Tutorial 13: Self-Supervised Contrastive Learning with SimCLR\n", "\n", "* **Author:** Phillip Lippe\n", "* **License:** CC BY-SA\n", "* **Generated:** 2021-10-10T18:35:52.598167\n", "\n", "In this tutorial, we will take a closer look at self-supervised contrastive learning.\n", "Self-supervised learning, or also sometimes called unsupervised learning, describes the scenario where we have given input data, but no accompanying labels to train in a classical supervised way.\n", "However, this data still contains a lot of information from which we can learn: how are the images different from each other?\n", "What patterns are descriptive for certain images?\n", "Can we cluster the images?\n", "To get an insight into these questions, we will implement a popular, simple contrastive learning method, SimCLR, and apply it to the STL10 dataset.\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/13-contrastive-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": "c075e657", "metadata": {"papermill": {"duration": 0.028259, "end_time": "2021-10-10T16:38:20.837183", "exception": false, "start_time": "2021-10-10T16:38:20.808924", "status": "completed"}, "tags": []}, "source": ["## Setup\n", "This notebook requires some packages besides pytorch-lightning."]}, {"cell_type": "code", "execution_count": 1, "id": "132c3c36", "metadata": {"colab": {}, "colab_type": "code", "execution": {"iopub.execute_input": "2021-10-10T16:38:20.897899Z", "iopub.status.busy": "2021-10-10T16:38:20.897428Z", "iopub.status.idle": "2021-10-10T16:38:20.900024Z", "shell.execute_reply": "2021-10-10T16:38:20.899479Z"}, "id": "LfrJLKPFyhsK", "lines_to_next_cell": 0, "papermill": {"duration": 0.034648, "end_time": "2021-10-10T16:38:20.900141", "exception": false, "start_time": "2021-10-10T16:38:20.865493", "status": "completed"}, "tags": []}, "outputs": [], "source": ["# ! pip install --quiet \"torch>=1.6, <1.9\" \"matplotlib\" \"pytorch-lightning>=1.3\" \"seaborn\" \"torchvision\" \"torchmetrics>=0.3\""]}, {"cell_type": "markdown", "id": "15410d3c", "metadata": {"papermill": {"duration": 0.02886, "end_time": "2021-10-10T16:38:20.957863", "exception": false, "start_time": "2021-10-10T16:38:20.929003", "status": "completed"}, "tags": []}, "source": ["<div class=\"center-wrapper\"><div class=\"video-wrapper\"><iframe src=\"https://www.youtube.com/embed/waVZDFR-06U\" title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen></iframe></div></div>\n", "Methods for self-supervised learning try to learn as much as possible from the data alone, so it can quickly be finetuned for a specific classification task.\n", "The benefit of self-supervised learning is that a large dataset can often easily be obtained.\n", "For instance, if we want to train a vision model on semantic segmentation for autonomous driving, we can collect large amounts of data by simply installing a camera in a car, and driving through a city for an hour.\n", "In contrast, if we would want to do supervised learning, we would have to manually label all those images before training a model.\n", "This is extremely expensive, and would likely take a couple of months to manually label the same amount of data.\n", "Further, self-supervised learning can provide an alternative to transfer learning from models pretrained on ImageNet since we could pretrain a model on a specific dataset/situation, e.g. traffic scenarios for autonomous driving.\n", "\n", "Within the last two years, a lot of new approaches have been proposed for self-supervised learning, in particular for images, that have resulted in great improvements over supervised models when few labels are available.\n", "The subfield that we will focus on in this tutorial is contrastive learning.\n", "Contrastive learning is motivated by the question mentioned above: how are images different from each other?\n", "Specifically, contrastive learning methods train a model to cluster an image and its slightly augmented version in latent space, while the distance to other images should be maximized.\n", "A very recent and simple method for this is [SimCLR](https://arxiv.org/abs/2006.10029), which is visualized below (figure credit - [Ting Chen et al. ](https://simclr.github.io/)).\n", "\n", "<center width=\"100%\"> {width=\"500px\"} </center>\n", "\n", "The general setup is that we are given a dataset of images without any labels, and want to train a model on this data such that it can quickly adapt to any image recognition task afterward.\n", "During each training iteration, we sample a batch of images as usual.\n", "For each image, we create two versions by applying data augmentation techniques like cropping, Gaussian noise, blurring, etc.\n", "An example of such is shown on the left with the image of the dog.\n", "We will go into the details and effects of the chosen augmentation techniques later.\n", "On those images, we apply a CNN like ResNet and obtain as output a 1D feature vector on which we apply a small MLP.\n", "The output features of the two augmented images are then trained to be close to each other, while all other images in that batch should be as different as possible.\n", "This way, the model has to learn to recognize the content of the image that remains unchanged under the data augmentations, such as objects which we usually care about in supervised tasks.\n", "\n", "We will now implement this framework ourselves and discuss further details along the way.\n", "Let's first start with importing our standard libraries below:"]}, {"cell_type": "code", "execution_count": 2, "id": "e2627246", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:38:21.024058Z", "iopub.status.busy": "2021-10-10T16:38:21.022126Z", "iopub.status.idle": "2021-10-10T16:38:22.765560Z", "shell.execute_reply": "2021-10-10T16:38:22.765143Z"}, "papermill": {"duration": 1.779594, "end_time": "2021-10-10T16:38:22.765675", "exception": false, "start_time": "2021-10-10T16:38:20.986081", "status": "completed"}, "tags": []}, "outputs": [{"name": "stderr", "output_type": "stream", "text": ["/tmp/ipykernel_1189/3845858059.py:24: 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", "Number of workers: 12\n"]}, {"data": {"text/plain": ["<Figure size 432x288 with 0 Axes>"]}, "metadata": {}, "output_type": "display_data"}], "source": ["import os\n", "import urllib.request\n", "from copy import deepcopy\n", "from urllib.error import HTTPError\n", "\n", "import matplotlib\n", "import matplotlib.pyplot as plt\n", "import pytorch_lightning as pl\n", "import seaborn as sns\n", "import torch\n", "import torch.nn as nn\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 pytorch_lightning.callbacks import LearningRateMonitor, ModelCheckpoint\n", "from torchvision import transforms\n", "from torchvision.datasets import STL10\n", "from tqdm.notebook 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.set()\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/ContrastiveLearning/\")\n", "# In this notebook, we use data loaders with heavier computational processing. It is recommended to use as many\n", "# workers as possible in a data loader, which corresponds to the number of CPU cores\n", "NUM_WORKERS = os.cpu_count()\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)\n", "print(\"Number of workers:\", NUM_WORKERS)"]}, {"cell_type": "markdown", "id": "ae59fd9f", "metadata": {"papermill": {"duration": 0.029754, "end_time": "2021-10-10T16:38:22.826902", "exception": false, "start_time": "2021-10-10T16:38:22.797148", "status": "completed"}, "tags": []}, "source": ["As in many tutorials before, we provide pre-trained models.\n", "Note that those models are slightly larger as normal (~100MB overall) since we use the default ResNet-18 architecture.\n", "If you are running this notebook locally, make sure to have sufficient disk space available."]}, {"cell_type": "code", "execution_count": 3, "id": "482bf0ff", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:38:22.890766Z", "iopub.status.busy": "2021-10-10T16:38:22.887393Z", "iopub.status.idle": "2021-10-10T16:38:25.058940Z", "shell.execute_reply": "2021-10-10T16:38:25.058450Z"}, "papermill": {"duration": 2.20285, "end_time": "2021-10-10T16:38:25.059060", "exception": false, "start_time": "2021-10-10T16:38:22.856210", "status": "completed"}, "tags": []}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial17/SimCLR.ckpt...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial17/ResNet.ckpt...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial17/tensorboards/SimCLR/events.out.tfevents.SimCLR...\n", "Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial17/tensorboards/classification/ResNet/events.out.tfevents.ResNet...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial17/LogisticRegression_10.ckpt...\n", "Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial17/LogisticRegression_20.ckpt...\n", "Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial17/LogisticRegression_50.ckpt...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial17/LogisticRegression_100.ckpt...\n", "Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial17/LogisticRegression_200.ckpt...\n", "Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial17/LogisticRegression_500.ckpt...\n"]}], "source": ["# Github URL where saved models are stored for this tutorial\n", "base_url = \"https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial17/\"\n", "# Files to download\n", "pretrained_files = [\n", " \"SimCLR.ckpt\",\n", " \"ResNet.ckpt\",\n", " \"tensorboards/SimCLR/events.out.tfevents.SimCLR\",\n", " \"tensorboards/classification/ResNet/events.out.tfevents.ResNet\",\n", "]\n", "pretrained_files += [f\"LogisticRegression_{size}.ckpt\" for size in [10, 20, 50, 100, 200, 500]]\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(f\"Downloading {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": "f7e66a12", "metadata": {"papermill": {"duration": 0.030275, "end_time": "2021-10-10T16:38:25.125477", "exception": false, "start_time": "2021-10-10T16:38:25.095202", "status": "completed"}, "tags": []}, "source": ["## SimCLR\n", "\n", "We will start our exploration of contrastive learning by discussing the effect of different data augmentation techniques, and how we can implement an efficient data loader for such.\n", "Next, we implement SimCLR with PyTorch Lightning, and finally train it on a large, unlabeled dataset."]}, {"cell_type": "markdown", "id": "f78a4c91", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.030063, "end_time": "2021-10-10T16:38:25.185749", "exception": false, "start_time": "2021-10-10T16:38:25.155686", "status": "completed"}, "tags": []}, "source": ["### Data Augmentation for Contrastive Learning\n", "\n", "To allow efficient training, we need to prepare the data loading such that we sample two different, random augmentations for each image in the batch.\n", "The easiest way to do this is by creating a transformation that, when being called, applies a set of data augmentations to an image twice.\n", "This is implemented in the class `ContrastiveTransformations` below:"]}, {"cell_type": "code", "execution_count": 4, "id": "c7868578", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:38:25.253314Z", "iopub.status.busy": "2021-10-10T16:38:25.252845Z", "iopub.status.idle": "2021-10-10T16:38:25.254844Z", "shell.execute_reply": "2021-10-10T16:38:25.254446Z"}, "papermill": {"duration": 0.036682, "end_time": "2021-10-10T16:38:25.254947", "exception": false, "start_time": "2021-10-10T16:38:25.218265", "status": "completed"}, "tags": []}, "outputs": [], "source": ["class ContrastiveTransformations:\n", " def __init__(self, base_transforms, n_views=2):\n", " self.base_transforms = base_transforms\n", " self.n_views = n_views\n", "\n", " def __call__(self, x):\n", " return [self.base_transforms(x) for i in range(self.n_views)]"]}, {"cell_type": "markdown", "id": "ebf730fc", "metadata": {"papermill": {"duration": 0.030955, "end_time": "2021-10-10T16:38:25.316735", "exception": false, "start_time": "2021-10-10T16:38:25.285780", "status": "completed"}, "tags": []}, "source": ["The contrastive learning framework can easily be extended to have more _positive_ examples by sampling more than two augmentations of the same image.\n", "However, the most efficient training is usually obtained by using only two.\n", "\n", "Next, we can look at the specific augmentations we want to apply.\n", "The choice of the data augmentation to use is the most crucial hyperparameter in SimCLR since it directly affects how the latent space is structured, and what patterns might be learned from the data.\n", "Let's first take a look at some of the most popular data augmentations (figure credit - [Ting Chen and Geoffrey Hinton](https://ai.googleblog.com/2020/04/advancing-self-supervised-and-semi.html)):\n", "\n", "<center width=\"100%\"><img src=\"https://github.com/PyTorchLightning/lightning-tutorials/raw/main/course_UvA-DL/13-contrastive-learning/simclr_data_augmentations.jpg\" width=\"800px\" style=\"padding-top: 10px; padding-bottom: 10px\"></center>\n", "\n", "All of them can be used, but it turns out that two augmentations stand out in their importance: crop-and-resize, and color distortion.\n", "Interestingly, however, they only lead to strong performance if they have been used together as discussed by [Ting Chen et al. ](https://arxiv.org/abs/2006.10029) in their SimCLR paper.\n", "When performing randomly cropping and resizing, we can distinguish between two situations: (a) cropped image A provides a local view of cropped image B, or (b) cropped images C and D show neighboring views of the same image (figure credit - [Ting Chen and Geoffrey Hinton](https://ai.googleblog.com/2020/04/advancing-self-supervised-and-semi.html)).\n", "\n", "<center width=\"100%\"><img src=\"https://github.com/PyTorchLightning/lightning-tutorials/raw/main/course_UvA-DL/13-contrastive-learning/crop_views.svg\" width=\"400px\" style=\"padding-top: 20px; padding-bottom: 0px\"></center>\n", "\n", "While situation (a) requires the model to learn some sort of scale invariance to make crops A and B similar in latent space, situation (b) is more challenging since the model needs to recognize an object beyond its limited view.\n", "However, without color distortion, there is a loophole that the model can exploit, namely that different crops of the same image usually look very similar in color space.\n", "Consider the picture of the dog above.\n", "Simply from the color of the fur and the green color tone of the background, you can reason that two patches belong to the same image without actually recognizing the dog in the picture.\n", "In this case, the model might end up focusing only on the color histograms of the images, and ignore other more generalizable features.\n", "If, however, we distort the colors in the two patches randomly and independently of each other, the model cannot rely on this simple feature anymore.\n", "Hence, by combining random cropping and color distortions, the model can only match two patches by learning generalizable representations.\n", "\n", "Overall, for our experiments, we apply a set of 5 transformations following the original SimCLR setup: random horizontal flip, crop-and-resize, color distortion, random grayscale, and gaussian blur.\n", "In comparison to the [original implementation](https://github.com/google-research/simclr), we reduce the effect of the color jitter slightly (0.5 instead of 0.8 for brightness, contrast, and saturation, and 0.1 instead of 0.2 for hue).\n", "In our experiments, this setting obtained better performance and was faster and more stable to train.\n", "If, for instance, the brightness scale highly varies in a dataset, the\n", "original settings can be more beneficial since the model can't rely on\n", "this information anymore to distinguish between images."]}, {"cell_type": "code", "execution_count": 5, "id": "cfb65837", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:38:25.382410Z", "iopub.status.busy": "2021-10-10T16:38:25.381935Z", "iopub.status.idle": "2021-10-10T16:38:25.383969Z", "shell.execute_reply": "2021-10-10T16:38:25.383557Z"}, "papermill": {"duration": 0.036481, "end_time": "2021-10-10T16:38:25.384069", "exception": false, "start_time": "2021-10-10T16:38:25.347588", "status": "completed"}, "tags": []}, "outputs": [], "source": ["contrast_transforms = transforms.Compose(\n", " [\n", " transforms.RandomHorizontalFlip(),\n", " transforms.RandomResizedCrop(size=96),\n", " transforms.RandomApply([transforms.ColorJitter(brightness=0.5, contrast=0.5, saturation=0.5, hue=0.1)], p=0.8),\n", " transforms.RandomGrayscale(p=0.2),\n", " transforms.GaussianBlur(kernel_size=9),\n", " transforms.ToTensor(),\n", " transforms.Normalize((0.5,), (0.5,)),\n", " ]\n", ")"]}, {"cell_type": "markdown", "id": "64514ea2", "metadata": {"papermill": {"duration": 0.030802, "end_time": "2021-10-10T16:38:25.444902", "exception": false, "start_time": "2021-10-10T16:38:25.414100", "status": "completed"}, "tags": []}, "source": ["After discussing the data augmentation techniques, we can now focus on the dataset.\n", "In this tutorial, we will use the [STL10 dataset](https://cs.stanford.edu/~acoates/stl10/), which, similarly to CIFAR10, contains images of 10 classes: airplane, bird, car, cat, deer, dog, horse, monkey, ship, truck.\n", "However, the images have a higher resolution, namely $96\\times 96$ pixels, and we are only provided with 500 labeled images per class.\n", "Additionally, we have a much larger set of $100,000$ unlabeled images which are similar to the training images but are sampled from a wider range of animals and vehicles.\n", "This makes the dataset ideal to showcase the benefits that self-supervised learning offers.\n", "\n", "Luckily, the STL10 dataset is provided through torchvision.\n", "Keep in mind, however, that since this dataset is relatively large and has a considerably higher resolution than CIFAR10, it requires more disk space (~3GB) and takes a bit of time to download.\n", "For our initial discussion of self-supervised learning and SimCLR, we\n", "will create two data loaders with our contrastive transformations above:\n", "the `unlabeled_data` will be used to train our model via contrastive\n", "learning, and `train_data_contrast` will be used as a validation set in\n", "contrastive learning."]}, {"cell_type": "code", "execution_count": 6, "id": "5893d109", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:38:25.510013Z", "iopub.status.busy": "2021-10-10T16:38:25.509537Z", "iopub.status.idle": "2021-10-10T16:41:52.516922Z", "shell.execute_reply": "2021-10-10T16:41:52.517324Z"}, "papermill": {"duration": 207.042247, "end_time": "2021-10-10T16:41:52.517484", "exception": false, "start_time": "2021-10-10T16:38:25.475237", "status": "completed"}, "tags": []}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Downloading http://ai.stanford.edu/~acoates/stl10/stl10_binary.tar.gz to /__w/1/s/.datasets/stl10_binary.tar.gz\n"]}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "c111f74da90d4a8f831df4733df12b94", "version_major": 2, "version_minor": 0}, "text/plain": [" 0%| | 0/2640397119 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"name": "stdout", "output_type": "stream", "text": ["Extracting /__w/1/s/.datasets/stl10_binary.tar.gz to /__w/1/s/.datasets\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Files already downloaded and verified\n"]}], "source": ["unlabeled_data = STL10(\n", " root=DATASET_PATH,\n", " split=\"unlabeled\",\n", " download=True,\n", " transform=ContrastiveTransformations(contrast_transforms, n_views=2),\n", ")\n", "train_data_contrast = STL10(\n", " root=DATASET_PATH,\n", " split=\"train\",\n", " download=True,\n", " transform=ContrastiveTransformations(contrast_transforms, n_views=2),\n", ")"]}, {"cell_type": "markdown", "id": "b5b37f86", "metadata": {"papermill": {"duration": 0.103929, "end_time": "2021-10-10T16:41:52.724307", "exception": false, "start_time": "2021-10-10T16:41:52.620378", "status": "completed"}, "tags": []}, "source": ["Finally, before starting with our implementation of SimCLR, let's look\n", "at some example image pairs sampled with our augmentations:"]}, {"cell_type": "code", "execution_count": 7, "id": "b8165695", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:41:52.980855Z", "iopub.status.busy": "2021-10-10T16:41:52.980381Z", "iopub.status.idle": "2021-10-10T16:41:53.330052Z", "shell.execute_reply": "2021-10-10T16:41:53.330430Z"}, "papermill": {"duration": 0.502194, "end_time": "2021-10-10T16:41:53.330573", "exception": false, "start_time": "2021-10-10T16:41:52.828379", "status": "completed"}, "tags": []}, "outputs": [{"name": "stderr", "output_type": "stream", "text": ["Global seed set to 42\n"]}, {"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=\"216.779142pt\" version=\"1.1\" viewBox=\"0 0 572.4 216.779142\" width=\"572.4pt\" 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>2021-10-10T18:41:53.106628</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 0 216.779142 \n", "L 572.4 216.779142 \n", "L 572.4 0 \n", "L 0 0 \n", "z\n", "\" style=\"fill:#ffffff;\"/>\n", " </g>\n", " <g id=\"axes_1\">\n", " <g clip-path=\"url(#p0e1073f67f)\">\n", " <image height=\"188\" id=\"imagef804d0b0e1\" transform=\"scale(1 -1)translate(0 -188)\" width=\"558\" x=\"7.2\" xlink:href=\"data:image/png;base64,\n", "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\" y=\"-21.579142\"/>\n", " </g>\n", " <g id=\"text_1\">\n", " <!-- Augmented image examples of the STL10 dataset -->\n", " <g style=\"fill:#262626;\" transform=\"translate(135.4425 16.318125)scale(0.12 -0.12)\">\n", " <defs>\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 544 1381 \n", "L 544 3500 \n", "L 1119 3500 \n", "L 1119 1403 \n", "Q 1119 906 1312 657 \n", "Q 1506 409 1894 409 \n", "Q 2359 409 2629 706 \n", "Q 2900 1003 2900 1516 \n", "L 2900 3500 \n", "L 3475 3500 \n", "L 3475 0 \n", "L 2900 0 \n", "L 2900 538 \n", "Q 2691 219 2414 64 \n", "Q 2138 -91 1772 -91 \n", "Q 1169 -91 856 284 \n", "Q 544 659 544 1381 \n", "z\n", "M 1991 3584 \n", "L 1991 3584 \n", "z\n", "\" id=\"DejaVuSans-75\" 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 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 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 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 3500 \n", "L 1159 3500 \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-6e\" 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 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", " <path id=\"DejaVuSans-20\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 603 3500 \n", "L 1178 3500 \n", "L 1178 0 \n", "L 603 0 \n", "L 603 3500 \n", "z\n", "M 603 4863 \n", "L 1178 4863 \n", "L 1178 4134 \n", "L 603 4134 \n", "L 603 4863 \n", "z\n", "\" id=\"DejaVuSans-69\" 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 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 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 -19 4666 \n", "L 3928 4666 \n", "L 3928 4134 \n", "L 2272 4134 \n", "L 2272 0 \n", "L 1638 0 \n", "L 1638 4134 \n", "L -19 4134 \n", "L -19 4666 \n", "z\n", "\" id=\"DejaVuSans-54\" 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", " <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", " </defs>\n", " <use xlink:href=\"#DejaVuSans-41\"/>\n", " <use x=\"68.408203\" xlink:href=\"#DejaVuSans-75\"/>\n", " <use x=\"131.787109\" xlink:href=\"#DejaVuSans-67\"/>\n", " <use x=\"195.263672\" xlink:href=\"#DejaVuSans-6d\"/>\n", " <use x=\"292.675781\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"354.199219\" xlink:href=\"#DejaVuSans-6e\"/>\n", " <use x=\"417.578125\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"456.787109\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"518.310547\" xlink:href=\"#DejaVuSans-64\"/>\n", " <use x=\"581.787109\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"613.574219\" xlink:href=\"#DejaVuSans-69\"/>\n", " <use x=\"641.357422\" xlink:href=\"#DejaVuSans-6d\"/>\n", " <use x=\"738.769531\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"800.048828\" xlink:href=\"#DejaVuSans-67\"/>\n", " <use x=\"863.525391\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"925.048828\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"956.835938\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"1016.609375\" xlink:href=\"#DejaVuSans-78\"/>\n", " <use x=\"1075.789062\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"1137.068359\" xlink:href=\"#DejaVuSans-6d\"/>\n", " <use x=\"1234.480469\" xlink:href=\"#DejaVuSans-70\"/>\n", " <use x=\"1297.957031\" xlink:href=\"#DejaVuSans-6c\"/>\n", " <use x=\"1325.740234\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"1387.263672\" xlink:href=\"#DejaVuSans-73\"/>\n", " <use x=\"1439.363281\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"1471.150391\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"1532.332031\" xlink:href=\"#DejaVuSans-66\"/>\n", " <use x=\"1567.537109\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"1599.324219\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"1638.533203\" xlink:href=\"#DejaVuSans-68\"/>\n", " <use x=\"1701.912109\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"1763.435547\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"1795.222656\" xlink:href=\"#DejaVuSans-53\"/>\n", " <use x=\"1858.699219\" xlink:href=\"#DejaVuSans-54\"/>\n", " <use x=\"1919.783203\" xlink:href=\"#DejaVuSans-4c\"/>\n", " <use x=\"1975.496094\" xlink:href=\"#DejaVuSans-31\"/>\n", " <use x=\"2039.119141\" xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"2102.742188\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"2134.529297\" xlink:href=\"#DejaVuSans-64\"/>\n", " <use x=\"2198.005859\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"2259.285156\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"2298.494141\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"2359.773438\" xlink:href=\"#DejaVuSans-73\"/>\n", " <use x=\"2411.873047\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"2473.396484\" xlink:href=\"#DejaVuSans-74\"/>\n", " </g>\n", " </g>\n", " </g>\n", " </g>\n", " <defs>\n", " <clipPath id=\"p0e1073f67f\">\n", " <rect height=\"187.261017\" width=\"558\" x=\"7.2\" y=\"22.318125\"/>\n", " </clipPath>\n", " </defs>\n", "</svg>\n"], "text/plain": ["<Figure size 720x360 with 1 Axes>"]}, "metadata": {}, "output_type": "display_data"}], "source": ["# Visualize some examples\n", "pl.seed_everything(42)\n", "NUM_IMAGES = 6\n", "imgs = torch.stack([img for idx in range(NUM_IMAGES) for img in unlabeled_data[idx][0]], dim=0)\n", "img_grid = torchvision.utils.make_grid(imgs, nrow=6, normalize=True, pad_value=0.9)\n", "img_grid = img_grid.permute(1, 2, 0)\n", "\n", "plt.figure(figsize=(10, 5))\n", "plt.title(\"Augmented image examples of the STL10 dataset\")\n", "plt.imshow(img_grid)\n", "plt.axis(\"off\")\n", "plt.show()\n", "plt.close()"]}, {"cell_type": "markdown", "id": "d9b44c08", "metadata": {"papermill": {"duration": 0.079471, "end_time": "2021-10-10T16:41:53.515584", "exception": false, "start_time": "2021-10-10T16:41:53.436113", "status": "completed"}, "tags": []}, "source": ["We see the wide variety of our data augmentation, including randomly cropping, grayscaling, gaussian blur, and color distortion.\n", "Thus, it remains a challenging task for the model to match two, independently augmented patches of the same image."]}, {"cell_type": "markdown", "id": "525c3967", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.047654, "end_time": "2021-10-10T16:41:53.615813", "exception": false, "start_time": "2021-10-10T16:41:53.568159", "status": "completed"}, "tags": []}, "source": ["### SimCLR implementation\n", "\n", "Using the data loader pipeline above, we can now implement SimCLR.\n", "At each iteration, we get for every image $x$ two differently augmented versions, which we refer to as $\\tilde{x}_i$ and $\\tilde{x}_j$.\n", "Both of these images are encoded into a one-dimensional feature vector, between which we want to maximize similarity which minimizes it to all other images in the batch.\n", "The encoder network is split into two parts: a base encoder network $f(\\cdot)$, and a projection head $g(\\cdot)$.\n", "The base network is usually a deep CNN as we have seen in e.g. [Tutorial 5](https://uvadlc-notebooks.readthedocs.io/en/latest/tutorial_notebooks/tutorial5/Inception_ResNet_DenseNet.html) before, and is responsible for extracting a representation vector from the augmented data examples.\n", "In our experiments, we will use the common ResNet-18 architecture as $f(\\cdot)$, and refer to the output as $f(\\tilde{x}_i)=h_i$.\n", "The projection head $g(\\cdot)$ maps the representation $h$ into a space where we apply the contrastive loss, i.e., compare similarities between vectors.\n", "It is often chosen to be a small MLP with non-linearities, and for simplicity, we follow the original SimCLR paper setup by defining it as a two-layer MLP with ReLU activation in the hidden layer.\n", "Note that in the follow-up paper, [SimCLRv2](https://arxiv.org/abs/2006.10029), the authors mention that larger/wider MLPs can boost the performance considerably.\n", "This is why we apply an MLP with four times larger hidden dimensions, but deeper MLPs showed to overfit on the given dataset.\n", "The general setup is visualized below (figure credit - [Ting Chen et al. ](https://arxiv.org/abs/2006.10029)):\n", "\n", "<center width=\"100%\"><img src=\"https://github.com/PyTorchLightning/lightning-tutorials/raw/main/course_UvA-DL/13-contrastive-learning/simclr_network_setup.svg\" width=\"350px\"></center>\n", "\n", "After finishing the training with contrastive learning, we will remove the projection head $g(\\cdot)$, and use $f(\\cdot)$ as a pretrained feature extractor.\n", "The representations $z$ that come out of the projection head $g(\\cdot)$ have been shown to perform worse than those of the base network $f(\\cdot)$ when finetuning the network for a new task.\n", "This is likely because the representations $z$ are trained to become invariant to many features like the color that can be important for downstream tasks.\n", "Thus, $g(\\cdot)$ is only needed for the contrastive learning stage.\n", "\n", "Now that the architecture is described, let's take a closer look at how we train the model.\n", "As mentioned before, we want to maximize the similarity between the representations of the two augmented versions of the same image, i.e., $z_i$ and $z_j$ in the figure above, while minimizing it to all other examples in the batch.\n", "SimCLR thereby applies the InfoNCE loss, originally proposed by [Aaron van den Oord et al. ](https://arxiv.org/abs/1807.03748) for contrastive learning.\n", "In short, the InfoNCE loss compares the similarity of $z_i$ and $z_j$ to the similarity of $z_i$ to any other representation in the batch by performing a softmax over the similarity values.\n", "The loss can be formally written as:\n", "$$\n", "\\ell_{i,j}=-\\log \\frac{\\exp(\\text{sim}(z_i,z_j)/\\tau)}{\\sum_{k=1}^{2N}\\mathbb{1}_{[k\\neq i]}\\exp(\\text{sim}(z_i,z_k)/\\tau)}=-\\text{sim}(z_i,z_j)/\\tau+\\log\\left[\\sum_{k=1}^{2N}\\mathbb{1}_{[k\\neq i]}\\exp(\\text{sim}(z_i,z_k)/\\tau)\\right]\n", "$$\n", "The function $\\text{sim}$ is a similarity metric, and the hyperparameter $\\tau$ is called temperature determining how peaked the distribution is.\n", "Since many similarity metrics are bounded, the temperature parameter allows us to balance the influence of many dissimilar image patches versus one similar patch.\n", "The similarity metric that is used in SimCLR is cosine similarity, as defined below:\n", "$$\n", "\\text{sim}(z_i,z_j) = \\frac{z_i^\\top \\cdot z_j}{||z_i||\\cdot||z_j||}\n", "$$\n", "The maximum cosine similarity possible is $1$, while the minimum is $-1$.\n", "In general, we will see that the features of two different images will converge to a cosine similarity around zero since the minimum, $-1$, would require $z_i$ and $z_j$ to be in the exact opposite direction in all feature dimensions, which does not allow for great flexibility.\n", "\n", "Finally, now that we have discussed all details, let's implement SimCLR below as a PyTorch Lightning module:"]}, {"cell_type": "code", "execution_count": 8, "id": "a94c063a", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:41:53.767396Z", "iopub.status.busy": "2021-10-10T16:41:53.764007Z", "iopub.status.idle": "2021-10-10T16:41:53.769425Z", "shell.execute_reply": "2021-10-10T16:41:53.769027Z"}, "lines_to_next_cell": 2, "papermill": {"duration": 0.09737, "end_time": "2021-10-10T16:41:53.769531", "exception": false, "start_time": "2021-10-10T16:41:53.672161", "status": "completed"}, "tags": []}, "outputs": [], "source": ["class SimCLR(pl.LightningModule):\n", " def __init__(self, hidden_dim, lr, temperature, weight_decay, max_epochs=500):\n", " super().__init__()\n", " self.save_hyperparameters()\n", " assert self.hparams.temperature > 0.0, \"The temperature must be a positive float!\"\n", " # Base model f(.)\n", " self.convnet = torchvision.models.resnet18(\n", " pretrained=False, num_classes=4 * hidden_dim\n", " ) # num_classes is the output size of the last linear layer\n", " # The MLP for g(.) consists of Linear->ReLU->Linear\n", " self.convnet.fc = nn.Sequential(\n", " self.convnet.fc, # Linear(ResNet output, 4*hidden_dim)\n", " nn.ReLU(inplace=True),\n", " nn.Linear(4 * hidden_dim, hidden_dim),\n", " )\n", "\n", " def configure_optimizers(self):\n", " optimizer = optim.AdamW(self.parameters(), lr=self.hparams.lr, weight_decay=self.hparams.weight_decay)\n", " lr_scheduler = optim.lr_scheduler.CosineAnnealingLR(\n", " optimizer, T_max=self.hparams.max_epochs, eta_min=self.hparams.lr / 50\n", " )\n", " return [optimizer], [lr_scheduler]\n", "\n", " def info_nce_loss(self, batch, mode=\"train\"):\n", " imgs, _ = batch\n", " imgs = torch.cat(imgs, dim=0)\n", "\n", " # Encode all images\n", " feats = self.convnet(imgs)\n", " # Calculate cosine similarity\n", " cos_sim = F.cosine_similarity(feats[:, None, :], feats[None, :, :], dim=-1)\n", " # Mask out cosine similarity to itself\n", " self_mask = torch.eye(cos_sim.shape[0], dtype=torch.bool, device=cos_sim.device)\n", " cos_sim.masked_fill_(self_mask, -9e15)\n", " # Find positive example -> batch_size//2 away from the original example\n", " pos_mask = self_mask.roll(shifts=cos_sim.shape[0] // 2, dims=0)\n", " # InfoNCE loss\n", " cos_sim = cos_sim / self.hparams.temperature\n", " nll = -cos_sim[pos_mask] + torch.logsumexp(cos_sim, dim=-1)\n", " nll = nll.mean()\n", "\n", " # Logging loss\n", " self.log(mode + \"_loss\", nll)\n", " # Get ranking position of positive example\n", " comb_sim = torch.cat(\n", " [cos_sim[pos_mask][:, None], cos_sim.masked_fill(pos_mask, -9e15)], # First position positive example\n", " dim=-1,\n", " )\n", " sim_argsort = comb_sim.argsort(dim=-1, descending=True).argmin(dim=-1)\n", " # Logging ranking metrics\n", " self.log(mode + \"_acc_top1\", (sim_argsort == 0).float().mean())\n", " self.log(mode + \"_acc_top5\", (sim_argsort < 5).float().mean())\n", " self.log(mode + \"_acc_mean_pos\", 1 + sim_argsort.float().mean())\n", "\n", " return nll\n", "\n", " def training_step(self, batch, batch_idx):\n", " return self.info_nce_loss(batch, mode=\"train\")\n", "\n", " def validation_step(self, batch, batch_idx):\n", " self.info_nce_loss(batch, mode=\"val\")"]}, {"cell_type": "markdown", "id": "5930dd21", "metadata": {"papermill": {"duration": 0.339364, "end_time": "2021-10-10T16:41:54.219681", "exception": false, "start_time": "2021-10-10T16:41:53.880317", "status": "completed"}, "tags": []}, "source": ["Alternatively to performing the validation on the contrastive learning loss as well, we could also take a simple, small downstream task, and track the performance of the base network $f(\\cdot)$ on that.\n", "However, in this tutorial, we will restrict ourselves to the STL10\n", "dataset where we use the task of image classification on STL10 as our\n", "test task."]}, {"cell_type": "markdown", "id": "371aa9b6", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.041653, "end_time": "2021-10-10T16:41:54.360538", "exception": false, "start_time": "2021-10-10T16:41:54.318885", "status": "completed"}, "tags": []}, "source": ["### Training\n", "\n", "Now that we have implemented SimCLR and the data loading pipeline, we are ready to train the model.\n", "We will use the same training function setup as usual.\n", "For saving the best model checkpoint, we track the metric `val_acc_top5`, which describes how often the correct image patch is within the top-5 most similar examples in the batch.\n", "This is usually less noisy than the top-1 metric, making it a better metric to choose the best model from."]}, {"cell_type": "code", "execution_count": 9, "id": "7ae8797a", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:41:54.466376Z", "iopub.status.busy": "2021-10-10T16:41:54.465889Z", "iopub.status.idle": "2021-10-10T16:41:54.467539Z", "shell.execute_reply": "2021-10-10T16:41:54.467915Z"}, "papermill": {"duration": 0.056039, "end_time": "2021-10-10T16:41:54.468066", "exception": false, "start_time": "2021-10-10T16:41:54.412027", "status": "completed"}, "tags": []}, "outputs": [], "source": ["def train_simclr(batch_size, max_epochs=500, **kwargs):\n", " trainer = pl.Trainer(\n", " default_root_dir=os.path.join(CHECKPOINT_PATH, \"SimCLR\"),\n", " gpus=1 if str(device) == \"cuda:0\" else 0,\n", " max_epochs=max_epochs,\n", " callbacks=[\n", " ModelCheckpoint(save_weights_only=True, mode=\"max\", monitor=\"val_acc_top5\"),\n", " LearningRateMonitor(\"epoch\"),\n", " ],\n", " progress_bar_refresh_rate=1,\n", " )\n", " trainer.logger._default_hp_metric = None # Optional logging argument that we don't need\n", "\n", " # Check whether pretrained model exists. If yes, load it and skip training\n", " pretrained_filename = os.path.join(CHECKPOINT_PATH, \"SimCLR.ckpt\")\n", " if os.path.isfile(pretrained_filename):\n", " print(f\"Found pretrained model at {pretrained_filename}, loading...\")\n", " # Automatically loads the model with the saved hyperparameters\n", " model = SimCLR.load_from_checkpoint(pretrained_filename)\n", " else:\n", " train_loader = data.DataLoader(\n", " unlabeled_data,\n", " batch_size=batch_size,\n", " shuffle=True,\n", " drop_last=True,\n", " pin_memory=True,\n", " num_workers=NUM_WORKERS,\n", " )\n", " val_loader = data.DataLoader(\n", " train_data_contrast,\n", " batch_size=batch_size,\n", " shuffle=False,\n", " drop_last=False,\n", " pin_memory=True,\n", " num_workers=NUM_WORKERS,\n", " )\n", " pl.seed_everything(42) # To be reproducable\n", " model = SimCLR(max_epochs=max_epochs, **kwargs)\n", " trainer.fit(model, train_loader, val_loader)\n", " # Load best checkpoint after training\n", " model = SimCLR.load_from_checkpoint(trainer.checkpoint_callback.best_model_path)\n", "\n", " return model"]}, {"cell_type": "markdown", "id": "30619702", "metadata": {"papermill": {"duration": 0.043291, "end_time": "2021-10-10T16:41:54.559443", "exception": false, "start_time": "2021-10-10T16:41:54.516152", "status": "completed"}, "tags": []}, "source": ["A common observation in contrastive learning is that the larger the batch size, the better the models perform.\n", "A larger batch size allows us to compare each image to more negative examples, leading to overall smoother loss gradients.\n", "However, in our case, we experienced that a batch size of 256 was sufficient to get good results."]}, {"cell_type": "code", "execution_count": 10, "id": "204e88a8", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:41:54.726388Z", "iopub.status.busy": "2021-10-10T16:41:54.725918Z", "iopub.status.idle": "2021-10-10T16:41:54.977674Z", "shell.execute_reply": "2021-10-10T16:41:54.977166Z"}, "papermill": {"duration": 0.357848, "end_time": "2021-10-10T16:41:54.977825", "exception": false, "start_time": "2021-10-10T16:41:54.619977", "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/ContrastiveLearning/SimCLR.ckpt, loading...\n"]}], "source": ["simclr_model = train_simclr(\n", " batch_size=256, hidden_dim=128, lr=5e-4, temperature=0.07, weight_decay=1e-4, max_epochs=500\n", ")"]}, {"cell_type": "markdown", "id": "6e791b30", "metadata": {"papermill": {"duration": 0.041235, "end_time": "2021-10-10T16:41:55.168558", "exception": false, "start_time": "2021-10-10T16:41:55.127323", "status": "completed"}, "tags": []}, "source": ["To get an intuition of how training with contrastive learning behaves, we can take a look at the TensorBoard below:"]}, {"cell_type": "code", "execution_count": 11, "id": "4faca6fd", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:41:55.269774Z", "iopub.status.busy": "2021-10-10T16:41:55.269307Z", "iopub.status.idle": "2021-10-10T16:41:55.271319Z", "shell.execute_reply": "2021-10-10T16:41:55.270919Z"}, "papermill": {"duration": 0.045346, "end_time": "2021-10-10T16:41:55.271426", "exception": false, "start_time": "2021-10-10T16:41:55.226080", "status": "completed"}, "tags": []}, "outputs": [], "source": ["# %tensorboard --logdir ../saved_models/tutorial17/tensorboards/SimCLR/"]}, {"cell_type": "markdown", "id": "6defaecc", "metadata": {"papermill": {"duration": 0.040274, "end_time": "2021-10-10T16:41:55.366743", "exception": false, "start_time": "2021-10-10T16:41:55.326469", "status": "completed"}, "tags": []}, "source": ["<center width=\"100%\"> {width=\"1200px\"} </center>\n", "\n", "One thing to note is that contrastive learning benefits a lot from long training.\n", "The shown plot above is from a training that took approx.\n", "1 day on a NVIDIA TitanRTX.\n", "Training the model for even longer might reduce its loss further, but we did not experience any gains from it for the downstream task on image classification.\n", "In general, contrastive learning can also benefit from using larger models, if sufficient unlabeled data is available."]}, {"cell_type": "markdown", "id": "aaab8b66", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.110092, "end_time": "2021-10-10T16:41:55.567176", "exception": false, "start_time": "2021-10-10T16:41:55.457084", "status": "completed"}, "tags": []}, "source": ["## Logistic Regression\n", "\n", "<div class=\"center-wrapper\"><div class=\"video-wrapper\"><iframe src=\"https://www.youtube.com/embed/o3FktysLLd4\" title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen></iframe></div></div>\n", "After we have trained our model via contrastive learning, we can deploy it on downstream tasks and see how well it performs with little data.\n", "A common setup, which also verifies whether the model has learned generalized representations, is to perform Logistic Regression on the features.\n", "In other words, we learn a single, linear layer that maps the representations to a class prediction.\n", "Since the base network $f(\\cdot)$ is not changed during the training process, the model can only perform well if the representations of $h$ describe all features that might be necessary for the task.\n", "Further, we do not have to worry too much about overfitting since we have very few parameters that are trained.\n", "Hence, we might expect that the model can perform well even with very little data.\n", "\n", "First, let's implement a simple Logistic Regression setup for which we assume that the images already have been encoded in their feature vectors.\n", "If very little data is available, it might be beneficial to dynamically encode the images during training so that we can also apply data augmentations.\n", "However, the way we implement it here is much more efficient and can be trained within a few seconds.\n", "Further, using data augmentations did not show any significant gain in this simple setup."]}, {"cell_type": "code", "execution_count": 12, "id": "6745071e", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:41:55.788482Z", "iopub.status.busy": "2021-10-10T16:41:55.788000Z", "iopub.status.idle": "2021-10-10T16:41:55.789951Z", "shell.execute_reply": "2021-10-10T16:41:55.789550Z"}, "papermill": {"duration": 0.117728, "end_time": "2021-10-10T16:41:55.790056", "exception": false, "start_time": "2021-10-10T16:41:55.672328", "status": "completed"}, "tags": []}, "outputs": [], "source": ["class LogisticRegression(pl.LightningModule):\n", " def __init__(self, feature_dim, num_classes, lr, weight_decay, max_epochs=100):\n", " super().__init__()\n", " self.save_hyperparameters()\n", " # Mapping from representation h to classes\n", " self.model = nn.Linear(feature_dim, num_classes)\n", "\n", " def configure_optimizers(self):\n", " optimizer = optim.AdamW(self.parameters(), lr=self.hparams.lr, weight_decay=self.hparams.weight_decay)\n", " lr_scheduler = optim.lr_scheduler.MultiStepLR(\n", " optimizer, milestones=[int(self.hparams.max_epochs * 0.6), int(self.hparams.max_epochs * 0.8)], gamma=0.1\n", " )\n", " return [optimizer], [lr_scheduler]\n", "\n", " def _calculate_loss(self, batch, mode=\"train\"):\n", " feats, labels = batch\n", " preds = self.model(feats)\n", " loss = F.cross_entropy(preds, labels)\n", " acc = (preds.argmax(dim=-1) == labels).float().mean()\n", "\n", " self.log(mode + \"_loss\", loss)\n", " self.log(mode + \"_acc\", 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\")\n", "\n", " def test_step(self, batch, batch_idx):\n", " self._calculate_loss(batch, mode=\"test\")"]}, {"cell_type": "markdown", "id": "55495b0b", "metadata": {"papermill": {"duration": 0.040786, "end_time": "2021-10-10T16:41:56.009838", "exception": false, "start_time": "2021-10-10T16:41:55.969052", "status": "completed"}, "tags": []}, "source": ["The data we use is the training and test set of STL10.\n", "The training contains 500 images per class, while the test set has 800 images per class."]}, {"cell_type": "code", "execution_count": 13, "id": "eeca05e6", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:41:56.197171Z", "iopub.status.busy": "2021-10-10T16:41:56.196690Z", "iopub.status.idle": "2021-10-10T16:42:07.538122Z", "shell.execute_reply": "2021-10-10T16:42:07.537640Z"}, "papermill": {"duration": 11.449982, "end_time": "2021-10-10T16:42:07.538239", "exception": false, "start_time": "2021-10-10T16:41:56.088257", "status": "completed"}, "tags": []}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Files already downloaded and verified\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Files already downloaded and verified\n", "Number of training examples: 5000\n", "Number of test examples: 8000\n"]}], "source": ["img_transforms = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))])\n", "\n", "train_img_data = STL10(root=DATASET_PATH, split=\"train\", download=True, transform=img_transforms)\n", "test_img_data = STL10(root=DATASET_PATH, split=\"test\", download=True, transform=img_transforms)\n", "\n", "print(\"Number of training examples:\", len(train_img_data))\n", "print(\"Number of test examples:\", len(test_img_data))"]}, {"cell_type": "markdown", "id": "88ebb27b", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.066846, "end_time": "2021-10-10T16:42:07.663036", "exception": false, "start_time": "2021-10-10T16:42:07.596190", "status": "completed"}, "tags": []}, "source": ["Next, we implement a small function to encode all images in our datasets.\n", "The output representations are then used as inputs to the Logistic Regression model."]}, {"cell_type": "code", "execution_count": 14, "id": "08b87e56", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:42:07.810979Z", "iopub.status.busy": "2021-10-10T16:42:07.810493Z", "iopub.status.idle": "2021-10-10T16:42:07.812587Z", "shell.execute_reply": "2021-10-10T16:42:07.812116Z"}, "papermill": {"duration": 0.049258, "end_time": "2021-10-10T16:42:07.812757", "exception": false, "start_time": "2021-10-10T16:42:07.763499", "status": "completed"}, "tags": []}, "outputs": [], "source": ["@torch.no_grad()\n", "def prepare_data_features(model, dataset):\n", " # Prepare model\n", " network = deepcopy(model.convnet)\n", " network.fc = nn.Identity() # Removing projection head g(.)\n", " network.eval()\n", " network.to(device)\n", "\n", " # Encode all images\n", " data_loader = data.DataLoader(dataset, batch_size=64, num_workers=NUM_WORKERS, shuffle=False, drop_last=False)\n", " feats, labels = [], []\n", " for batch_imgs, batch_labels in tqdm(data_loader):\n", " batch_imgs = batch_imgs.to(device)\n", " batch_feats = network(batch_imgs)\n", " feats.append(batch_feats.detach().cpu())\n", " labels.append(batch_labels)\n", "\n", " feats = torch.cat(feats, dim=0)\n", " labels = torch.cat(labels, dim=0)\n", "\n", " # Sort images by labels\n", " labels, idxs = labels.sort()\n", " feats = feats[idxs]\n", "\n", " return data.TensorDataset(feats, labels)"]}, {"cell_type": "markdown", "id": "f1e62cc6", "metadata": {"papermill": {"duration": 0.10389, "end_time": "2021-10-10T16:42:08.012147", "exception": false, "start_time": "2021-10-10T16:42:07.908257", "status": "completed"}, "tags": []}, "source": ["Let's apply the function to both training and test set below."]}, {"cell_type": "code", "execution_count": 15, "id": "274643eb", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:42:08.330518Z", "iopub.status.busy": "2021-10-10T16:42:08.330044Z", "iopub.status.idle": "2021-10-10T16:42:14.259714Z", "shell.execute_reply": "2021-10-10T16:42:14.260561Z"}, "papermill": {"duration": 5.994866, "end_time": "2021-10-10T16:42:14.260713", "exception": false, "start_time": "2021-10-10T16:42:08.265847", "status": "completed"}, "tags": []}, "outputs": [{"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "32cad3ea3e3644baaa844883a715a613", "version_major": 2, "version_minor": 0}, "text/plain": [" 0%| | 0/79 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "3329a069de5d4624a9412647f0d80198", "version_major": 2, "version_minor": 0}, "text/plain": [" 0%| | 0/125 [00:00<?, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}], "source": ["train_feats_simclr = prepare_data_features(simclr_model, train_img_data)\n", "test_feats_simclr = prepare_data_features(simclr_model, test_img_data)"]}, {"cell_type": "markdown", "id": "07d9c6d0", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.038742, "end_time": "2021-10-10T16:42:14.339838", "exception": false, "start_time": "2021-10-10T16:42:14.301096", "status": "completed"}, "tags": []}, "source": ["Finally, we can write a training function as usual.\n", "We evaluate the model on the test set every 10 epochs to allow early\n", "stopping, but the low frequency of the validation ensures that we do not\n", "overfit too much on the test set."]}, {"cell_type": "code", "execution_count": 16, "id": "39e736ac", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:42:14.428282Z", "iopub.status.busy": "2021-10-10T16:42:14.427775Z", "iopub.status.idle": "2021-10-10T16:42:14.429787Z", "shell.execute_reply": "2021-10-10T16:42:14.429385Z"}, "lines_to_next_cell": 2, "papermill": {"duration": 0.049818, "end_time": "2021-10-10T16:42:14.429892", "exception": false, "start_time": "2021-10-10T16:42:14.380074", "status": "completed"}, "tags": []}, "outputs": [], "source": ["def train_logreg(batch_size, train_feats_data, test_feats_data, model_suffix, max_epochs=100, **kwargs):\n", " trainer = pl.Trainer(\n", " default_root_dir=os.path.join(CHECKPOINT_PATH, \"LogisticRegression\"),\n", " gpus=1 if str(device) == \"cuda:0\" else 0,\n", " max_epochs=max_epochs,\n", " callbacks=[\n", " ModelCheckpoint(save_weights_only=True, mode=\"max\", monitor=\"val_acc\"),\n", " LearningRateMonitor(\"epoch\"),\n", " ],\n", " progress_bar_refresh_rate=0,\n", " check_val_every_n_epoch=10,\n", " )\n", " trainer.logger._default_hp_metric = None\n", "\n", " # Data loaders\n", " train_loader = data.DataLoader(\n", " train_feats_data, batch_size=batch_size, shuffle=True, drop_last=False, pin_memory=True, num_workers=0\n", " )\n", " test_loader = data.DataLoader(\n", " test_feats_data, batch_size=batch_size, shuffle=False, drop_last=False, pin_memory=True, num_workers=0\n", " )\n", "\n", " # Check whether pretrained model exists. If yes, load it and skip training\n", " pretrained_filename = os.path.join(CHECKPOINT_PATH, f\"LogisticRegression_{model_suffix}.ckpt\")\n", " if os.path.isfile(pretrained_filename):\n", " print(f\"Found pretrained model at {pretrained_filename}, loading...\")\n", " model = LogisticRegression.load_from_checkpoint(pretrained_filename)\n", " else:\n", " pl.seed_everything(42) # To be reproducable\n", " model = LogisticRegression(**kwargs)\n", " trainer.fit(model, train_loader, test_loader)\n", " model = LogisticRegression.load_from_checkpoint(trainer.checkpoint_callback.best_model_path)\n", "\n", " # Test best model on train and validation set\n", " train_result = trainer.test(model, test_dataloaders=train_loader, verbose=False)\n", " test_result = trainer.test(model, test_dataloaders=test_loader, verbose=False)\n", " result = {\"train\": train_result[0][\"test_acc\"], \"test\": test_result[0][\"test_acc\"]}\n", "\n", " return model, result"]}, {"cell_type": "markdown", "id": "9466a2b3", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.038939, "end_time": "2021-10-10T16:42:14.508335", "exception": false, "start_time": "2021-10-10T16:42:14.469396", "status": "completed"}, "tags": []}, "source": ["Despite the training dataset of STL10 already only having 500 labeled images per class, we will perform experiments with even smaller datasets.\n", "Specifically, we train a Logistic Regression model for datasets with only 10, 20, 50, 100, 200, and all 500 examples per class.\n", "This gives us an intuition on how well the representations learned by contrastive learning can be transfered to a image recognition task like this classification.\n", "First, let's define a function to create the intended sub-datasets from the full training set:"]}, {"cell_type": "code", "execution_count": 17, "id": "b3913e4c", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:42:14.591002Z", "iopub.status.busy": "2021-10-10T16:42:14.590531Z", "iopub.status.idle": "2021-10-10T16:42:14.592353Z", "shell.execute_reply": "2021-10-10T16:42:14.592734Z"}, "papermill": {"duration": 0.044896, "end_time": "2021-10-10T16:42:14.592854", "exception": false, "start_time": "2021-10-10T16:42:14.547958", "status": "completed"}, "tags": []}, "outputs": [], "source": ["def get_smaller_dataset(original_dataset, num_imgs_per_label):\n", " new_dataset = data.TensorDataset(\n", " *(t.unflatten(0, (10, 500))[:, :num_imgs_per_label].flatten(0, 1) for t in original_dataset.tensors)\n", " )\n", " return new_dataset"]}, {"cell_type": "markdown", "id": "990bb943", "metadata": {"papermill": {"duration": 0.039252, "end_time": "2021-10-10T16:42:14.671356", "exception": false, "start_time": "2021-10-10T16:42:14.632104", "status": "completed"}, "tags": []}, "source": ["Next, let's run all models.\n", "Despite us training 6 models, this cell could be run within a minute or two without the pretrained models."]}, {"cell_type": "code", "execution_count": 18, "id": "6539fd23", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:42:14.754555Z", "iopub.status.busy": "2021-10-10T16:42:14.754086Z", "iopub.status.idle": "2021-10-10T16:42:16.144060Z", "shell.execute_reply": "2021-10-10T16:42:16.143610Z"}, "papermill": {"duration": 1.433844, "end_time": "2021-10-10T16:42:16.144181", "exception": false, "start_time": "2021-10-10T16:42:14.710337", "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": "stderr", "output_type": "stream", "text": ["/home/AzDevOps_azpcontainer/.local/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py:678: LightningDeprecationWarning: `trainer.test(test_dataloaders)` is deprecated in v1.4 and will be removed in v1.6. Use `trainer.test(dataloaders)` instead.\n", " rank_zero_deprecation(\n", "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1]\n"]}, {"name": "stderr", "output_type": "stream", "text": ["Missing logger folder: saved_models/ContrastiveLearning/LogisticRegression/lightning_logs\n"]}, {"name": "stderr", "output_type": "stream", "text": ["/home/AzDevOps_azpcontainer/.local/lib/python3.9/site-packages/pytorch_lightning/trainer/data_loading.py:376: UserWarning: Your test_dataloader has `shuffle=True`, it is best practice to turn this off for val/test/predict dataloaders.\n", " rank_zero_warn(\n", "/home/AzDevOps_azpcontainer/.local/lib/python3.9/site-packages/pytorch_lightning/trainer/data_loading.py:105: UserWarning: The dataloader, test dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 12 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n", " rank_zero_warn(\n", "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1]\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Found pretrained model at saved_models/ContrastiveLearning/LogisticRegression_10.ckpt, loading...\n"]}, {"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": "stderr", "output_type": "stream", "text": ["LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1]\n"]}, {"name": "stderr", "output_type": "stream", "text": ["LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1]\n"]}, {"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/ContrastiveLearning/LogisticRegression_20.ckpt, loading...\n", "Found pretrained model at saved_models/ContrastiveLearning/LogisticRegression_50.ckpt, loading...\n"]}, {"name": "stderr", "output_type": "stream", "text": ["LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1]\n"]}, {"name": "stderr", "output_type": "stream", "text": ["LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1]\n"]}, {"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": "stderr", "output_type": "stream", "text": ["LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1]\n"]}, {"name": "stderr", "output_type": "stream", "text": ["LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1]\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Found pretrained model at saved_models/ContrastiveLearning/LogisticRegression_100.ckpt, loading...\n"]}, {"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": "stderr", "output_type": "stream", "text": ["LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1]\n"]}, {"name": "stderr", "output_type": "stream", "text": ["LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1]\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Found pretrained model at saved_models/ContrastiveLearning/LogisticRegression_200.ckpt, loading...\n"]}, {"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": "stderr", "output_type": "stream", "text": ["LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1]\n"]}, {"name": "stderr", "output_type": "stream", "text": ["LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1]\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Found pretrained model at saved_models/ContrastiveLearning/LogisticRegression_500.ckpt, loading...\n"]}], "source": ["results = {}\n", "for num_imgs_per_label in [10, 20, 50, 100, 200, 500]:\n", " sub_train_set = get_smaller_dataset(train_feats_simclr, num_imgs_per_label)\n", " _, small_set_results = train_logreg(\n", " batch_size=64,\n", " train_feats_data=sub_train_set,\n", " test_feats_data=test_feats_simclr,\n", " model_suffix=num_imgs_per_label,\n", " feature_dim=train_feats_simclr.tensors[0].shape[1],\n", " num_classes=10,\n", " lr=1e-3,\n", " weight_decay=1e-3,\n", " )\n", " results[num_imgs_per_label] = small_set_results"]}, {"cell_type": "markdown", "id": "ccf2215a", "metadata": {"papermill": {"duration": 0.047056, "end_time": "2021-10-10T16:42:16.238910", "exception": false, "start_time": "2021-10-10T16:42:16.191854", "status": "completed"}, "tags": []}, "source": ["Finally, let's plot the results."]}, {"cell_type": "code", "execution_count": 19, "id": "2d6fa797", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:42:16.356906Z", "iopub.status.busy": "2021-10-10T16:42:16.345293Z", "iopub.status.idle": "2021-10-10T16:42:16.647718Z", "shell.execute_reply": "2021-10-10T16:42:16.647234Z"}, "papermill": {"duration": 0.362514, "end_time": "2021-10-10T16:42:16.647837", "exception": false, "start_time": "2021-10-10T16:42:16.285323", "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=\"284.2375pt\" version=\"1.1\" viewBox=\"0 0 405.804688 284.2375\" width=\"405.804688pt\" 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>2021-10-10T18:42:16.456325</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 0 284.2375 \n", "L 405.804688 284.2375 \n", "L 405.804688 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 63.804688 241.277813 \n", "L 398.604688 241.277813 \n", "L 398.604688 23.837812 \n", "L 63.804688 23.837812 \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(#p1935b151f5)\" d=\"M 79.022869 241.277813 \n", "L 79.022869 23.837812 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_1\">\n", " <!-- 10 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(72.024119 259.136094)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 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", " </defs>\n", " <use xlink:href=\"#DejaVuSans-31\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_2\">\n", " <g id=\"line2d_2\">\n", " <path clip-path=\"url(#p1935b151f5)\" d=\"M 132.951181 241.277813 \n", "L 132.951181 23.837812 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_2\">\n", " <!-- 20 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(125.952431 259.136094)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", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_3\">\n", " <g id=\"line2d_3\">\n", " <path clip-path=\"url(#p1935b151f5)\" d=\"M 204.240532 241.277813 \n", "L 204.240532 23.837812 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_3\">\n", " <!-- 50 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(197.241782 259.136094)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-35\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_4\">\n", " <g id=\"line2d_4\">\n", " <path clip-path=\"url(#p1935b151f5)\" d=\"M 258.168843 241.277813 \n", "L 258.168843 23.837812 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_4\">\n", " <!-- 100 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(247.670718 259.136094)scale(0.11 -0.11)\">\n", " <use xlink:href=\"#DejaVuSans-31\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"127.246094\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_5\">\n", " <g id=\"line2d_5\">\n", " <path clip-path=\"url(#p1935b151f5)\" d=\"M 312.097155 241.277813 \n", "L 312.097155 23.837812 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_5\">\n", " <!-- 200 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(301.59903 259.136094)scale(0.11 -0.11)\">\n", " <use xlink:href=\"#DejaVuSans-32\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"127.246094\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"xtick_6\">\n", " <g id=\"line2d_6\">\n", " <path clip-path=\"url(#p1935b151f5)\" d=\"M 383.386506 241.277813 \n", "L 383.386506 23.837812 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_6\">\n", " <!-- 500 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(372.888381 259.136094)scale(0.11 -0.11)\">\n", " <use xlink:href=\"#DejaVuSans-35\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"127.246094\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"text_7\">\n", " <!-- Number of images per class -->\n", " <g style=\"fill:#262626;\" transform=\"translate(147.014375 274.541875)scale(0.12 -0.12)\">\n", " <defs>\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 544 1381 \n", "L 544 3500 \n", "L 1119 3500 \n", "L 1119 1403 \n", "Q 1119 906 1312 657 \n", "Q 1506 409 1894 409 \n", "Q 2359 409 2629 706 \n", "Q 2900 1003 2900 1516 \n", "L 2900 3500 \n", "L 3475 3500 \n", "L 3475 0 \n", "L 2900 0 \n", "L 2900 538 \n", "Q 2691 219 2414 64 \n", "Q 2138 -91 1772 -91 \n", "Q 1169 -91 856 284 \n", "Q 544 659 544 1381 \n", "z\n", "M 1991 3584 \n", "L 1991 3584 \n", "z\n", "\" id=\"DejaVuSans-75\" 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 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", "M 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", "L 1159 0 \n", "L 581 0 \n", "L 581 4863 \n", "L 1159 4863 \n", "L 1159 2969 \n", "z\n", "\" id=\"DejaVuSans-62\" 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 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 id=\"DejaVuSans-20\" 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 603 3500 \n", "L 1178 3500 \n", "L 1178 0 \n", "L 603 0 \n", "L 603 3500 \n", "z\n", "M 603 4863 \n", "L 1178 4863 \n", "L 1178 4134 \n", "L 603 4134 \n", "L 603 4863 \n", "z\n", "\" id=\"DejaVuSans-69\" 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 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 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 3122 3366 \n", "L 3122 2828 \n", "Q 2878 2963 2633 3030 \n", "Q 2388 3097 2138 3097 \n", "Q 1578 3097 1268 2742 \n", "Q 959 2388 959 1747 \n", "Q 959 1106 1268 751 \n", "Q 1578 397 2138 397 \n", "Q 2388 397 2633 464 \n", "Q 2878 531 3122 666 \n", "L 3122 134 \n", "Q 2881 22 2623 -34 \n", "Q 2366 -91 2075 -91 \n", "Q 1284 -91 818 406 \n", "Q 353 903 353 1747 \n", "Q 353 2603 823 3093 \n", "Q 1294 3584 2113 3584 \n", "Q 2378 3584 2631 3529 \n", "Q 2884 3475 3122 3366 \n", "z\n", "\" id=\"DejaVuSans-63\" 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", " </defs>\n", " <use xlink:href=\"#DejaVuSans-4e\"/>\n", " <use x=\"74.804688\" xlink:href=\"#DejaVuSans-75\"/>\n", " <use x=\"138.183594\" xlink:href=\"#DejaVuSans-6d\"/>\n", " <use x=\"235.595703\" xlink:href=\"#DejaVuSans-62\"/>\n", " <use x=\"299.072266\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"360.595703\" xlink:href=\"#DejaVuSans-72\"/>\n", " <use x=\"401.708984\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"433.496094\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"494.677734\" xlink:href=\"#DejaVuSans-66\"/>\n", " <use x=\"529.882812\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"561.669922\" xlink:href=\"#DejaVuSans-69\"/>\n", " <use x=\"589.453125\" xlink:href=\"#DejaVuSans-6d\"/>\n", " <use x=\"686.865234\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"748.144531\" xlink:href=\"#DejaVuSans-67\"/>\n", " <use x=\"811.621094\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"873.144531\" xlink:href=\"#DejaVuSans-73\"/>\n", " <use x=\"925.244141\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"957.03125\" xlink:href=\"#DejaVuSans-70\"/>\n", " <use x=\"1020.507812\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"1082.03125\" xlink:href=\"#DejaVuSans-72\"/>\n", " <use x=\"1123.144531\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"1154.931641\" xlink:href=\"#DejaVuSans-63\"/>\n", " <use x=\"1209.912109\" xlink:href=\"#DejaVuSans-6c\"/>\n", " <use x=\"1237.695312\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"1298.974609\" xlink:href=\"#DejaVuSans-73\"/>\n", " <use x=\"1351.074219\" xlink:href=\"#DejaVuSans-73\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"matplotlib.axis_2\">\n", " <g id=\"ytick_1\">\n", " <g id=\"line2d_7\">\n", " <path clip-path=\"url(#p1935b151f5)\" d=\"M 63.804688 234.459871 \n", "L 398.604688 234.459871 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_8\">\n", " <!-- 0.625 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 238.639011)scale(0.11 -0.11)\">\n", " <defs>\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", " <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-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-32\"/>\n", " <use x=\"222.65625\" xlink:href=\"#DejaVuSans-35\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_2\">\n", " <g id=\"line2d_8\">\n", " <path clip-path=\"url(#p1935b151f5)\" d=\"M 63.804688 207.801383 \n", "L 398.604688 207.801383 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_9\">\n", " <!-- 0.650 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 211.980523)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", " <use x=\"222.65625\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_3\">\n", " <g id=\"line2d_9\">\n", " <path clip-path=\"url(#p1935b151f5)\" d=\"M 63.804688 181.142894 \n", "L 398.604688 181.142894 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_10\">\n", " <!-- 0.675 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 185.322035)scale(0.11 -0.11)\">\n", " <defs>\n", " <path d=\"M 525 4666 \n", "L 3525 4666 \n", "L 3525 4397 \n", "L 1831 0 \n", "L 1172 0 \n", "L 2766 4134 \n", "L 525 4134 \n", "L 525 4666 \n", "z\n", "\" id=\"DejaVuSans-37\" 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-36\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-37\"/>\n", " <use x=\"222.65625\" xlink:href=\"#DejaVuSans-35\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_4\">\n", " <g id=\"line2d_10\">\n", " <path clip-path=\"url(#p1935b151f5)\" d=\"M 63.804688 154.484406 \n", "L 398.604688 154.484406 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_11\">\n", " <!-- 0.700 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 158.663547)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-37\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"222.65625\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_5\">\n", " <g id=\"line2d_11\">\n", " <path clip-path=\"url(#p1935b151f5)\" d=\"M 63.804688 127.825918 \n", "L 398.604688 127.825918 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_12\">\n", " <!-- 0.725 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 132.005058)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-37\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-32\"/>\n", " <use x=\"222.65625\" xlink:href=\"#DejaVuSans-35\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_6\">\n", " <g id=\"line2d_12\">\n", " <path clip-path=\"url(#p1935b151f5)\" d=\"M 63.804688 101.16743 \n", "L 398.604688 101.16743 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_13\">\n", " <!-- 0.750 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 105.34657)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-37\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-35\"/>\n", " <use x=\"222.65625\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_7\">\n", " <g id=\"line2d_13\">\n", " <path clip-path=\"url(#p1935b151f5)\" d=\"M 63.804688 74.508941 \n", "L 398.604688 74.508941 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_14\">\n", " <!-- 0.775 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 78.688082)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-37\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-37\"/>\n", " <use x=\"222.65625\" xlink:href=\"#DejaVuSans-35\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"ytick_8\">\n", " <g id=\"line2d_14\">\n", " <path clip-path=\"url(#p1935b151f5)\" d=\"M 63.804688 47.850453 \n", "L 398.604688 47.850453 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:round;\"/>\n", " </g>\n", " <g id=\"text_15\">\n", " <!-- 0.800 -->\n", " <g style=\"fill:#262626;\" transform=\"translate(22.81375 52.029594)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-30\"/>\n", " <use x=\"63.623047\" xlink:href=\"#DejaVuSans-2e\"/>\n", " <use x=\"95.410156\" xlink:href=\"#DejaVuSans-38\"/>\n", " <use x=\"159.033203\" xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"222.65625\" xlink:href=\"#DejaVuSans-30\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"text_16\">\n", " <!-- Test accuracy -->\n", " <g style=\"fill:#262626;\" transform=\"translate(16.318125 173.350313)rotate(-90)scale(0.12 -0.12)\">\n", " <defs>\n", " <path d=\"M -19 4666 \n", "L 3928 4666 \n", "L 3928 4134 \n", "L 2272 4134 \n", "L 2272 0 \n", "L 1638 0 \n", "L 1638 4134 \n", "L -19 4134 \n", "L -19 4666 \n", "z\n", "\" id=\"DejaVuSans-54\" 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 2059 -325 \n", "Q 1816 -950 1584 -1140 \n", "Q 1353 -1331 966 -1331 \n", "L 506 -1331 \n", "L 506 -850 \n", "L 844 -850 \n", "Q 1081 -850 1212 -737 \n", "Q 1344 -625 1503 -206 \n", "L 1606 56 \n", "L 191 3500 \n", "L 800 3500 \n", "L 1894 763 \n", "L 2988 3500 \n", "L 3597 3500 \n", "L 2059 -325 \n", "z\n", "\" id=\"DejaVuSans-79\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-54\"/>\n", " <use x=\"44.083984\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"105.607422\" xlink:href=\"#DejaVuSans-73\"/>\n", " <use x=\"157.707031\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"196.916016\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"228.703125\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"289.982422\" xlink:href=\"#DejaVuSans-63\"/>\n", " <use x=\"344.962891\" xlink:href=\"#DejaVuSans-63\"/>\n", " <use x=\"399.943359\" xlink:href=\"#DejaVuSans-75\"/>\n", " <use x=\"463.322266\" xlink:href=\"#DejaVuSans-72\"/>\n", " <use x=\"504.435547\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"565.714844\" xlink:href=\"#DejaVuSans-63\"/>\n", " <use x=\"620.695312\" xlink:href=\"#DejaVuSans-79\"/>\n", " </g>\n", " </g>\n", " </g>\n", " <g id=\"line2d_15\">\n", " <path clip-path=\"url(#p1935b151f5)\" d=\"M 79.022869 231.394176 \n", "L 132.951181 169.413171 \n", "L 204.240532 107.1656 \n", "L 258.168843 77.707944 \n", "L 312.097155 57.847412 \n", "L 383.386506 33.721449 \n", "\" style=\"fill:none;stroke:#000000;stroke-dasharray:5.55,2.4;stroke-dashoffset:0;stroke-width:1.5;\"/>\n", " <defs>\n", " <path d=\"M 0 -8 \n", "L -1.796112 -2.472136 \n", "L -7.608452 -2.472136 \n", "L -2.90617 0.944272 \n", "L -4.702282 6.472136 \n", "L -0 3.055728 \n", "L 4.702282 6.472136 \n", "L 2.90617 0.944272 \n", "L 7.608452 -2.472136 \n", "L 1.796112 -2.472136 \n", "z\n", "\" id=\"m4ab42bb68c\" style=\"stroke:#000000;stroke-linejoin:bevel;\"/>\n", " </defs>\n", " <g clip-path=\"url(#p1935b151f5)\">\n", " <use style=\"fill:#ccb974;stroke:#000000;stroke-linejoin:bevel;\" x=\"79.022869\" xlink:href=\"#m4ab42bb68c\" y=\"231.394176\"/>\n", " <use style=\"fill:#ccb974;stroke:#000000;stroke-linejoin:bevel;\" x=\"132.951181\" xlink:href=\"#m4ab42bb68c\" y=\"169.413171\"/>\n", " <use style=\"fill:#ccb974;stroke:#000000;stroke-linejoin:bevel;\" x=\"204.240532\" xlink:href=\"#m4ab42bb68c\" y=\"107.1656\"/>\n", " <use style=\"fill:#ccb974;stroke:#000000;stroke-linejoin:bevel;\" x=\"258.168843\" xlink:href=\"#m4ab42bb68c\" y=\"77.707944\"/>\n", " <use style=\"fill:#ccb974;stroke:#000000;stroke-linejoin:bevel;\" x=\"312.097155\" xlink:href=\"#m4ab42bb68c\" y=\"57.847412\"/>\n", " <use style=\"fill:#ccb974;stroke:#000000;stroke-linejoin:bevel;\" x=\"383.386506\" xlink:href=\"#m4ab42bb68c\" y=\"33.721449\"/>\n", " </g>\n", " </g>\n", " <g id=\"patch_3\">\n", " <path d=\"M 63.804688 241.277813 \n", "L 63.804688 23.837813 \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 398.604688 241.277813 \n", "L 398.604688 23.837813 \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 63.804688 241.277813 \n", "L 398.604688 241.277813 \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 63.804688 23.837812 \n", "L 398.604688 23.837812 \n", "\" style=\"fill:none;stroke:#ffffff;stroke-linecap:square;stroke-linejoin:miter;stroke-width:1.25;\"/>\n", " </g>\n", " <g id=\"text_17\">\n", " <!-- STL10 classification over dataset size -->\n", " <g style=\"fill:#262626;\" transform=\"translate(99.852969 17.837812)scale(0.14 -0.14)\">\n", " <defs>\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 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", " <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 3500 \n", "L 1159 3500 \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-6e\" transform=\"scale(0.015625)\"/>\n", " <path d=\"M 191 3500 \n", "L 800 3500 \n", "L 1894 563 \n", "L 2988 3500 \n", "L 3597 3500 \n", "L 2284 0 \n", "L 1503 0 \n", "L 191 3500 \n", "z\n", "\" id=\"DejaVuSans-76\" 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", " <path d=\"M 353 3500 \n", "L 3084 3500 \n", "L 3084 2975 \n", "L 922 459 \n", "L 3084 459 \n", "L 3084 0 \n", "L 275 0 \n", "L 275 525 \n", "L 2438 3041 \n", "L 353 3041 \n", "L 353 3500 \n", "z\n", "\" id=\"DejaVuSans-7a\" transform=\"scale(0.015625)\"/>\n", " </defs>\n", " <use xlink:href=\"#DejaVuSans-53\"/>\n", " <use x=\"63.476562\" xlink:href=\"#DejaVuSans-54\"/>\n", " <use x=\"124.560547\" xlink:href=\"#DejaVuSans-4c\"/>\n", " <use x=\"180.273438\" xlink:href=\"#DejaVuSans-31\"/>\n", " <use x=\"243.896484\" xlink:href=\"#DejaVuSans-30\"/>\n", " <use x=\"307.519531\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"339.306641\" xlink:href=\"#DejaVuSans-63\"/>\n", " <use x=\"394.287109\" xlink:href=\"#DejaVuSans-6c\"/>\n", " <use x=\"422.070312\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"483.349609\" xlink:href=\"#DejaVuSans-73\"/>\n", " <use x=\"535.449219\" xlink:href=\"#DejaVuSans-73\"/>\n", " <use x=\"587.548828\" xlink:href=\"#DejaVuSans-69\"/>\n", " <use x=\"615.332031\" xlink:href=\"#DejaVuSans-66\"/>\n", " <use x=\"650.537109\" xlink:href=\"#DejaVuSans-69\"/>\n", " <use x=\"678.320312\" xlink:href=\"#DejaVuSans-63\"/>\n", " <use x=\"733.300781\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"794.580078\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"833.789062\" xlink:href=\"#DejaVuSans-69\"/>\n", " <use x=\"861.572266\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"922.753906\" xlink:href=\"#DejaVuSans-6e\"/>\n", " <use x=\"986.132812\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"1017.919922\" xlink:href=\"#DejaVuSans-6f\"/>\n", " <use x=\"1079.101562\" xlink:href=\"#DejaVuSans-76\"/>\n", " <use x=\"1138.28125\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"1199.804688\" xlink:href=\"#DejaVuSans-72\"/>\n", " <use x=\"1240.917969\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"1272.705078\" xlink:href=\"#DejaVuSans-64\"/>\n", " <use x=\"1336.181641\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"1397.460938\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"1436.669922\" xlink:href=\"#DejaVuSans-61\"/>\n", " <use x=\"1497.949219\" xlink:href=\"#DejaVuSans-73\"/>\n", " <use x=\"1550.048828\" xlink:href=\"#DejaVuSans-65\"/>\n", " <use x=\"1611.572266\" xlink:href=\"#DejaVuSans-74\"/>\n", " <use x=\"1650.78125\" xlink:href=\"#DejaVuSans-20\"/>\n", " <use x=\"1682.568359\" xlink:href=\"#DejaVuSans-73\"/>\n", " <use x=\"1734.667969\" xlink:href=\"#DejaVuSans-69\"/>\n", " <use x=\"1762.451172\" xlink:href=\"#DejaVuSans-7a\"/>\n", " <use x=\"1814.941406\" xlink:href=\"#DejaVuSans-65\"/>\n", " </g>\n", " </g>\n", " </g>\n", " </g>\n", " <defs>\n", " <clipPath id=\"p1935b151f5\">\n", " <rect height=\"217.44\" width=\"334.8\" x=\"63.804688\" y=\"23.837812\"/>\n", " </clipPath>\n", " </defs>\n", "</svg>\n"], "text/plain": ["<Figure size 432x288 with 1 Axes>"]}, "metadata": {}, "output_type": "display_data"}, {"name": "stdout", "output_type": "stream", "text": ["Test accuracy for 10 images per label: 62.79%\n", "Test accuracy for 20 images per label: 68.60%\n", "Test accuracy for 50 images per label: 74.44%\n", "Test accuracy for 100 images per label: 77.20%\n", "Test accuracy for 200 images per label: 79.06%\n", "Test accuracy for 500 images per label: 81.33%\n"]}], "source": ["dataset_sizes = sorted(k for k in results)\n", "test_scores = [results[k][\"test\"] for k in dataset_sizes]\n", "\n", "fig = plt.figure(figsize=(6, 4))\n", "plt.plot(\n", " dataset_sizes,\n", " test_scores,\n", " \"--\",\n", " color=\"#000\",\n", " marker=\"*\",\n", " markeredgecolor=\"#000\",\n", " markerfacecolor=\"y\",\n", " markersize=16,\n", ")\n", "plt.xscale(\"log\")\n", "plt.xticks(dataset_sizes, labels=dataset_sizes)\n", "plt.title(\"STL10 classification over dataset size\", fontsize=14)\n", "plt.xlabel(\"Number of images per class\")\n", "plt.ylabel(\"Test accuracy\")\n", "plt.minorticks_off()\n", "plt.show()\n", "\n", "for k, score in zip(dataset_sizes, test_scores):\n", " print(f\"Test accuracy for {k:3d} images per label: {100*score:4.2f}%\")"]}, {"cell_type": "markdown", "id": "e6cb0f66", "metadata": {"papermill": {"duration": 0.049197, "end_time": "2021-10-10T16:42:16.746998", "exception": false, "start_time": "2021-10-10T16:42:16.697801", "status": "completed"}, "tags": []}, "source": ["As one would expect, the classification performance improves the more data we have.\n", "However, with only 10 images per class, we can already classify more than 60% of the images correctly.\n", "This is quite impressive, considering that the images are also higher dimensional than e.g. CIFAR10.\n", "With the full dataset, we achieve an accuracy of 81%.\n", "The increase between 50 to 500 images per class might suggest a linear increase in performance with an exponentially larger dataset.\n", "However, with even more data, we could also finetune $f(\\cdot)$ in the training process, allowing for the representations to adapt more to the specific classification task given.\n", "\n", "To set the results above into perspective, we will train the base\n", "network, a ResNet-18, on the classification task from scratch."]}, {"cell_type": "markdown", "id": "237fe863", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.048695, "end_time": "2021-10-10T16:42:16.844984", "exception": false, "start_time": "2021-10-10T16:42:16.796289", "status": "completed"}, "tags": []}, "source": ["## Baseline\n", "\n", "As a baseline to our results above, we will train a standard ResNet-18 with random initialization on the labeled training set of STL10.\n", "The results will give us an indication of the advantages that contrastive learning on unlabeled data has compared to using only supervised training.\n", "The implementation of the model is straightforward since the ResNet\n", "architecture is provided in the torchvision library."]}, {"cell_type": "code", "execution_count": 20, "id": "201725a2", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:42:16.952607Z", "iopub.status.busy": "2021-10-10T16:42:16.952127Z", "iopub.status.idle": "2021-10-10T16:42:16.954345Z", "shell.execute_reply": "2021-10-10T16:42:16.953881Z"}, "papermill": {"duration": 0.059107, "end_time": "2021-10-10T16:42:16.954448", "exception": false, "start_time": "2021-10-10T16:42:16.895341", "status": "completed"}, "tags": []}, "outputs": [], "source": ["class ResNet(pl.LightningModule):\n", " def __init__(self, num_classes, lr, weight_decay, max_epochs=100):\n", " super().__init__()\n", " self.save_hyperparameters()\n", " self.model = torchvision.models.resnet18(pretrained=False, num_classes=num_classes)\n", "\n", " def configure_optimizers(self):\n", " optimizer = optim.AdamW(self.parameters(), lr=self.hparams.lr, weight_decay=self.hparams.weight_decay)\n", " lr_scheduler = optim.lr_scheduler.MultiStepLR(\n", " optimizer, milestones=[int(self.hparams.max_epochs * 0.7), int(self.hparams.max_epochs * 0.9)], gamma=0.1\n", " )\n", " return [optimizer], [lr_scheduler]\n", "\n", " def _calculate_loss(self, batch, mode=\"train\"):\n", " imgs, labels = batch\n", " preds = self.model(imgs)\n", " loss = F.cross_entropy(preds, labels)\n", " acc = (preds.argmax(dim=-1) == labels).float().mean()\n", "\n", " self.log(mode + \"_loss\", loss)\n", " self.log(mode + \"_acc\", 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\")\n", "\n", " def test_step(self, batch, batch_idx):\n", " self._calculate_loss(batch, mode=\"test\")"]}, {"cell_type": "markdown", "id": "e6fe14f2", "metadata": {"papermill": {"duration": 0.049585, "end_time": "2021-10-10T16:42:17.052720", "exception": false, "start_time": "2021-10-10T16:42:17.003135", "status": "completed"}, "tags": []}, "source": ["It is clear that the ResNet easily overfits on the training data since its parameter count is more than 1000 times larger than the dataset size.\n", "To make the comparison to the contrastive learning models fair, we apply data augmentations similar to the ones we used before: horizontal flip, crop-and-resize, grayscale, and gaussian blur.\n", "Color distortions as before are not used because the color distribution of an image showed to be an important feature for the classification.\n", "Hence, we observed no noticeable performance gains when adding color distortions to the set of augmentations.\n", "Similarly, we restrict the resizing operation before cropping to the max.\n", "125% of its original resolution, instead of 1250% as done in SimCLR.\n", "This is because, for classification, the model needs to recognize the full object, while in contrastive learning, we only want to check whether two patches belong to the same image/object.\n", "Hence, the chosen augmentations below are overall weaker than in the contrastive learning case."]}, {"cell_type": "code", "execution_count": 21, "id": "3c7c2020", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:42:17.163394Z", "iopub.status.busy": "2021-10-10T16:42:17.162926Z", "iopub.status.idle": "2021-10-10T16:42:22.652111Z", "shell.execute_reply": "2021-10-10T16:42:22.652505Z"}, "papermill": {"duration": 5.551414, "end_time": "2021-10-10T16:42:22.652657", "exception": false, "start_time": "2021-10-10T16:42:17.101243", "status": "completed"}, "tags": []}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Files already downloaded and verified\n"]}], "source": ["train_transforms = transforms.Compose(\n", " [\n", " transforms.RandomHorizontalFlip(),\n", " transforms.RandomResizedCrop(size=96, scale=(0.8, 1.0)),\n", " transforms.RandomGrayscale(p=0.2),\n", " transforms.GaussianBlur(kernel_size=9, sigma=(0.1, 0.5)),\n", " transforms.ToTensor(),\n", " transforms.Normalize((0.5,), (0.5,)),\n", " ]\n", ")\n", "\n", "train_img_aug_data = STL10(root=DATASET_PATH, split=\"train\", download=True, transform=train_transforms)"]}, {"cell_type": "markdown", "id": "318c1f64", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.053189, "end_time": "2021-10-10T16:42:22.755918", "exception": false, "start_time": "2021-10-10T16:42:22.702729", "status": "completed"}, "tags": []}, "source": ["The training function for the ResNet is almost identical to the Logistic Regression setup.\n", "Note that we allow the ResNet to perform validation every 2 epochs to\n", "also check whether the model overfits strongly in the first iterations\n", "or not."]}, {"cell_type": "code", "execution_count": 22, "id": "9f4db9de", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:42:22.863515Z", "iopub.status.busy": "2021-10-10T16:42:22.862996Z", "iopub.status.idle": "2021-10-10T16:42:22.865112Z", "shell.execute_reply": "2021-10-10T16:42:22.864714Z"}, "papermill": {"duration": 0.059991, "end_time": "2021-10-10T16:42:22.865213", "exception": false, "start_time": "2021-10-10T16:42:22.805222", "status": "completed"}, "tags": []}, "outputs": [], "source": ["def train_resnet(batch_size, max_epochs=100, **kwargs):\n", " trainer = pl.Trainer(\n", " default_root_dir=os.path.join(CHECKPOINT_PATH, \"ResNet\"),\n", " gpus=1 if str(device) == \"cuda:0\" else 0,\n", " max_epochs=max_epochs,\n", " callbacks=[\n", " ModelCheckpoint(save_weights_only=True, mode=\"max\", monitor=\"val_acc\"),\n", " LearningRateMonitor(\"epoch\"),\n", " ],\n", " progress_bar_refresh_rate=1,\n", " check_val_every_n_epoch=2,\n", " )\n", " trainer.logger._default_hp_metric = None\n", "\n", " # Data loaders\n", " train_loader = data.DataLoader(\n", " train_img_aug_data,\n", " batch_size=batch_size,\n", " shuffle=True,\n", " drop_last=True,\n", " pin_memory=True,\n", " num_workers=NUM_WORKERS,\n", " )\n", " test_loader = data.DataLoader(\n", " test_img_data, batch_size=batch_size, shuffle=False, drop_last=False, pin_memory=True, num_workers=NUM_WORKERS\n", " )\n", "\n", " # Check whether pretrained model exists. If yes, load it and skip training\n", " pretrained_filename = os.path.join(CHECKPOINT_PATH, \"ResNet.ckpt\")\n", " if os.path.isfile(pretrained_filename):\n", " print(\"Found pretrained model at %s, loading...\" % pretrained_filename)\n", " model = ResNet.load_from_checkpoint(pretrained_filename)\n", " else:\n", " pl.seed_everything(42) # To be reproducable\n", " model = ResNet(**kwargs)\n", " trainer.fit(model, train_loader, test_loader)\n", " model = ResNet.load_from_checkpoint(trainer.checkpoint_callback.best_model_path)\n", "\n", " # Test best model on validation set\n", " train_result = trainer.test(model, test_dataloaders=train_loader, verbose=False)\n", " val_result = trainer.test(model, test_dataloaders=test_loader, verbose=False)\n", " result = {\"train\": train_result[0][\"test_acc\"], \"test\": val_result[0][\"test_acc\"]}\n", "\n", " return model, result"]}, {"cell_type": "markdown", "id": "f3781014", "metadata": {"papermill": {"duration": 0.049896, "end_time": "2021-10-10T16:42:22.965127", "exception": false, "start_time": "2021-10-10T16:42:22.915231", "status": "completed"}, "tags": []}, "source": ["Finally, let's train the model and check its results:"]}, {"cell_type": "code", "execution_count": 23, "id": "4f4caab0", "metadata": {"execution": {"iopub.execute_input": "2021-10-10T16:42:23.068310Z", "iopub.status.busy": "2021-10-10T16:42:23.066889Z", "iopub.status.idle": "2021-10-10T16:42:27.618125Z", "shell.execute_reply": "2021-10-10T16:42:27.618532Z"}, "papermill": {"duration": 4.604524, "end_time": "2021-10-10T16:42:27.618678", "exception": false, "start_time": "2021-10-10T16:42:23.014154", "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/ContrastiveLearning/ResNet.ckpt, loading...\n"]}, {"name": "stderr", "output_type": "stream", "text": ["/home/AzDevOps_azpcontainer/.local/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py:678: LightningDeprecationWarning: `trainer.test(test_dataloaders)` is deprecated in v1.4 and will be removed in v1.6. Use `trainer.test(dataloaders)` instead.\n", " rank_zero_deprecation(\n", "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1]\n"]}, {"name": "stderr", "output_type": "stream", "text": ["Missing logger folder: saved_models/ContrastiveLearning/ResNet/lightning_logs\n"]}, {"name": "stderr", "output_type": "stream", "text": ["/home/AzDevOps_azpcontainer/.local/lib/python3.9/site-packages/pytorch_lightning/trainer/data_loading.py:376: UserWarning: Your test_dataloader has `shuffle=True`, it is best practice to turn this off for val/test/predict dataloaders.\n", " rank_zero_warn(\n"]}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "0f6b628c8d4d45f9876bc31bc99904ed", "version_major": 2, "version_minor": 0}, "text/plain": ["Testing: 0it [00:00, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"name": "stderr", "output_type": "stream", "text": ["LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1]\n"]}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "d901ede9b3054a479a22fda21e763fea", "version_major": 2, "version_minor": 0}, "text/plain": ["Testing: 0it [00:00, ?it/s]"]}, "metadata": {}, "output_type": "display_data"}, {"name": "stdout", "output_type": "stream", "text": ["Accuracy on training set: 99.76%\n", "Accuracy on test set: 73.31%\n"]}], "source": ["resnet_model, resnet_result = train_resnet(batch_size=64, num_classes=10, lr=1e-3, weight_decay=2e-4, max_epochs=100)\n", "print(f\"Accuracy on training set: {100*resnet_result['train']:4.2f}%\")\n", "print(f\"Accuracy on test set: {100*resnet_result['test']:4.2f}%\")"]}, {"cell_type": "markdown", "id": "a98707ed", "metadata": {"papermill": {"duration": 0.05204, "end_time": "2021-10-10T16:42:27.724471", "exception": false, "start_time": "2021-10-10T16:42:27.672431", "status": "completed"}, "tags": []}, "source": ["The ResNet trained from scratch achieves 73.31% on the test set.\n", "This is almost 8% less than the contrastive learning model, and even slightly less than SimCLR achieves with 1/10 of the data.\n", "This shows that self-supervised, contrastive learning provides\n", "considerable performance gains by leveraging large amounts of unlabeled\n", "data when little labeled data is available."]}, {"cell_type": "markdown", "id": "333d9e8c", "metadata": {"papermill": {"duration": 0.051935, "end_time": "2021-10-10T16:42:27.828975", "exception": false, "start_time": "2021-10-10T16:42:27.777040", "status": "completed"}, "tags": []}, "source": ["## Conclusion\n", "\n", "In this tutorial, we have discussed self-supervised contrastive learning and implemented SimCLR as an example method.\n", "We have applied it to the STL10 dataset and showed that it can learn generalizable representations that we can use to train simple classification models.\n", "With 500 images per label, it achieved an 8% higher accuracy than a similar model solely trained from supervision and performs on par with it when only using a tenth of the labeled data.\n", "Our experimental results are limited to a single dataset, but recent works such as [Ting Chen et al. ](https://arxiv.org/abs/2006.10029) showed similar trends for larger datasets like ImageNet.\n", "Besides the discussed hyperparameters, the size of the model seems to be important in contrastive learning as well.\n", "If a lot of unlabeled data is available, larger models can achieve much stronger results and come close to their supervised baselines.\n", "Further, there are also approaches for combining contrastive and supervised learning, leading to performance gains beyond supervision (see [Khosla et al.](https://arxiv.org/abs/2004.11362)).\n", "Moreover, contrastive learning is not the only approach to self-supervised learning that has come up in the last two years and showed great results.\n", "Other methods include distillation-based methods like [BYOL](https://arxiv.org/abs/2006.07733) and redundancy reduction techniques like [Barlow Twins](https://arxiv.org/abs/2103.03230).\n", "There is a lot more to explore in the self-supervised domain, and more, impressive steps ahead are to be expected.\n", "\n", "### References\n", "\n", "[1] Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020).\n", "A simple framework for contrastive learning of visual representations.\n", "In International conference on machine learning (pp.\n", "1597-1607).\n", "PMLR.\n", "([link](https://arxiv.org/abs/2002.05709))\n", "\n", "[2] Chen, T., Kornblith, S., Swersky, K., Norouzi, M., and Hinton, G. (2020).\n", "Big self-supervised models are strong semi-supervised learners.\n", "NeurIPS 2021 ([link](https://arxiv.org/abs/2006.10029)).\n", "\n", "[3] Oord, A. V. D., Li, Y., and Vinyals, O.\n", "(2018).\n", "Representation learning with contrastive predictive coding.\n", "arXiv preprint arXiv:1807.03748.\n", "([link](https://arxiv.org/abs/1807.03748))\n", "\n", "[4] Grill, J.B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P.H., Buchatskaya, E., Doersch, C., Pires, B.A., Guo, Z.D., Azar, M.G.\n", "and Piot, B.\n", "(2020).\n", "Bootstrap your own latent: A new approach to self-supervised learning.\n", "arXiv preprint arXiv:2006.07733.\n", "([link](https://arxiv.org/abs/2006.07733))\n", "\n", "[5] Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C. and Krishnan, D. (2020).\n", "Supervised contrastive learning.\n", "arXiv preprint arXiv:2004.11362.\n", "([link](https://arxiv.org/abs/2004.11362))\n", "\n", "[6] Zbontar, J., Jing, L., Misra, I., LeCun, Y. and Deny, S. (2021).\n", "Barlow twins: Self-supervised learning via redundancy reduction.\n", "arXiv preprint arXiv:2103.03230.\n", "([link](https://arxiv.org/abs/2103.03230))"]}, {"cell_type": "markdown", "id": "ce384bac", "metadata": {"papermill": {"duration": 0.052469, "end_time": "2021-10-10T16:42:27.933096", "exception": false, "start_time": "2021-10-10T16:42:27.880627", "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 13: Self-Supervised Contrastive Learning with SimCLR\n", " :card_description: In this tutorial, we will take a closer look at self-supervised contrastive learning. Self-supervised learning, or also sometimes called unsupervised learning, describes the...\n", " :tags: Image,Self-Supervised,Contrastive-Learning,GPU/TPU,UvA-DL-Course\n", " :image: _static/images/course_UvA-DL/13-contrastive-learning.jpg"]}], "metadata": {"jupytext": {"cell_metadata_filter": "id,colab_type,colab,-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": 249.204813, "end_time": "2021-10-10T16:42:28.695919", "environment_variables": {}, "exception": null, "input_path": "course_UvA-DL/13-contrastive-learning/SimCLR.ipynb", "output_path": ".notebooks/course_UvA-DL/13-contrastive-learning.ipynb", "parameters": {}, "start_time": "2021-10-10T16:38:19.491106", "version": "2.3.3"}, "widgets": {"application/vnd.jupyter.widget-state+json": {"state": {"014eb2b9e9f84518838020b1995c1b8d": {"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_b2fc0cc8b5aa4c0c8b7c6ed61e30e1a1", "max": 1.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_06e3324339554e7d8653dd5ca34502c3", "value": 1.0}}, "06e3324339554e7d8653dd5ca34502c3": {"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": ""}}, "0f6b628c8d4d45f9876bc31bc99904ed": {"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_574e12bb3361469f9592f0b1e3ea131c", "IPY_MODEL_17ae240504aa41a69aac2f89637a872f", "IPY_MODEL_3c71b91bf99a44088d998afcceba0c5a"], "layout": "IPY_MODEL_c9f6fa6ff0a4421bbbebceb0868d6f72"}}, "17ae240504aa41a69aac2f89637a872f": {"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_9815469b386b421aa09d7a7c435486d6", "max": 1.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_48df5e7e12f14d529ee8253b7e81c15d", "value": 1.0}}, "1ba6707c32324d89a25d94b8826ad3fb": {"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}}, "261190710d154e79846a4b2be71408ed": {"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}}, "262c7a46de2548a1bb2c1bd654bae044": {"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_5dc49442ae4b4da1b8883f9729335464", "placeholder": "\u200b", "style": "IPY_MODEL_6fa3b6f47f774f06911972e497cbaa80", "value": " 79/79 [00:01<00:00, 80.29it/s]"}}, "29f4053f18004b2aa3ad1439d2b93651": {"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": ""}}, "2e223ff880144417a99a792b90424c4e": {"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}}, "32cad3ea3e3644baaa844883a715a613": {"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_8ac65a9e9dbc4e9b84ae76dbf7ba131e", "IPY_MODEL_ac28c76d49c141fb834867a4cee9bb41", "IPY_MODEL_262c7a46de2548a1bb2c1bd654bae044"], "layout": "IPY_MODEL_4d296fe6da9a4f4fbc71862dd3aef6a8"}}, "3329a069de5d4624a9412647f0d80198": {"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_492d73828f01466f9f1aad76d13d0217", "IPY_MODEL_b7093bf46de847f79cd6d83a8bca17be", "IPY_MODEL_dad5ea58db1c4416bebfd763d88c5c70"], "layout": "IPY_MODEL_261190710d154e79846a4b2be71408ed"}}, "3c71b91bf99a44088d998afcceba0c5a": {"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_b769c6c21b5b4aeba81b70f8ac423d79", "placeholder": "\u200b", "style": "IPY_MODEL_5a9c689a271f4e35b11302006704a498", "value": " 78/78 [00:02<00:00, 35.66it/s]"}}, "3de31fdecbe4407286cc95695466de5d": {"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_d87935149db141678e50b111ed61ec82", "placeholder": "\u200b", "style": "IPY_MODEL_98e77a3d53234245ab2a62d09bd5ddef", "value": " 2640397312/? [02:43<00:00, 17274904.03it/s]"}}, "48df5e7e12f14d529ee8253b7e81c15d": {"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": ""}}, "492d73828f01466f9f1aad76d13d0217": {"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_d56f70bb6f13477e9412473f278615c1", "placeholder": "\u200b", "style": "IPY_MODEL_f8d33dc2ecbe4476bd02a6b12d40d79b", "value": "100%"}}, "4b5ff77984894ccbb8ae6abd263a4b7c": {"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}}, "4d296fe6da9a4f4fbc71862dd3aef6a8": {"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}}, "57424a7cd3c7417dae1073397b010b1c": {"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": ""}}, "574e12bb3361469f9592f0b1e3ea131c": {"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_1ba6707c32324d89a25d94b8826ad3fb", "placeholder": "\u200b", "style": "IPY_MODEL_57424a7cd3c7417dae1073397b010b1c", "value": "Testing: 100%"}}, "5a9c689a271f4e35b11302006704a498": {"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": ""}}, "5c036d43b260499385714d1317f05efe": {"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}}, "5d2b7d0577694436ade46306715f91de": {"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": ""}}, "5dc49442ae4b4da1b8883f9729335464": {"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}}, "6fa3b6f47f774f06911972e497cbaa80": {"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": ""}}, "721cee3a7bed406c8050c8433a106386": {"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": ""}}, "762e3668c79e48839269b8d565098578": {"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": ""}}, "84c4574fe0744cdf837bcc9c3032acfc": {"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": ""}}, "8ac65a9e9dbc4e9b84ae76dbf7ba131e": {"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_2e223ff880144417a99a792b90424c4e", "placeholder": "\u200b", "style": "IPY_MODEL_721cee3a7bed406c8050c8433a106386", "value": "100%"}}, "8c91c107ddbc4f84a5a8b5e583c69773": {"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}}, "979d4939c8c04651bfd4a96e20d4d508": {"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}}, "97fdda0f484c4954804bd2c4ff8d013a": {"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_be6a5b00c73049329a585c53e6eb481a", "placeholder": "\u200b", "style": "IPY_MODEL_762e3668c79e48839269b8d565098578", "value": " 125/125 [00:01<00:00, 106.26it/s]"}}, "9815469b386b421aa09d7a7c435486d6": {"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": "2", "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}}, "98e77a3d53234245ab2a62d09bd5ddef": {"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": ""}}, "ac28c76d49c141fb834867a4cee9bb41": {"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_8c91c107ddbc4f84a5a8b5e583c69773", "max": 79.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_5d2b7d0577694436ade46306715f91de", "value": 79.0}}, "b2a75df791794c5cbf5d75ccfd368544": {"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_d174cfe6f91a431fbedf6fe767738f26", "placeholder": "\u200b", "style": "IPY_MODEL_84c4574fe0744cdf837bcc9c3032acfc", "value": ""}}, "b2fc0cc8b5aa4c0c8b7c6ed61e30e1a1": {"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": "2", "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}}, "b7093bf46de847f79cd6d83a8bca17be": {"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_979d4939c8c04651bfd4a96e20d4d508", "max": 125.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_c967a959d2e54813af244ce923b9bf70", "value": 125.0}}, "b769c6c21b5b4aeba81b70f8ac423d79": {"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}}, "be6a5b00c73049329a585c53e6eb481a": {"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}}, "c111f74da90d4a8f831df4733df12b94": {"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_b2a75df791794c5cbf5d75ccfd368544", "IPY_MODEL_dd15111b76d447d783d02a4ea9a5dbb2", "IPY_MODEL_3de31fdecbe4407286cc95695466de5d"], "layout": "IPY_MODEL_ef6374a810a14d32a08759170c9d66d1"}}, "c6548cbf34cb4f5f88108f9f7ac77fb4": {"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": ""}}, "c967a959d2e54813af244ce923b9bf70": {"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": ""}}, "c9f6fa6ff0a4421bbbebceb0868d6f72": {"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": "inline-flex", "flex": null, "flex_flow": "row wrap", "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": "100%"}}, "d174cfe6f91a431fbedf6fe767738f26": {"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}}, "d56f70bb6f13477e9412473f278615c1": {"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}}, "d87935149db141678e50b111ed61ec82": {"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}}, "d901ede9b3054a479a22fda21e763fea": {"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_f56016fba5604d9db49374c9af2829e1", "IPY_MODEL_014eb2b9e9f84518838020b1995c1b8d", "IPY_MODEL_97fdda0f484c4954804bd2c4ff8d013a"], "layout": "IPY_MODEL_e8120e786bbe4d56aed3a534970c020d"}}, "dad5ea58db1c4416bebfd763d88c5c70": {"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_4b5ff77984894ccbb8ae6abd263a4b7c", "placeholder": "\u200b", "style": "IPY_MODEL_ef38b8535cdf4ddfba9ced74f238ab28", "value": " 125/125 [00:01<00:00, 77.70it/s]"}}, "dd15111b76d447d783d02a4ea9a5dbb2": {"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_e2187c1fd5554b5c89ebf37667b20858", "max": 2640397119.0, "min": 0.0, "orientation": "horizontal", "style": "IPY_MODEL_29f4053f18004b2aa3ad1439d2b93651", "value": 2640397119.0}}, "e2187c1fd5554b5c89ebf37667b20858": {"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}}, "e8120e786bbe4d56aed3a534970c020d": {"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": "inline-flex", "flex": null, "flex_flow": "row wrap", "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": "100%"}}, "ef38b8535cdf4ddfba9ced74f238ab28": {"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": ""}}, "ef6374a810a14d32a08759170c9d66d1": {"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}}, "f56016fba5604d9db49374c9af2829e1": {"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_5c036d43b260499385714d1317f05efe", "placeholder": "\u200b", "style": "IPY_MODEL_c6548cbf34cb4f5f88108f9f7ac77fb4", "value": "Testing: 100%"}}, "f8d33dc2ecbe4476bd02a6b12d40d79b": {"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": ""}}}, "version_major": 2, "version_minor": 0}}}, "nbformat": 4, "nbformat_minor": 5}