{"cells": [{"cell_type": "markdown", "id": "ed3501af", "metadata": {"papermill": {"duration": 0.023462, "end_time": "2021-09-16T12:33:15.496875", "exception": false, "start_time": "2021-09-16T12:33:15.473413", "status": "completed"}, "tags": []}, "source": ["\n", "# Tutorial 2: Activation Functions\n", "\n", "* **Author:** Phillip Lippe\n", "* **License:** CC BY-SA\n", "* **Generated:** 2021-09-16T14:32:18.973374\n", "\n", "In this tutorial, we will take a closer look at (popular) activation functions and investigate their effect on optimization properties in neural networks.\n", "Activation functions are a crucial part of deep learning models as they add the non-linearity to neural networks.\n", "There is a great variety of activation functions in the literature, and some are more beneficial than others.\n", "The goal of this tutorial is to show the importance of choosing a good activation function (and how to do so), and what problems might occur if we don't.\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/02-activation-functions.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": "66b84901", "metadata": {"papermill": {"duration": 0.021804, "end_time": "2021-09-16T12:33:15.540678", "exception": false, "start_time": "2021-09-16T12:33:15.518874", "status": "completed"}, "tags": []}, "source": ["## Setup\n", "This notebook requires some packages besides pytorch-lightning."]}, {"cell_type": "code", "execution_count": 1, "id": "4d7c8160", "metadata": {"colab": {}, "colab_type": "code", "execution": {"iopub.execute_input": "2021-09-16T12:33:15.587749Z", "iopub.status.busy": "2021-09-16T12:33:15.587280Z", "iopub.status.idle": "2021-09-16T12:33:15.589355Z", "shell.execute_reply": "2021-09-16T12:33:15.589747Z"}, "id": "LfrJLKPFyhsK", "lines_to_next_cell": 0, "papermill": {"duration": 0.027383, "end_time": "2021-09-16T12:33:15.589924", "exception": false, "start_time": "2021-09-16T12:33:15.562541", "status": "completed"}, "tags": []}, "outputs": [], "source": ["# ! pip install --quiet \"torchmetrics>=0.3\" \"torch>=1.6, <1.9\" \"pytorch-lightning>=1.3\" \"torchvision\" \"seaborn\" \"matplotlib\""]}, {"cell_type": "markdown", "id": "94e4c637", "metadata": {"papermill": {"duration": 0.021895, "end_time": "2021-09-16T12:33:15.635408", "exception": false, "start_time": "2021-09-16T12:33:15.613513", "status": "completed"}, "tags": []}, "source": ["
\n", "Before we start, we import our standard libraries and set up basic functions:"]}, {"cell_type": "code", "execution_count": 2, "id": "afda8dd1", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:15.687272Z", "iopub.status.busy": "2021-09-16T12:33:15.686802Z", "iopub.status.idle": "2021-09-16T12:33:16.799385Z", "shell.execute_reply": "2021-09-16T12:33:16.799794Z"}, "papermill": {"duration": 1.142099, "end_time": "2021-09-16T12:33:16.799933", "exception": false, "start_time": "2021-09-16T12:33:15.657834", "status": "completed"}, "tags": []}, "outputs": [{"name": "stderr", "output_type": "stream", "text": ["/tmp/ipykernel_749/3776275675.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"]}], "source": ["import json\n", "import math\n", "import os\n", "import urllib.request\n", "import warnings\n", "from urllib.error import HTTPError\n", "\n", "import matplotlib.pyplot as plt\n", "import numpy as np\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", "\n", "# %matplotlib inline\n", "from IPython.display import set_matplotlib_formats\n", "from torchvision import transforms\n", "from torchvision.datasets import FashionMNIST\n", "from tqdm.notebook import tqdm\n", "\n", "set_matplotlib_formats(\"svg\", \"pdf\") # For export\n", "sns.set()"]}, {"cell_type": "markdown", "id": "2587fcef", "metadata": {"papermill": {"duration": 0.022118, "end_time": "2021-09-16T12:33:16.844975", "exception": false, "start_time": "2021-09-16T12:33:16.822857", "status": "completed"}, "tags": []}, "source": ["We will define a function to set a seed on all libraries we might interact with in this tutorial (here numpy and torch).\n", "This allows us to make our training reproducible.\n", "However, note that in contrast to the CPU, the same seed on different GPU architectures can give different results.\n", "All models here have been trained on an NVIDIA GTX1080Ti.\n", "\n", "Additionally, the following cell defines two paths: `DATASET_PATH` and `CHECKPOINT_PATH`.\n", "The dataset path is the directory where we will download datasets used in the notebooks.\n", "It is recommended to store all datasets from PyTorch in one joined directory to prevent duplicate downloads.\n", "The checkpoint path is the directory where we will store trained model weights and additional files.\n", "The needed files will be automatically downloaded.\n", "In case you are on Google Colab, it is recommended to change the\n", "directories to start from the current directory (i.e. remove `../` for\n", "both dataset and checkpoint path)."]}, {"cell_type": "code", "execution_count": 3, "id": "5ad210ad", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:16.894843Z", "iopub.status.busy": "2021-09-16T12:33:16.894366Z", "iopub.status.idle": "2021-09-16T12:33:16.964040Z", "shell.execute_reply": "2021-09-16T12:33:16.963624Z"}, "papermill": {"duration": 0.096979, "end_time": "2021-09-16T12:33:16.964150", "exception": false, "start_time": "2021-09-16T12:33:16.867171", "status": "completed"}, "tags": []}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Using device cuda:0\n"]}], "source": ["# Path to the folder where the datasets are/should be downloaded (e.g. MNIST)\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/Activation_Functions/\")\n", "\n", "\n", "# Function for setting the seed\n", "def set_seed(seed):\n", " np.random.seed(seed)\n", " torch.manual_seed(seed)\n", " if torch.cuda.is_available(): # GPU operation have separate seed\n", " torch.cuda.manual_seed(seed)\n", " torch.cuda.manual_seed_all(seed)\n", "\n", "\n", "set_seed(42)\n", "\n", "# Additionally, some operations on a GPU are implemented stochastic for efficiency\n", "# We want to 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", "# Fetching the device that will be used throughout this notebook\n", "device = torch.device(\"cpu\") if not torch.cuda.is_available() else torch.device(\"cuda:0\")\n", "print(\"Using device\", device)"]}, {"cell_type": "markdown", "id": "5aa7e547", "metadata": {"papermill": {"duration": 0.022623, "end_time": "2021-09-16T12:33:17.010058", "exception": false, "start_time": "2021-09-16T12:33:16.987435", "status": "completed"}, "tags": []}, "source": ["The following cell downloads all pretrained models we will use in this notebook.\n", "The files are stored on a separate [repository](https://github.com/phlippe/saved_models) to reduce the size of the notebook repository, especially for building the documentation on ReadTheDocs.\n", "In case the download below fails, you can download the models from a [Google Drive folder](https://drive.google.com/drive/folders/1sFpZUpDJVjiYEvIqISqfkFizfsTnPf4s?usp=sharing).\n", "Please let me (Phillip) know if an error occurs so it can be fixed for all students."]}, {"cell_type": "code", "execution_count": 4, "id": "58e26273", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:17.060096Z", "iopub.status.busy": "2021-09-16T12:33:17.059620Z", "iopub.status.idle": "2021-09-16T12:33:18.470969Z", "shell.execute_reply": "2021-09-16T12:33:18.470514Z"}, "papermill": {"duration": 1.438459, "end_time": "2021-09-16T12:33:18.471082", "exception": false, "start_time": "2021-09-16T12:33:17.032623", "status": "completed"}, "tags": []}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial3/FashionMNIST_elu.config...\n", "Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial3/FashionMNIST_elu.tar...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial3/FashionMNIST_leakyrelu.config...\n", "Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial3/FashionMNIST_leakyrelu.tar...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial3/FashionMNIST_relu.config...\n", "Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial3/FashionMNIST_relu.tar...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial3/FashionMNIST_sigmoid.config...\n", "Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial3/FashionMNIST_sigmoid.tar...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial3/FashionMNIST_swish.config...\n", "Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial3/FashionMNIST_swish.tar...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial3/FashionMNIST_tanh.config...\n", "Downloading https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial3/FashionMNIST_tanh.tar...\n"]}], "source": ["# Github URL where saved models are stored for this tutorial\n", "base_url = \"https://raw.githubusercontent.com/phlippe/saved_models/main/tutorial3/\"\n", "# Files to download\n", "pretrained_files = [\n", " \"FashionMNIST_elu.config\",\n", " \"FashionMNIST_elu.tar\",\n", " \"FashionMNIST_leakyrelu.config\",\n", " \"FashionMNIST_leakyrelu.tar\",\n", " \"FashionMNIST_relu.config\",\n", " \"FashionMNIST_relu.tar\",\n", " \"FashionMNIST_sigmoid.config\",\n", " \"FashionMNIST_sigmoid.tar\",\n", " \"FashionMNIST_swish.config\",\n", " \"FashionMNIST_swish.tar\",\n", " \"FashionMNIST_tanh.config\",\n", " \"FashionMNIST_tanh.tar\",\n", "]\n", "# Create checkpoint path if it doesn't exist yet\n", "os.makedirs(CHECKPOINT_PATH, exist_ok=True)\n", "\n", "# For each file, check whether it already exists. If not, try downloading it.\n", "for file_name in pretrained_files:\n", " file_path = os.path.join(CHECKPOINT_PATH, file_name)\n", " if 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": "acbb3e50", "metadata": {"papermill": {"duration": 0.023807, "end_time": "2021-09-16T12:33:18.519257", "exception": false, "start_time": "2021-09-16T12:33:18.495450", "status": "completed"}, "tags": []}, "source": ["## Common activation functions"]}, {"cell_type": "markdown", "id": "aa4d6503", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.023651, "end_time": "2021-09-16T12:33:18.566824", "exception": false, "start_time": "2021-09-16T12:33:18.543173", "status": "completed"}, "tags": []}, "source": ["As a first step, we will implement some common activation functions by ourselves.\n", "Of course, most of them can also be found in the `torch.nn` package (see the [documentation](https://pytorch.org/docs/stable/nn.html#non-linear-activations-weighted-sum-nonlinearity) for an overview).\n", "However, we'll write our own functions here for a better understanding and insights.\n", "\n", "For an easier time of comparing various activation functions, we start\n", "with defining a base class from which all our future modules will\n", "inherit:"]}, {"cell_type": "code", "execution_count": 5, "id": "3dcfd06e", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:18.618629Z", "iopub.status.busy": "2021-09-16T12:33:18.618166Z", "iopub.status.idle": "2021-09-16T12:33:18.620230Z", "shell.execute_reply": "2021-09-16T12:33:18.619833Z"}, "papermill": {"duration": 0.029814, "end_time": "2021-09-16T12:33:18.620328", "exception": false, "start_time": "2021-09-16T12:33:18.590514", "status": "completed"}, "tags": []}, "outputs": [], "source": ["class ActivationFunction(nn.Module):\n", " def __init__(self):\n", " super().__init__()\n", " self.name = self.__class__.__name__\n", " self.config = {\"name\": self.name}"]}, {"cell_type": "markdown", "id": "d528e8e9", "metadata": {"papermill": {"duration": 0.023943, "end_time": "2021-09-16T12:33:18.668417", "exception": false, "start_time": "2021-09-16T12:33:18.644474", "status": "completed"}, "tags": []}, "source": ["Every activation function will be an `nn.Module` so that we can integrate them nicely in a network.\n", "We will use the `config` dictionary to store adjustable parameters for some activation functions.\n", "\n", "Next, we implement two of the \"oldest\" activation functions that are still commonly used for various tasks: sigmoid and tanh.\n", "Both the sigmoid and tanh activation can be also found as PyTorch functions (`torch.sigmoid`, `torch.tanh`) or as modules (`nn.Sigmoid`, `nn.Tanh`).\n", "Here, we implement them by hand:"]}, {"cell_type": "code", "execution_count": 6, "id": "e86a8cd3", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:18.720307Z", "iopub.status.busy": "2021-09-16T12:33:18.719843Z", "iopub.status.idle": "2021-09-16T12:33:18.721916Z", "shell.execute_reply": "2021-09-16T12:33:18.721501Z"}, "papermill": {"duration": 0.029566, "end_time": "2021-09-16T12:33:18.722011", "exception": false, "start_time": "2021-09-16T12:33:18.692445", "status": "completed"}, "tags": []}, "outputs": [], "source": ["class Sigmoid(ActivationFunction):\n", " def forward(self, x):\n", " return 1 / (1 + torch.exp(-x))\n", "\n", "\n", "class Tanh(ActivationFunction):\n", " def forward(self, x):\n", " x_exp, neg_x_exp = torch.exp(x), torch.exp(-x)\n", " return (x_exp - neg_x_exp) / (x_exp + neg_x_exp)"]}, {"cell_type": "markdown", "id": "b2beae98", "metadata": {"papermill": {"duration": 0.023891, "end_time": "2021-09-16T12:33:18.770175", "exception": false, "start_time": "2021-09-16T12:33:18.746284", "status": "completed"}, "tags": []}, "source": ["Another popular activation function that has allowed the training of deeper networks, is the Rectified Linear Unit (ReLU).\n", "Despite its simplicity of being a piecewise linear function, ReLU has one major benefit compared to sigmoid and tanh: a strong, stable gradient for a large range of values.\n", "Based on this idea, a lot of variations of ReLU have been proposed, of which we will implement the following three: LeakyReLU, ELU, and Swish.\n", "LeakyReLU replaces the zero settings in the negative part with a smaller slope to allow gradients to flow also in this part of the input.\n", "Similarly, ELU replaces the negative part with an exponential decay.\n", "The third, most recently proposed activation function is Swish, which is actually the result of a large experiment with the purpose of finding the \"optimal\" activation function.\n", "Compared to the other activation functions, Swish is both smooth and non-monotonic (i.e. contains a change of sign in the gradient).\n", "This has been shown to prevent dead neurons as in standard ReLU activation, especially for deep networks.\n", "If interested, a more detailed discussion of the benefits of Swish can be found in [this paper](https://arxiv.org/abs/1710.05941) [1].\n", "\n", "Let's implement the four activation functions below:"]}, {"cell_type": "code", "execution_count": 7, "id": "68254625", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:18.823746Z", "iopub.status.busy": "2021-09-16T12:33:18.823281Z", "iopub.status.idle": "2021-09-16T12:33:18.825314Z", "shell.execute_reply": "2021-09-16T12:33:18.824855Z"}, "papermill": {"duration": 0.030969, "end_time": "2021-09-16T12:33:18.825411", "exception": false, "start_time": "2021-09-16T12:33:18.794442", "status": "completed"}, "tags": []}, "outputs": [], "source": ["class ReLU(ActivationFunction):\n", " def forward(self, x):\n", " return x * (x > 0).float()\n", "\n", "\n", "class LeakyReLU(ActivationFunction):\n", " def __init__(self, alpha=0.1):\n", " super().__init__()\n", " self.config[\"alpha\"] = alpha\n", "\n", " def forward(self, x):\n", " return torch.where(x > 0, x, self.config[\"alpha\"] * x)\n", "\n", "\n", "class ELU(ActivationFunction):\n", " def forward(self, x):\n", " return torch.where(x > 0, x, torch.exp(x) - 1)\n", "\n", "\n", "class Swish(ActivationFunction):\n", " def forward(self, x):\n", " return x * torch.sigmoid(x)"]}, {"cell_type": "markdown", "id": "587dfd90", "metadata": {"papermill": {"duration": 0.023958, "end_time": "2021-09-16T12:33:18.873222", "exception": false, "start_time": "2021-09-16T12:33:18.849264", "status": "completed"}, "tags": []}, "source": ["For later usage, we summarize all our activation functions in a dictionary mapping the name to the class object.\n", "In case you implement a new activation function by yourself, add it here to include it in future comparisons as well:"]}, {"cell_type": "code", "execution_count": 8, "id": "61e3706d", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:18.924380Z", "iopub.status.busy": "2021-09-16T12:33:18.923908Z", "iopub.status.idle": "2021-09-16T12:33:18.925974Z", "shell.execute_reply": "2021-09-16T12:33:18.925558Z"}, "papermill": {"duration": 0.02888, "end_time": "2021-09-16T12:33:18.926069", "exception": false, "start_time": "2021-09-16T12:33:18.897189", "status": "completed"}, "tags": []}, "outputs": [], "source": ["act_fn_by_name = {\"sigmoid\": Sigmoid, \"tanh\": Tanh, \"relu\": ReLU, \"leakyrelu\": LeakyReLU, \"elu\": ELU, \"swish\": Swish}"]}, {"cell_type": "markdown", "id": "21624a4a", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.024088, "end_time": "2021-09-16T12:33:18.974301", "exception": false, "start_time": "2021-09-16T12:33:18.950213", "status": "completed"}, "tags": []}, "source": ["### Visualizing activation functions\n", "\n", "To get an idea of what each activation function actually does, we will visualize them in the following.\n", "Next to the actual activation value, the gradient of the function is an important aspect as it is crucial for optimizing the neural network.\n", "PyTorch allows us to compute the gradients simply by calling the `backward` function:"]}, {"cell_type": "code", "execution_count": 9, "id": "f0c123df", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:19.026746Z", "iopub.status.busy": "2021-09-16T12:33:19.026268Z", "iopub.status.idle": "2021-09-16T12:33:19.027904Z", "shell.execute_reply": "2021-09-16T12:33:19.028280Z"}, "lines_to_next_cell": 2, "papermill": {"duration": 0.029948, "end_time": "2021-09-16T12:33:19.028393", "exception": false, "start_time": "2021-09-16T12:33:18.998445", "status": "completed"}, "tags": []}, "outputs": [], "source": ["def get_grads(act_fn, x):\n", " \"\"\"Computes the gradients of an activation function at specified positions.\n", "\n", " Args:\n", " act_fn: An object of the class \"ActivationFunction\" with an implemented forward pass.\n", " x: 1D input tensor.\n", " Returns:\n", " A tensor with the same size of x containing the gradients of act_fn at x.\n", " \"\"\"\n", " x = x.clone().requires_grad_() # Mark the input as tensor for which we want to store gradients\n", " out = act_fn(x)\n", " out.sum().backward() # Summing results in an equal gradient flow to each element in x\n", " return x.grad # Accessing the gradients of x by \"x.grad\""]}, {"cell_type": "markdown", "id": "76f9c1ee", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.024154, "end_time": "2021-09-16T12:33:19.077839", "exception": false, "start_time": "2021-09-16T12:33:19.053685", "status": "completed"}, "tags": []}, "source": ["Now we can visualize all our activation functions including their gradients:"]}, {"cell_type": "code", "execution_count": 10, "id": "a03e014f", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:19.132841Z", "iopub.status.busy": "2021-09-16T12:33:19.132367Z", "iopub.status.idle": "2021-09-16T12:33:20.711026Z", "shell.execute_reply": "2021-09-16T12:33:20.711412Z"}, "papermill": {"duration": 1.60939, "end_time": "2021-09-16T12:33:20.711553", "exception": false, "start_time": "2021-09-16T12:33:19.102163", "status": "completed"}, "tags": []}, "outputs": [{"data": {"application/pdf": "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\n", "image/svg+xml": ["\n", "\n", "\n"], "text/plain": [""]}, "metadata": {}, "output_type": "display_data"}], "source": ["def vis_act_fn(act_fn, ax, x):\n", " # Run activation function\n", " y = act_fn(x)\n", " y_grads = get_grads(act_fn, x)\n", " # Push x, y and gradients back to cpu for plotting\n", " x, y, y_grads = x.cpu().numpy(), y.cpu().numpy(), y_grads.cpu().numpy()\n", " # Plotting\n", " ax.plot(x, y, linewidth=2, label=\"ActFn\")\n", " ax.plot(x, y_grads, linewidth=2, label=\"Gradient\")\n", " ax.set_title(act_fn.name)\n", " ax.legend()\n", " ax.set_ylim(-1.5, x.max())\n", "\n", "\n", "# Add activation functions if wanted\n", "act_fns = [act_fn() for act_fn in act_fn_by_name.values()]\n", "x = torch.linspace(-5, 5, 1000) # Range on which we want to visualize the activation functions\n", "# Plotting\n", "cols = 2\n", "rows = math.ceil(len(act_fns) / float(cols))\n", "fig, ax = plt.subplots(rows, cols, figsize=(cols * 4, rows * 4))\n", "for i, act_fn in enumerate(act_fns):\n", " vis_act_fn(act_fn, ax[divmod(i, cols)], x)\n", "fig.subplots_adjust(hspace=0.3)\n", "plt.show()"]}, {"cell_type": "markdown", "id": "350e27aa", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.027663, "end_time": "2021-09-16T12:33:20.771273", "exception": false, "start_time": "2021-09-16T12:33:20.743610", "status": "completed"}, "tags": []}, "source": ["## Analysing the effect of activation functions\n", "
"]}, {"cell_type": "markdown", "id": "683c2c7d", "metadata": {"papermill": {"duration": 0.027646, "end_time": "2021-09-16T12:33:20.826418", "exception": false, "start_time": "2021-09-16T12:33:20.798772", "status": "completed"}, "tags": []}, "source": ["After implementing and visualizing the activation functions, we are aiming to gain insights into their effect.\n", "We do this by using a simple neural network trained on\n", "[FashionMNIST](https://github.com/zalandoresearch/fashion-mnist) and\n", "examine various aspects of the model, including the performance and\n", "gradient flow."]}, {"cell_type": "markdown", "id": "84e11974", "metadata": {"papermill": {"duration": 0.027431, "end_time": "2021-09-16T12:33:20.881415", "exception": false, "start_time": "2021-09-16T12:33:20.853984", "status": "completed"}, "tags": []}, "source": ["### Setup"]}, {"cell_type": "markdown", "id": "cf662ea5", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.027344, "end_time": "2021-09-16T12:33:20.936216", "exception": false, "start_time": "2021-09-16T12:33:20.908872", "status": "completed"}, "tags": []}, "source": ["Firstly, let's set up a neural network.\n", "The chosen network views the images as 1D tensors and pushes them through a sequence of linear layers and a specified activation function.\n", "Feel free to experiment with other network architectures."]}, {"cell_type": "code", "execution_count": 11, "id": "517f9479", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:20.997665Z", "iopub.status.busy": "2021-09-16T12:33:20.997195Z", "iopub.status.idle": "2021-09-16T12:33:20.999429Z", "shell.execute_reply": "2021-09-16T12:33:20.998822Z"}, "lines_to_next_cell": 2, "papermill": {"duration": 0.035645, "end_time": "2021-09-16T12:33:20.999530", "exception": false, "start_time": "2021-09-16T12:33:20.963885", "status": "completed"}, "tags": []}, "outputs": [], "source": ["class BaseNetwork(nn.Module):\n", " def __init__(self, act_fn, input_size=784, num_classes=10, hidden_sizes=[512, 256, 256, 128]):\n", " \"\"\"\n", " Args:\n", " act_fn: Object of the activation function that should be used as non-linearity in the network.\n", " input_size: Size of the input images in pixels\n", " num_classes: Number of classes we want to predict\n", " hidden_sizes: A list of integers specifying the hidden layer sizes in the NN\n", " \"\"\"\n", " super().__init__()\n", "\n", " # Create the network based on the specified hidden sizes\n", " layers = []\n", " layer_sizes = [input_size] + hidden_sizes\n", " layer_size_last = layer_sizes[0]\n", " for layer_size in layer_sizes[1:]:\n", " layers += [nn.Linear(layer_size_last, layer_size), act_fn]\n", " layer_size_last = layer_size\n", " layers += [nn.Linear(layer_sizes[-1], num_classes)]\n", " # nn.Sequential summarizes a list of modules into a single module, applying them in sequence\n", " self.layers = nn.Sequential(*layers)\n", "\n", " # We store all hyperparameters in a dictionary for saving and loading of the model\n", " self.config = {\n", " \"act_fn\": act_fn.config,\n", " \"input_size\": input_size,\n", " \"num_classes\": num_classes,\n", " \"hidden_sizes\": hidden_sizes,\n", " }\n", "\n", " def forward(self, x):\n", " x = x.view(x.size(0), -1) # Reshape images to a flat vector\n", " out = self.layers(x)\n", " return out"]}, {"cell_type": "markdown", "id": "6f191c6f", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.027564, "end_time": "2021-09-16T12:33:21.054674", "exception": false, "start_time": "2021-09-16T12:33:21.027110", "status": "completed"}, "tags": []}, "source": ["We also add functions for loading and saving the model.\n", "The hyperparameters are stored in a configuration file (simple json file):"]}, {"cell_type": "code", "execution_count": 12, "id": "36782eee", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:21.117432Z", "iopub.status.busy": "2021-09-16T12:33:21.116957Z", "iopub.status.idle": "2021-09-16T12:33:21.119088Z", "shell.execute_reply": "2021-09-16T12:33:21.118695Z"}, "papermill": {"duration": 0.036557, "end_time": "2021-09-16T12:33:21.119184", "exception": false, "start_time": "2021-09-16T12:33:21.082627", "status": "completed"}, "tags": []}, "outputs": [], "source": ["def _get_config_file(model_path, model_name):\n", " # Name of the file for storing hyperparameter details\n", " return os.path.join(model_path, model_name + \".config\")\n", "\n", "\n", "def _get_model_file(model_path, model_name):\n", " # Name of the file for storing network parameters\n", " return os.path.join(model_path, model_name + \".tar\")\n", "\n", "\n", "def load_model(model_path, model_name, net=None):\n", " \"\"\"Loads a saved model from disk.\n", "\n", " Args:\n", " model_path: Path of the checkpoint directory\n", " model_name: Name of the model (str)\n", " net: (Optional) If given, the state dict is loaded into this model. Otherwise, a new model is created.\n", " \"\"\"\n", " config_file, model_file = _get_config_file(model_path, model_name), _get_model_file(model_path, model_name)\n", " assert os.path.isfile(\n", " config_file\n", " ), f'Could not find the config file \"{config_file}\". Are you sure this is the correct path and you have your model config stored here?'\n", " assert os.path.isfile(\n", " model_file\n", " ), f'Could not find the model file \"{model_file}\". Are you sure this is the correct path and you have your model stored here?'\n", " with open(config_file) as f:\n", " config_dict = json.load(f)\n", " if net is None:\n", " act_fn_name = config_dict[\"act_fn\"].pop(\"name\").lower()\n", " act_fn = act_fn_by_name[act_fn_name](**config_dict.pop(\"act_fn\"))\n", " net = BaseNetwork(act_fn=act_fn, **config_dict)\n", " net.load_state_dict(torch.load(model_file, map_location=device))\n", " return net\n", "\n", "\n", "def save_model(model, model_path, model_name):\n", " \"\"\"Given a model, we save the state_dict and hyperparameters.\n", "\n", " Args:\n", " model: Network object to save parameters from\n", " model_path: Path of the checkpoint directory\n", " model_name: Name of the model (str)\n", " \"\"\"\n", " config_dict = model.config\n", " os.makedirs(model_path, exist_ok=True)\n", " config_file, model_file = _get_config_file(model_path, model_name), _get_model_file(model_path, model_name)\n", " with open(config_file, \"w\") as f:\n", " json.dump(config_dict, f)\n", " torch.save(model.state_dict(), model_file)"]}, {"cell_type": "markdown", "id": "b2ca0082", "metadata": {"papermill": {"duration": 0.027629, "end_time": "2021-09-16T12:33:21.174646", "exception": false, "start_time": "2021-09-16T12:33:21.147017", "status": "completed"}, "tags": []}, "source": ["We also set up the dataset we want to train it on, namely [FashionMNIST](https://github.com/zalandoresearch/fashion-mnist).\n", "FashionMNIST is a more complex version of MNIST and contains black-and-white images of clothes instead of digits.\n", "The 10 classes include trousers, coats, shoes, bags and more.\n", "To load this dataset, we will make use of yet another PyTorch package, namely `torchvision` ([documentation](https://pytorch.org/vision/stable/index.html)).\n", "The `torchvision` package consists of popular datasets, model architectures, and common image transformations for computer vision.\n", "We will use the package for many of the notebooks in this course to simplify our dataset handling.\n", "\n", "Let's load the dataset below, and visualize a few images to get an impression of the data."]}, {"cell_type": "code", "execution_count": 13, "id": "d28b09ac", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:21.234912Z", "iopub.status.busy": "2021-09-16T12:33:21.234444Z", "iopub.status.idle": "2021-09-16T12:33:25.742469Z", "shell.execute_reply": "2021-09-16T12:33:25.741983Z"}, "papermill": {"duration": 4.539991, "end_time": "2021-09-16T12:33:25.742582", "exception": false, "start_time": "2021-09-16T12:33:21.202591", "status": "completed"}, "tags": []}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz\n"]}, {"name": "stdout", "output_type": "stream", "text": ["Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to /__w/2/s/.datasets/FashionMNIST/raw/train-images-idx3-ubyte.gz\n"]}, {"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "783d0fee8e0b4746ad687e2606ab92b1", "version_major": 2, "version_minor": 0}, "text/plain": [" 0%| | 0/26421880 [00:00 first make them a tensor, then normalize them in the range -1 to 1\n", "transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))])\n", "\n", "# Loading the training dataset. We need to split it into a training and validation part\n", "train_dataset = FashionMNIST(root=DATASET_PATH, train=True, transform=transform, download=True)\n", "train_set, val_set = torch.utils.data.random_split(train_dataset, [50000, 10000])\n", "\n", "# Loading the test set\n", "test_set = FashionMNIST(root=DATASET_PATH, train=False, transform=transform, download=True)"]}, {"cell_type": "markdown", "id": "22d8c0df", "metadata": {"papermill": {"duration": 0.031277, "end_time": "2021-09-16T12:33:25.805768", "exception": false, "start_time": "2021-09-16T12:33:25.774491", "status": "completed"}, "tags": []}, "source": ["We define a set of data loaders that we can use for various purposes later.\n", "Note that for actually training a model, we will use different data loaders\n", "with a lower batch size."]}, {"cell_type": "code", "execution_count": 14, "id": "079a68d3", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:25.874180Z", "iopub.status.busy": "2021-09-16T12:33:25.873691Z", "iopub.status.idle": "2021-09-16T12:33:25.875574Z", "shell.execute_reply": "2021-09-16T12:33:25.875949Z"}, "papermill": {"duration": 0.036986, "end_time": "2021-09-16T12:33:25.876059", "exception": false, "start_time": "2021-09-16T12:33:25.839073", "status": "completed"}, "tags": []}, "outputs": [], "source": ["train_loader = data.DataLoader(train_set, batch_size=1024, shuffle=True, drop_last=False)\n", "val_loader = data.DataLoader(val_set, batch_size=1024, shuffle=False, drop_last=False)\n", "test_loader = data.DataLoader(test_set, batch_size=1024, shuffle=False, drop_last=False)"]}, {"cell_type": "code", "execution_count": 15, "id": "09ec856b", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:25.943298Z", "iopub.status.busy": "2021-09-16T12:33:25.942829Z", "iopub.status.idle": "2021-09-16T12:33:26.149461Z", "shell.execute_reply": "2021-09-16T12:33:26.148976Z"}, "papermill": {"duration": 0.241991, "end_time": "2021-09-16T12:33:26.149573", "exception": false, "start_time": "2021-09-16T12:33:25.907582", "status": "completed"}, "tags": []}, "outputs": [{"data": {"application/pdf": "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\n", "image/svg+xml": ["\n", "\n", "\n"], "text/plain": [""]}, "metadata": {}, "output_type": "display_data"}], "source": ["exmp_imgs = [train_set[i][0] for i in range(16)]\n", "# Organize the images into a grid for nicer visualization\n", "img_grid = torchvision.utils.make_grid(torch.stack(exmp_imgs, dim=0), nrow=4, normalize=True, pad_value=0.5)\n", "img_grid = img_grid.permute(1, 2, 0)\n", "\n", "plt.figure(figsize=(8, 8))\n", "plt.title(\"FashionMNIST examples\")\n", "plt.imshow(img_grid)\n", "plt.axis(\"off\")\n", "plt.show()\n", "plt.close()"]}, {"cell_type": "markdown", "id": "23a0bd21", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.032861, "end_time": "2021-09-16T12:33:26.216246", "exception": false, "start_time": "2021-09-16T12:33:26.183385", "status": "completed"}, "tags": []}, "source": ["### Visualizing the gradient flow after initialization\n", "\n", "As mentioned previously, one important aspect of activation functions is how they propagate gradients through the network.\n", "Imagine we have a very deep neural network with more than 50 layers.\n", "The gradients for the input layer, i.e. the very first layer, have passed >50 times the activation function, but we still want them to be of a reasonable size.\n", "If the gradient through the activation function is (in expectation) considerably smaller than 1, our gradients will vanish until they reach the input layer.\n", "If the gradient through the activation function is larger than 1, the gradients exponentially increase and might explode.\n", "\n", "To get a feeling of how every activation function influences the\n", "gradients, we can look at a freshly initialized network and measure the\n", "gradients for each parameter for a batch of 256 images:"]}, {"cell_type": "code", "execution_count": 16, "id": "d0313697", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:26.290315Z", "iopub.status.busy": "2021-09-16T12:33:26.289838Z", "iopub.status.idle": "2021-09-16T12:33:26.291904Z", "shell.execute_reply": "2021-09-16T12:33:26.291439Z"}, "papermill": {"duration": 0.043006, "end_time": "2021-09-16T12:33:26.292005", "exception": false, "start_time": "2021-09-16T12:33:26.248999", "status": "completed"}, "tags": []}, "outputs": [], "source": ["def visualize_gradients(net, color=\"C0\"):\n", " \"\"\"\n", " Args:\n", " net: Object of class BaseNetwork\n", " color: Color in which we want to visualize the histogram (for easier separation of activation functions)\n", " \"\"\"\n", " net.eval()\n", " small_loader = data.DataLoader(train_set, batch_size=256, shuffle=False)\n", " imgs, labels = next(iter(small_loader))\n", " imgs, labels = imgs.to(device), labels.to(device)\n", "\n", " # Pass one batch through the network, and calculate the gradients for the weights\n", " net.zero_grad()\n", " preds = net(imgs)\n", " loss = F.cross_entropy(preds, labels)\n", " loss.backward()\n", " # We limit our visualization to the weight parameters and exclude the bias to reduce the number of plots\n", " grads = {\n", " name: params.grad.data.view(-1).cpu().clone().numpy()\n", " for name, params in net.named_parameters()\n", " if \"weight\" in name\n", " }\n", " net.zero_grad()\n", "\n", " # Plotting\n", " columns = len(grads)\n", " fig, ax = plt.subplots(1, columns, figsize=(columns * 3.5, 2.5))\n", " fig_index = 0\n", " for key in grads:\n", " key_ax = ax[fig_index % columns]\n", " sns.histplot(data=grads[key], bins=30, ax=key_ax, color=color, kde=True)\n", " key_ax.set_title(str(key))\n", " key_ax.set_xlabel(\"Grad magnitude\")\n", " fig_index += 1\n", " fig.suptitle(\n", " f\"Gradient magnitude distribution for activation function {net.config['act_fn']['name']}\", fontsize=14, y=1.05\n", " )\n", " fig.subplots_adjust(wspace=0.45)\n", " plt.show()\n", " plt.close()"]}, {"cell_type": "code", "execution_count": 17, "id": "41a44b36", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:26.364210Z", "iopub.status.busy": "2021-09-16T12:33:26.363743Z", "iopub.status.idle": "2021-09-16T12:33:55.550270Z", "shell.execute_reply": "2021-09-16T12:33:55.550658Z"}, "papermill": {"duration": 29.22383, "end_time": "2021-09-16T12:33:55.550789", "exception": false, "start_time": "2021-09-16T12:33:26.326959", "status": "completed"}, "tags": []}, "outputs": [{"data": {"application/pdf": "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\n", "image/svg+xml": ["\n", "\n", "\n"], "text/plain": [""]}, "metadata": {}, "output_type": "display_data"}, {"data": {"application/pdf": "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\n", "image/svg+xml": ["\n", "\n", "\n"], "text/plain": [""]}, "metadata": {}, "output_type": "display_data"}, {"data": {"application/pdf": "JVBERi0xLjQKJazcIKu6CjEgMCBvYmoKPDwgL1BhZ2VzIDIgMCBSIC9UeXBlIC9DYXRhbG9nID4+CmVuZG9iago4IDAgb2JqCjw8IC9FeHRHU3RhdGUgNCAwIFIgL0ZvbnQgMyAwIFIgL1BhdHRlcm4gNSAwIFIKL1Byb2NTZXQgWyAvUERGIC9UZXh0IC9JbWFnZUIgL0ltYWdlQyAvSW1hZ2VJIF0gL1NoYWRpbmcgNiAwIFIKL1hPYmplY3QgNyAwIFIgPj4KZW5kb2JqCjExIDAgb2JqCjw8IC9Bbm5vdHMgMTAgMCBSIC9Db250ZW50cyA5IDAgUgovR3JvdXAgPDwgL0NTIC9EZXZpY2VSR0IgL1MgL1RyYW5zcGFyZW5jeSAvVHlwZSAvR3JvdXAgPj4KL01lZGlhQm94IFsgMCAwIDEwNzUuMzEwMzE2Mjc1MyAyMTYuNjY1NjI1IF0gL1BhcmVudCAyIDAgUiAvUmVzb3VyY2VzIDggMCBSCi9UeXBlIC9QYWdlID4+CmVuZG9iago5IDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggMTIgMCBSID4+CnN0cmVhbQp4nNWdT5NkqXXF9/UpcikthIALXFhalj0RCm8kj+2Fw4vxqCW3YnoUmj9S+Nv7HHiZCSRZmqrOrjaWpag8ncl79/d4cIHLxZ3+9PTLf3CnP35/wv+c7OlP+O/f8PcX/Pxk8enDk7MajTgrLuHzN8Nn75JJKSYf8Q92/Pg/T09/eLKmOE1Bbcz5NH8IxbqSrObTd7z4FzdfuHx4mr799KTBCC4TvCntgh+evFNTvJbgOvmbXnaaTT7rRwmDVu/5L6ebwl0Qk6xHGbglfJRoyum7d6f/OH17+uU/+AbwN/jvn/DfCvDpl79+99f3X7/73Re/On39/ZMmE8SV7IY7vqrDXTz969NvT385F2yNi3g457Lrxy8O9ekvTw7kfmHxTzEZqz7Z5FwuJx+Nsyzu6w9Pv/ry9Mt/xjXc6cs/PBWDp6QlZY345Ze/f/rP08+ssdb9/PRfpy9/8/RPXwIABMeCbffX1x9Yyi9+/e5PX/37j//61bff/+LD+29//P706z+ffvv023rHj+fmgjMSUpHxUXfyA8g5wIoFpaGylWfQ2QGYvQL7VNZ7m4xPLuNtGCr6VX6E9cWa6FiaWPdTjXe98V1hRY0L3paIl9afitG+HD+W88V3X/3+9OGrP377/ocff//u09P86U3GK19ANRk/l2w0xyL6LMM3MzdlY4MrUkZzr/JrzfWlmpsEFdB71KCQ0zMW+/gmr8xRYhGDKu2jH62+yh9pdc6mSI7onor6Z6ym0W9nNWwzroSY0mh2p3+k3XjK6BBC1hxCzM8Yrm/6uFmOV4sGcbT7Ir/abN/MlmJsca6gaQvhGbOdfdsHjtcYvRbe48nwq/6xlqdg4C9EGzXIc4bfvN9/eWIxv2CBcAuPlxI9g7ixd5l6hX/884/f/vCRAKUZKpf/g/+Y2CNJxE/wLwFuJDwvUamuJ/o/iw7Qolof7m//41P/46fpx09P2ZocfbBp6FlyNN4G+k59xzKq8MISq+ZYwlmFL/qr///GL8yE8cXEGJOLo/GDmn1SvUFyVvcwfmHmhyfU8gJH3JXB+E7FW+AlWz8i6dQtjF+ZCeOz8fxRGI2/qjAzp4K7mZGc1T2MX5jJkbI3ydng82B9L6M/ihqdzFAu6hbmLw2l/QkfvBU/2X+VxWDU5qLeYLnImwBYWAoADsNSJ0nSCKCTYRRGbhomLp28B4CVpQQQOQHkp/FUL2Oo7UQ0T1w6eRMAC0sBwHPCJOUwdn29rHBJg9aBV19IJ+8BYGUpAbAqY3RQJgAXOToTnEpII5de3gTAwlICwPjfWxtlAnCRYzGpYAxaJi6dvAmAhaUAIOjN1eGXI4CrrNFYKV5k5NLLewBYWUoAaoIXn6Zu8CrD84lio9WRSy9vAmBhaZudVQ05Td3gVXa1vc/qRy69vAeAlaUEkIzzCQPwCcBFdmJZ7VNOE5he3wTBwlYgiPimZqtTR3iVc0K5GosbyfTyHgBWlhJAMNmXpFNHeJVTxO8w8PUjl17eBMDCUgIoxmW071NHeJVjMtHjmjpy6eVNACwsBYDE9tyPqzff9DIeutMQU5i4dPIeAFaWEoCaTN9m6gg7WTHwFxfTyKWXNwGwsBQA1BsvyZapI+xk+DwabHATl07eA8DKUgLAu4w32U4dYScHgx/ZNHPp5E0ALCwFgGxNkQKvbgTQyaj1GP/YPHHp5D0ArCwlgGh8sfjPBOAqC5eMXfI3XC7yJgAWlhIAxnXBc3ZvBHCVhWNgze6Gy0XeBMDCUgDgPC/vb+oGRznHwxceCznLewBYWUoAXIyL6qducJQznnVYcDnkTQAsLGW8ijepKIZ4Y2DWKGdNxS+4HPIWAJaWEgAcmpCLTPb3KkZ/uSyoHPIm5t/ayXVphy/aKGMfOMnqUpAbKmf1teaPS+kmnv72dNeeEcbvvjiNS+7zMq3EyJiaoqbYXEJqPZba1o7biAFthBtfe3JbQhvnWkb8qW8LfgrIxwqJGoXfF5WODwrhFygXo06FK2QwO9fhIWeNcfmiwQv9RIlSWt/pApmEjLJT6zraHHNClyoxKOXinLR21ikcjILmtXrbqkf/47giqQlFZxgAa/WYpvVOUnSUUwqgXGXPIYuirY6Of8XoDjmLqoRT5BdSKW2qU0xgWFQ8RTo32Tafx2PgZ6PC6Ysc+vsotRn0yeAes2CUlI0WjAxa2ZwsQqOA4bMzPqH25GMW0WY8j8SohQT656nF4Ap+iDE13MncvivW2AZNuf6QD9iCDylZG06Kp5EkNE7ijfV4KeMpE4K34SwDsA2QHZ4Gnmk5JvNEUEXSKeOvjKd0nuMrBfbqCf17wDOqa31OAvo63G0+odezima/fRscXHB6claM52MPxzxZ8QmvzYnPVBJGiG3+LIOm9+JrIKPFH67dYoE3jQom9aXggLLNtwW85JFvzIlDLqdWjjkYALUJw64THXHBG1XOs1M5eZGE79fOOWnTgwEjfOvEWoM6XN9UzuHBcQtCGa8XzJN8TPHAcph+KgXvcFFbiQXCxmP3p4L3D91/GwsFAmGAFfmKVThGh4x6FfEBrnKxoBGO2RPBJzx2FYZGwnWuskNTkhKaUsUXtLR4GIdaiWrDKIuUWG0a9Uh/KyQMPxNeNnzJ+mNeomSvqNnJMpjoeL9RVwu8cyct7rZgsFbljMt7FHnC79QxKO4Y20dFo5b4RrANybVslJjxeohyyA9iIbTxMRoqVHJOK1feoc2Us27j5Qms1XhO9abrZBHaH6lvMV769shgF545yPOdR0uVjhLw8gR1obYQAa1TsyWhxFjwotZluILr1UKUU5HqQ219FHIzEXWD0/RVjZYvxKEmxvbUEZ0wTKreH5rrhIujPWXDFrO0pkDRSGsMrRnM0bIpbd4/KmmsTalEtCtNRSUttR9gCytBtcmKBko1afOUcd96eA9F+Pqcu89a6XFDAOyDHt2KlVop564pt/HGHXkMpPLsVQzahdZN/t1Y01W8OUpchqB+uBu1jl+8KI719qrPlm1h1E8OHLaWKxdooy2DfV0O56LuR3d989X/vvvue2PN3969/+P/DHFex0aEl+wYaNsV5p0DN5sOxp0DPuMVRGebRoSBHQ6aITs6qZ08sOpKud1BwFpy+QLvo7zSYXla1S2x1S3GqzkY0MkPiArn7ScPFyKxmrx4N4F/wG6CT0gQDS/tknGo3skPICho8dCio3tWi2bntbsKPh0FdLZo5fAWTy/CVX4AhcDhTGRpaHvTT6Xg72wvELjVcNKk2f1R+ws+HdeXNTCvfD3puVzv/nV7Dt4EAbppD9fX5hHBVX41Ask9AnoJcHg8PIH43D6EZUT+m5DgCAOOSd2J0XcrF/n1JFxPoo6RuJfJZ64ivjRY/W1Y0ANEy6gywbjqj6KBQR68W7r58AWfo3FTM7oIdoyEeyivj2R/JV1O4/zUmYu/P43z7BwQPSQOvkBrcklhdfAcC43zOJOsUqprPRVyyJeJnC1ArCwmCIxZtUzruvfUJbTNMNxa1vxNtF0hj7Hes3yuDmMZO9aGpcHkgLF0HQNNHEb5sPgOns1ALCwGCGdNrrtyRxCTjLGZW/A55L1ArCwmiMhpT1T5CcQga/JJbvmc5c1ALCwmiGKiaJmW/yf5CmLJZzMQC4sBwovJucQpDGCSi8bqBU6FnOW9QKwsJohsPG5vqhBXldugXKgT3n0RnbwZhlt7QUE851nVTV1nJ8PgpLG1lAOds7oXhpXB5JA4RSJTaEAvc4EipbpUMOK5yJuBWFgMEFx7KTBuDBHoZbiRYl245XOR9wKxspggosFtRz91nZ0s6BpCqOsqI5+LvBmIhcUEUdDyF7iKE4irHI33TutaTV9IJ28GYmExQMRgJFqdogd6mRspba7hsn0hnbwXiJXFBJGNWi9Tn3FRufRo1dYF+66IXt4Mw629nKOXunofJgxX2TkxXpyvK6HXQgZ5LxArk0lC8c0Yw9R5XuWYDAaaMcsIqJc3A7GwGCDqDJ+6OHWenawGnzDEGvn08l4gVhYTBJ4sSoxT59nJwWh2rua/6Qvp5M1ALCwGiIxvJitp6jw7WbhGrDUMpy+kk/cCsbKYIILBgy1p6jw7WRjpUCPFRjxndTMMC3uJoRiXZH4vriojTFLbcjWyucibYbi1FxS4v9S1mMQeQydzfJlSvqFzUffCsDKYHNQwLkinjrOTazIWX0OYJjxneTMQC4s/PHFt3rsseew4J7lIqWFzUyFneSsQS4sJIpmYSsk6gRjknFso/lTIWd4MxMJixn5YU7zj7tsBxCirq77jVMah7oVhZS8xYBDNuOs4YRjlY+1mLmTHJZ2lxQRRTEKDV8oEYpRTdG7B55A/FkQfWfBUY/hPPxHLbQz/vCqdQ02dx6lml4u2mWbrUg1qFdxHisGFlqLJBS9tDobvf5BYZ51UY24dBbxoNAqBA9aA0nzW9m0GN9igdVNjDDEkPSYqgljG+DIWNkmb+Y/OoPak4FtCGNUa34xLYfAWUqphvjkK44ApC6OhFDcbGGDso5wH/0mzhsSw/IyRXmu/Y2RsOoxn/L0vTPh6yKWAmZ7wl5fimu0Mxg8J1Yl5TZV5quqMGz6IxYMsDIfODjae5YKHEAqDpzMuGOQYfSdmi6yR9sLY3aqWmpUR70uO9LBafDNl1I3iGMcOP9yHUkN3GZUXcUHGt/dx6cINAPBSGN9ew5lzqIkeqeeCH4eajTantllBkmfYeyk1dJz9eCOOcTHnR1w8pRpBndsESk1rKnCGuc8go0LEdk08QlcsvCLOqzhvbZNhh0ZGmEbG94v35ZCzOIvmgMRdzO1pJq58KnxMPh+MyeUycMcb5eh+w/VyMLQN3DNKjC63GS3ck7YbLEaTel+rhAvl8NoqISe2xnKjyNSsZBhwLMLdHrBAc8ltCIgKrjVWOjD9UKhh85Lh8QSpaU2EaSR9tbF4hoOX0HYm4q2oNs5NQW4bXe7IL4igvhNFdy/uFiUvA+w+3I3gZez1SyP11ld/9hoviagWiydc0PhoC85+QUS1/4wR1fiEZpDt74AxCSqd3mRB6eSBVVfKOqL6+oVpi+VHB6ZFl7iyZKdte538iEjYkgzT3KBTTP4VCdofEVL9CREqmgqmRB7rQCc/IsU9uhn0FigtoO19dUj1p6OA1hkdWpwDQjr5ARTQo5oQUJpHNQkfG1IdHVr7Ugv4mHDqT8f0Za3LK99NZf93ufvXhVO/CQKtTbGXkcBFfTUAeFAdgMRdYxqDD3jRnkvqvgogfhMOha8RPNipKlzlB5Eo8KXhqQaFZ/9cLHX4bCS4UzZ7i0HKQOIqP4gEt/UmDK4iO7HnUoGnz4eCmy7Vc1fuyOKqPwpGtHQNMO7xdLzvw8jPBJUHKT2T1weVvxLu284wFI4cbZkyxkbr6qbvcU56UvnqfXNTQlMvsws7QFhZSwYYkNo2zzBAuCOviG2GYWEZ/W2UAR9vyh07y1zPX+A55L1ArCwmCLRXjN6QCcQdeYltMxAL0wiiGMs0FTpZPMjqWgqHqZCzvBmIhcUAweQZzsZpRXuSNVi3wNPUvTCs7CUGZovA+DhNGAb5Uh8mOlvWh5XFACGeU4Q6vReDqnD/ZEHnkPfCsLCXFJIJKcq0ot3LnM4PWk8W6Mro1M0wLAwGh8C5+FSmXLO9DIsl+5p9Y8JzlvcCsbKYIKJxqca2jSCuMueuc8u/MvE5y5uBWFhMEIVJdN20ot3LwozLbUVm5HORNwOxsBggopisTqcV7V5myqb618znIu8FYmUxQWTjvciUi7aXYYLjMZg3fC7yZiAWFgMEFwKn7bgXrZ7GoHV9sf95J++F4MZW2p+4zsol7hHBVU7G5ZgGMFdpMwALY7ks4YynIzR1mFe5rpx7NgQDml7eC8TKYoKIJvmSp+y0ncxMhvhVquvfXSmDvhmKhc1EUZhulXn3RhQXeagT10I2rhMLiwEiB5Zh/dRldjLuGQOrmqSjL6ST9wKxspggskk5pClvbS/zcEyRmvayL6STNwOxsBggODUtyU+NxFWVmrCyJkzsi+jkvTAs7CUFNYLyph1Yvczkkxobh57ORd0Mw8LgD0/JOqOMTho7z17GICKqbZ7kgOcibwViaTFBJJ4KbINMIK4y60CMNaJu5HORNwOxsBggHL4ZGNc5guhkpujkoSa3fM7yXiBWFhMEM6Uyff0EYpBzkRpoNxVyljcDsbCYIIpxzNObJhCDrD7VrVZTIWd5MxALiwGiZr1mLO7AYVDPM7IznR0nalf2koKajNtPYcIwyOcJ+onOg6btHxlGPi9FF84lcz6ah1gGez7imrnF66wSzMSDlTa9FkPJbeoFw8qSjxOAW1LtWJNMZ+Yy5qQDnkGqJTAldMFoq2ZdZrbAekR4ZLC1Vo+b4QnBtchojlddFsdEGcqMyb556pAzg4PrIaQphGDbEF9BO/K0pcCTF0INGYkp404JktHIIlr0ULNVV2rG6hiCO+6jmJAEY6Ca8d3ZcgydLD4UBlpzP3rglPshq0YfC0PLfcq5HvvKsSWA+8yI64IHGNqI0xtQEOuYlh3cbV31b3GFBaaNQeFRg7ExSpKWV9HG1IzUmo6bDWwGSl+OG9caJE0QLem3bb5bixBHg8Qw74Ay3FlmyB0D62ui9UNFXZAa1s/k3pq1nOVSXGjHfGkILeQa/14zNdia3Nuj3sh5FCW2Bblxw36uoewxo1K6GGvq/pwltQsy47xXfmiJ/o/nmMUwoT+n9SMD/mzdaBDrAeuqro5W2Ns0gDkxkv3YFMyjd5vKFoiUUCOzrZsF6MJZhqDnXDc8JEb/Nw/XMQS9NBc3osbVzP3V8dVSjs2lgdsFqhzrFHtL4YGH3456jYUpzq1T37J7S6ivDLtGHjhwzNvwXPiqAnVEbW47r/QIAZmbESs1EuCO/IIY9Duhh/cilVHyMirxw92YZ0atvzS8cX31Z6/xkhj0GvSMjodhSC8JQA+fMQA9Mel7YdD8wBC1Ay3ATeqQTh5AdaWsA9CvX2jt4uNi2NRxrtnqNNLq5EfEDZd6yrigRdBXhJ/HB8Sff0KC3FQkPkzr5J38AIIYvvEwiHqkxDNJ0afw85tYyE9HIVu4D+iVy9iYdPIjKPCQNna46G3cMxsZ7N3688kxMC9UjEX81B5c5AdgyB6eiUVp6ICf288xYoj2Thy+eu4zg7tQWobhj4jF/3RgX9bQvrKZyp5+3vnuXxeL/yYI6FnBdyxhRHCVX40A7nKHAP4eSgs2FZ4g9MJo/DchwZTjMXse1zOg6PQHsainSMGj1CROn4tCXwbkvw0MjIZycVZkgnHVHwUjxTqq4Wl5z+W8v4nI74LQ4VT1SF4fhP5Ktm86O4GmFc4tIzxGL8HiyWA0MaVnnWWeRlnlsZBDvsxP7AFiYTEdzgCHM4dpXfyevMa2F4iVac3zxujbTuvid+Uln81ALEwDCHg5dHGmFK2zrDUFylyGjolRtsCwspcY1PgsfkrQOsmamZP1hs5Z3gzEwmKA4KyahDytiU9yxhAp3PI5y3uBWFlMEJHHy01rf53KZFHF1nm8vohO3gzDrb081I5FZDt5/r0sGBdFX3NZDHQu6l4YVgaTQ90nmqY18V5mrpZY59ZHOmd1MwwLe4mhMDWIn9+KTmZml2TrWY0jnYu8GYiFxZx34voEXIKp2+zkaFhKmPl08l4gVhYTBI82DmFKztrL3AQbXV2i6gvp5M1ALCwGiOR5BrGdVsQ7mdOzse5PGfj08l4gVhYTROIptGnmcFEVb0AoNYF5X0Qnb4bh1l5Q4CJomVIPfTPIwcQSYt2715XRqXthWBlMDpHp0XKaOs5OFh4iHesepb6QTt4MxMJigigm2ssJxVcQV5kJzHkq8Q2fi7wZiIXFAMF17MjvjiA6mQlpbXblhs9F3gvEymKCYCRATFN61l5mHCHzLN7yOcubgVhYDBCFqfvU56nLGOXL4HssZM/B98piguCh9zlPbeWgFnE1VmIq4ixvhuHWXq5mOoOxQpiys07ypToMZWxZG5YGk0M0yXk7JWe9Ky+pbQZiYRpBFHwQtTJZPMptNnIuY8M5yqW9wOBqCJvYMQp7lo/lirmQHVcxlhYTRIZvWDPJjiBG+QxizWczEAuLAcIzvj5HN3ac9+Q1tr1ArEwjCB71YucKcUdd0tkMw61loCDOqHfqp47zjryksxeGlWXkkIxVET/1kJN89BdTGY/pLx4ZjD6tRyt6eVcXKBiHm22LrLWemdmPyecSrXjX4nClnvKiAWWEFj4nRl1qWcA1KB9A9HVQgbbRHrNTHIbbxPiqiLGGr0nANToTUEKss5jOe1/TXStDwq1PWmVc5CgaskYMYOt+c1uCtrnxyJw9QV3dcx6UMcpVDjDG8lg7hrRHLYccjWTmSWfYdMGz0za7mJjXREuNvfZOWnA9ZVyPI0QmVEfJIR9zbYKxNMPUmcfbtt0nuDljbYL/nJiOu4Ssh5qSz5lRERlDTzzcdsmCXiQXOwWkU8d1eESh43kJ2dk2k5HwiMUyxzcTjKurZwYoc5qDSQrMGI46k2w65BI8tw2QPBppd0yOxVIsl98Zos98DVXmY401mTFGQujn67lOlIsDeyVBPuu2NJVwU5xfrDPPXmsItyZaJq74tt0A1bheUB0eq/qWJj+HII2fKmi7kGpF4+GDegzMgSaGYwkoiLRhKpdGYwptmBpKbhbmVPNNHMN4l7RunsVrxWlQe6wflpirzC6blfWa+k3rm8qjtZnm8bnXWn1Lh3VHfkF0+J1guHthxCh5GSf34W5AMuPJXxpwt776s9d4SXQ4MPGBRGbTZE7nFwSIp88YII52CxXT2yk7NVo2a/LU713EgVNXwjo4/PKF2my/qiO4E1pWUFPF2jCtxHfyA6JZ4fWh8WbzEPBif6bw8E/IUIXZcGXKDtTJj2AYebYCS7M86eHV8eGfDgN8KceNWDItTvX6I0AULtugNFSVLK+PEP+UIAKtRLeVJhBX/QEg2HOy/0Rx6DV/Mom7QeJFLKd2HXfeMWPwRwSJf8J37QWN7StD77kF6nrvrwsRfxMAdKTgJ9UQ8QuAq/hqAJp6ANy7yL4vcavgfQTuLZuaDgKcOOfxCkgP4So+CEKGow2PFE4+D7R5Nkr+s1DAEMJgOM3dJx2GTn0QB+c4HPQeQzF1z4GQzwWCR5Rnnrk0gLiqjwIRMFyx+A/GBPk5EOFzgVCYHjHyHThcxEdhSHXXMgZeytHTfQzx7h4BODQ9jdfvEXgl1jedNCpOMMQpYQpUKC7X2jROrncqfiU8Va2q1yI6+TJptAeGW3tBwWOYEH2aMu7ek5fM9sKwsowcEvfH+ylIoZfFBK2b6vsiLuJmEBbWcgSKBvbIC9BD6OT+pRjYbPpSrCwmiMiZwDBl2+3lYOiY1MP4+kI6eTMQC4sJorDzslO23V7OTCbiamqKvpBO3gzEwmKA4IGKGOpNq+29HI1q8WXCc1X3wrCylxgw1EneT7EIvZyNzSimTHQ6eTMQC4sBIuID3vNpbrqT4f5JllDT0nSF9PJeIFYWEwRT/sSa/2YAcZEjOgfLKbSJTydvBmJhMUAkZ5LDCG3qPK9yTPgdSp75dPJeIFYWEwRuKdXFqxHEReZSmQulruF1hfTyZiAWFnMyGmX4tjLbg7jKSZhaNdR8Sj2fTt4LxMpiguAB1q5Mc4WdPCyxdqUM+mYoFjYTRWGisTiFKnSy8lDoID6NhHp5MxALiwEiixGNbkq+28ncIlFyyy7bFdLLe4FYWUwQapTRFFMHepUjfMjYdoh0ZXTqZhgW9gIDl5iYVXjqPq8yo1FsSnU7QE+nk/cCsbKYIFDB4SlOuXc7mROLJdq617bn08mbgVhYzBlUa41mjKzH/rPXYbPz2nzsAdBZ3QrE2uJKIjKVIv5hJnHV63Y669JEqNd3g7EwusIoJuSgscwwrjrDxWKLbRvK6fTdYCyMruv8YrIkmRLxDjrGF8XmtIB00TeDsTK6wsjG8VifPMO46pHxK8XrDKnTd4OxMJowvDdRMM70E4xOD8wiGOuS7VBOp28GY2V0hZGYqmuM6P1m1GuoY3AyQ+r03WAsjCYMcXi+Hh3EBKPTL+saE6IdVzvWBlcQkZuvJc/daqcPtWIAtGutWBldYTDeIpY8d6t39SW83WAsjKtRY2gCC3rJuVvt9G7NayjngWthj9xVMK5h+yx8cm0ZvBRmX6y5awCzruR4MTEXPV56QWdwWfJLtI23rb40MaMX5XEPdU+BBpfr3IVgPGJTjWYP8DlyS1pfhOVZJkxCn4u7Ca0QGC4lu+Nkunr81Dc1JFZxS1xIYXpzr9KWnzL3P3ipafJTptnHskspgFkLSfhWXa0NzpSYpSVdT2jT2wQsISieW3WE4AWVVgbzMWQfaqZ9HwCp2oJbzfgnrvCpwT/70IrGBzxFfhsUky1tJo9JHb1nxHtk6H7yNci9xAJmtvDgMeVOBF9bjzoBKplbGzL7HKl7AUpCFUHV9iijmJyj9/X2ODVoa878RBdfvW9loFomsaluPiii3h1qcXDxhDOKwaMVl2OiMeLmbDjhL1Hn2ypmgj8ojkEgCWa1N6rJOasL6aTO2IQbbdO23HMgPINYmTrf6VE26kKM3uaaNRVPpC2IKSP5GWFyci5x80A7lIC64q6YwNdbPvfSFhKViebrwd8OPXHyKaRyzIcx36aGmjfUuxwbcZ4GEHE1vEHecXtwDG1aDVXMRfw/rpvrgyutfO4V4KkL0IEuWmdb+VpXZ2A50APpseme008SUdApC7da+NimaPD+JYmZiaRR18Gj1gqm89fIk6JSfV1CblMWMIS5hQPD+/D+5br/hDM6hcc/RD5RySGUNtETuemDaUBRWVA/pCZaK8zyn5Rj2xiZgky9HtMh3B1j68EMLmkLwyvM/l+49a3uPnHpmEQqlrtBcvHcNiOac6tbxaN7dwW2RVRJrxrbuBqVNYU21naK+l5F1OWcHQ+YRc3HiMK1dtCyZcs+100poYgPx7ADVRGedmhvW2mZ+yFzLzdjX+v7LbjX5nM4BhPamkiqVtb6dPBI0EJZlFqbn2xZs6uMRhNDGSftgAL0yuncXTvloae1abPHCRTQM9oaCS3Ix3uYX24bd1zIuef0F+wsuRNBe28PAkpeBNcOMWXjt18Yobu+7jPlv2RHCZ4tqwBqRGFI80t2lOTFjpKuZBEUharGuGBXcr3TrszQlXkOl37/7tsfriHTp9+///6H797/948/vP/zt6c//Pm701df//D+r1+1jz9++3X943c/f+ImKbSXEU0E2q+fvfuXn3NHlmOTUdXTz/4N9/h0iYR7+j/F0H/WCmVuZHN0cmVhbQplbmRvYmoKMTIgMCBvYmoKODQ4OAplbmRvYmoKMTAgMCBvYmoKWyBdCmVuZG9iagoxNyAwIG9iago8PCAvRmlsdGVyIC9GbGF0ZURlY29kZSAvTGVuZ3RoIDIzNSA+PgpzdHJlYW0KeJw1UUluADEIu+cV/kClsCfvmarqof3/tYZRLwMD2Ngk78FGJD7EkO4oV3zK6jTL8DtZ5MXPSuHkvYgKpCrCCmkHz3JWMwyeG5kClzPxWWY+mRY7FlBNxHF25DSDQYhpXEfL6TDTPOgJuT4YcWOnWa5iSOvdUr2+1/KfKspH1t0st07Z1ErdomfsSVx2Xk9taV8YdRQ3BZEOHzu8B/ki5iwuOpFu9psph5WkITgtgB+JoVTPDq8RJn5mJHjKnk7vozS89kHT9b17QUduJmQqt1BGKp6sNMaMofqNaCap7/+BnvW9vv4AQ01UuQplbmRzdHJlYW0KZW5kb2JqCjE4IDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggMjQ3ID4+CnN0cmVhbQp4nE1RSW7EMAy7+xX8wACWrMV5T4pBD+3/ryUdFO3BECNLXOLuxEQWXrZQ10KH48NGXgmbge+D1pz4GrHiP9pGpJU/VFsgEzFRJHRRNxr3SDe8CtF+pIJXqvdY8xF3K81bOnaxv/fBtOaRKqtCPOTYHNlIWtdE0fE9tN5zQ3TKIIE+NyEHRGmOXoWkv/bDdW00u7U2syeqg0emhPJJsxqa0ylmyGyox20qVjIKN6qMivtURloP8jbOMoCT44QyWk92rCai/NQnl5AXE3HCLjs7FmITCxuHtB+VPrH8fOvN+JtpraWQcUEiNMWl32e8x+d4/wCVT1wmCmVuZHN0cmVhbQplbmRvYmoKMTkgMCBvYmoKPDwgL0ZpbHRlciAvRmxhdGVEZWNvZGUgL0xlbmd0aCA2MSA+PgpzdHJlYW0KeJwzNTVXMFCwtAASpqZGCuZGlgophlxAPoiVy2VoaQ5m5YBZFsZABkgZnGEApMGac2B6crgyuNIAyxUQzAplbmRzdHJlYW0KZW5kb2JqCjIwIDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggMjMyID4+CnN0cmVhbQp4nD2QS3IEIQxD95xCRwB/4TydSs2i5/7byO6ZbJCqwPITcRwTZ/OICKQc/KxhZlATvIeFQ9VgO6DrwGdATuAaLnQpcKPahHN8ncObCpq4h8dstUisneVMIeowJkls6EnINs5ocuOc3KpU3kxrvcbim3J3u8pr2pbCvYfK+jjjVDmrKmuRNhGZRWsbwUYe7LDPo6toy1kq3DeMTV0TlcObxe5Z3cniiu+vXOPVLMHM98O3vxwfV93oKsfYyoTZUpPm0jn1r5bR+nC0i4V64Ud7JkhwdasgVaXWztpTev1T3CT6/QP0wVcdCmVuZHN0cmVhbQplbmRvYmoKMjEgMCBvYmoKPDwgL0ZpbHRlciAvRmxhdGVEZWNvZGUgL0xlbmd0aCAxNTYgPj4Kc3RyZWFtCnicNY9LDsMwCET3PsVcoBJfQ86Tquoivf+2YCeSEU/2zBhCBYQMvFgxzRFy4M2jbpp+g3MuuhZJ1U2UVQR2hkiCOXAO8YlUKAnmhFbVOYdVQIGF96uT3nJXXgFuO3D1bEfT/vYZapOE3cSRmFJ+Cnjd+tE2iYqGea6FeoDuNVgpmoSsBeyxDcy0EmrfDqzWyvPZ/xrf8fkDYBM2+AplbmRzdHJlYW0KZW5kb2JqCjIyIDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggMzA3ID4+CnN0cmVhbQp4nD2SS24DMQxD9z6FLhDA+tme86Qoupjef9snJemKHNkWRWqWukxZUx6QNJOEf+nwcLGd8jtsz2Zm4Fqil4nllOfQFWLuonzZzEZdWSfF6oRmOrfoUTkXBzZNqp+rLKXdLngO1yaeW/YRP7zQoB7UNS4JN3RXo2UpNGOq+3/Se/yMMuBqTF1sUqt7HzxeRFXo6AdHiSJjlxfn40EJ6UrCaFqIlXdFA0Hu8rTKewnu295qyLIHqZjOOylmsOt0Ui5uF4chHsjyqPDlo9hrQs/4sCsl9EjYhjNyJ+5oxubUyOKQ/t6NBEuPrmgh8+CvbtYuYLxTOkViZE5yrGmLVU73UBTTucO9DBD1bEVDKXOR1epfw84La5ZsFnhK+gUeo90mSw5W2duoTu+tPNnQ9x9a13QfCmVuZHN0cmVhbQplbmRvYmoKMjMgMCBvYmoKPDwgL0ZpbHRlciAvRmxhdGVEZWNvZGUgL0xlbmd0aCAyNDQgPj4Kc3RyZWFtCnicRZFNcgUhCIT3nqIv8KrkVz3PpFJZTO6/Dc28JCtaheYD0wITR/ASQ+yJlRMfMnwv6DJ8tzI78DrZmXBPuG5cw2XDM2Fb4DsqyzteQ3e2Uj+doarvGjneLlI1dGVkn3qhmgvMkIiuEVl0K5d1QNOU7lLhGmxbghT1SqwnnaA06BHK8HeUa3x1E0+vseRUzSFaza0TGoqwbHhB1MkkEbUNiyeWcyFR+aobqzouYJMl4vSA3KCVZnx6UkkRMIN8rMlozAI20JO7ZxfGmkseRY5XNJiwO0k18ID34ra+9zZxj/MX+IV33/8rDn3XAj5/AEv+XQYKZW5kc3RyZWFtCmVuZG9iagoyNCAwIG9iago8PCAvRmlsdGVyIC9GbGF0ZURlY29kZSAvTGVuZ3RoIDIzMiA+PgpzdHJlYW0KeJw1UUluxDAMu/sV/MAA1u68J8Wgh/b/11LKFAhAJba4JWJjIwIvMfg5iNz4kjWjJn5nclf8LE+FR8Kt4EkUgZfhXnaCyxvGZT8OMx+8l1bOpMaTDMhFNj08ETLYJRA6MLsGddhm2om+IeGzI1LNRpbT1xL00ioEylO23+mCEm2r+nP7rAtt+9oTTnZ76knlE4jnlqzAZeMVk8VYBj1RuUsxfZDqbKEnobwon4NsPmqIRJcoZ+CJwcEo0A7sue1n4lUhaF3dp21jqEZKx9O/DU1Nkgj5RAlntjTuFv5/z72+1/sPTiFUEQplbmRzdHJlYW0KZW5kb2JqCjI1IDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggMjMxID4+CnN0cmVhbQp4nDVPOZIEIQzLeYU+MFUY20C/p6e2Ntj5f7qSmU6Q8CHJ0xMdmXiZIyOwZsfbWmQgZuBTTMW/9rQPE6r34B4ilIsLYYaRcNas426ejhf/dpXPWAfvNviKWV4Q2MJM1lcWZy7bBWNpnMQ5yW6MXROxjXWtp1NYRzChDIR0tsOUIHNUpPTJjjLm6DiRJ56L7/bbLHY5fg7rCzaNIRXn+Cp6gjaDoux57wIackH/Xd34HkW76CUgGwkW1lFi7pzlhF+9dnQetSgSc0KaQS4TIc3pKqYQmlCss6OgUlFwqT6n6Kyff+VfXC0KZW5kc3RyZWFtCmVuZG9iagoyNiAwIG9iago8PCAvRmlsdGVyIC9GbGF0ZURlY29kZSAvTGVuZ3RoIDI0OSA+PgpzdHJlYW0KeJw9UDuORCEM6zmFL/Ak8iNwHkarLWbv364DmilQTH62MyTQEYFHDDGUr+MlraCugb+LQvFu4uuDwiCrQ1IgznoPiHTspjaREzodnDM/YTdjjsBFMQac6XSmPQcmOfvCCoRzG2XsVkgniaoijuozjimeKnufeBYs7cg2WyeSPeQg4VJSicmln5TKP23KlAo6ZtEELBK54GQTTTjLu0lSjBmUMuoepnYifaw8yKM66GRNzqwjmdnTT9uZ+Bxwt1/aZE6Vx3QezPictM6DORW69+OJNgdNjdro7PcTaSovUrsdWp1+dRKV3RjnGBKXZ38Z32T/+Qf+h1oiCmVuZHN0cmVhbQplbmRvYmoKMjcgMCBvYmoKPDwgL0ZpbHRlciAvRmxhdGVEZWNvZGUgL0xlbmd0aCAzOTUgPj4Kc3RyZWFtCnicPVJLbsVACNvnFFyg0vCbz3lSVd28+29rQ1KpKryJMcYwfcqQueVLXRJxhcm3Xq5bPKZ8LltamXmIu4uNJT623JfuIbZddC6xOB1H8gsynSpEqM2q0aH4QpaFB5BO8KELwn05/uMvgMHXsA244T0yQbAk5ilCxm5RGZoSQRFh55EVqKRQn1nC31Hu6/cyBWpvjKULYxz0CbQFQm1IxALqQABE7JRUrZCOZyQTvxXdZ2IcYOfRsgGuGVRElnvsx4ipzqiMvETEPk9N+iiWTC1Wxm5TGV/8lIzUfHQFKqk08pTy0FWz0AtYiXkS9jn8SPjn1mwhhjpu1vKJ5R8zxTISzmBLOWChl+NH4NtZdRGuHbm4znSBH5XWcEy0637I9U/+dNtazXW8cgiiQOVNQfC7Dq5GscTEMj6djSl6oiywGpq8RjPBYRAR1vfDyAMa/XK8EDSnayK0WCKbtWJEjYpscz29BNZM78U51sMTwmzvndahsjMzKiGC2rqGautAdrO+83C2nz8z6KJtCmVuZHN0cmVhbQplbmRvYmoKMjggMCBvYmoKPDwgL0ZpbHRlciAvRmxhdGVEZWNvZGUgL0xlbmd0aCAxMzYgPj4Kc3RyZWFtCnicTY9BDgMxCAPveYWfQCBAeM9WVQ/b/19L2HbTCx7JgGxRBoElh3iHG+HR2w/fRTYVZ+OcX1IpYiGYT3CfMFMcjSl38mOPgHGUaiynaHheS85NwxctdxMtpa2XkxlvuO6X90eVbZENRc8tC0LXbJL5MoEHfBiYR3XjaaXH3fZsr/b8AM5sNEkKZW5kc3RyZWFtCmVuZG9iagoyOSAwIG9iago8PCAvRmlsdGVyIC9GbGF0ZURlY29kZSAvTGVuZ3RoIDI0OSA+PgpzdHJlYW0KeJxNUUmKAzAMu+cV+kAhXpO8p0OZQ+f/18oOhTkECa+Sk5aYWAsPMYQfLD34kSFzN/0bfqLZu1l6ksnZ/5jnIlNR+FKoLmJCXYgbz6ER8D2haxJZsb3xOSyjmXO+Bx+FuAQzoQFjfUkyuajmlSETTgx1HA5apMK4a2LD4lrRPI3cbvtGZmUmhA2PZELcGICIIOsCshgslDY2EzJZzgPtDckNWmDXqRtRi4IrlNYJdKJWxKrM4LPm1nY3Qy3y4Kh98fpoVpdghdFL9Vh4X4U+mKmZdu6SQnrhTTsizB4KpDI7LSu1e8TqboH6P8tS8P3J9/gdrw/N/FycCmVuZHN0cmVhbQplbmRvYmoKMzAgMCBvYmoKPDwgL0ZpbHRlciAvRmxhdGVEZWNvZGUgL0xlbmd0aCA5NCA+PgpzdHJlYW0KeJxFjcERwCAIBP9UQQkKCtpPJpOH9v+NEDJ8YOcO7oQFC7Z5Rh8FlSZeFVgHSmPcUI9AveFyLcncBQ9wJ3/a0FScltN3aZFJVSncpBJ5/w5nJpCoedFjnfcLY/sjPAplbmRzdHJlYW0KZW5kb2JqCjMxIDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggMzQxID4+CnN0cmVhbQp4nEVSS25EMQjbv1NwgUjhl5DztKq6mN5/W5tM1c3gCWBseMtTpmTKsLklIyTXlE99IkOspvw0ciQipvhJCQV2lY/Ha0usjeyRqBSf2vHjsfRGptkVWvXu0aXNolHNysg5yBChnhW6snvUDtnwelxIuu+UzSEcy/9QgSxl3XIKJUFb0HfsEd8PHa6CK4JhsGsug+1lMtT/+ocWXO9992LHLoAWrOe+wQ4AqKcTtAXIGdruNiloAFW6i0nCo/J6bnaibKNV6fkcADMOMHLAiCVbHb7R3gCWfV3oRY2K/StAUVlA/MjVdsHeMclIcBbmBo69cDzFmXBLOMYCQIq94hh68CXY5i9Xroia8Al1umQvvMKe2ubnQpMId60ADl5kw62ro6iW7ek8gvZnRXJGjNSLODohklrSOYLi0qAeWuNcN7HibSOxuVff7h/hnC9c9usXS+yExAplbmRzdHJlYW0KZW5kb2JqCjMyIDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggMTY0ID4+CnN0cmVhbQp4nEWQx3EFMQxD76oCJTCACvWsx/MP6/6vhvTTQXoYQgxiT8KwXFdxYXTDj7ctMw1/RxnuxvoyY7zVWCAn6AMMkYmr0aT6dsUZqvTk1WKuo6JcLzoiEsyS46tAI3w6sseTtrYz/XReH+wh7xP/KirnbmEBLqruQPlSH/HUj9lR6pqhjyorax5q2leEXRFK2z4upzJO3b0DWuG9las92u8/HnY68gplbmRzdHJlYW0KZW5kb2JqCjMzIDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggNzIgPj4Kc3RyZWFtCnicMzK3UDBQsDQBEoYWJgrmZgYKKYZcQL6piblCLhdIDMTKAbMMgLQlnIKIZ4CYIG0QxSAWRLGZiRlEHZwBkcvgSgMAJdsWyQplbmRzdHJlYW0KZW5kb2JqCjM0IDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggNDcgPj4Kc3RyZWFtCnicMzK3UDBQsDQBEoYWJgrmZgYKKYZclhBWLhdMLAfMAtGWcAoinsGVBgC5Zw0nCmVuZHN0cmVhbQplbmRvYmoKMzUgMCBvYmoKPDwgL0ZpbHRlciAvRmxhdGVEZWNvZGUgL0xlbmd0aCAyNTggPj4Kc3RyZWFtCnicRZFLcgQgCET3noIjgPzkPJNKZTG5/zYNzmQ2dpeo/YRKI6YSLOcUeTB9yfLNZLbpdzlWOxsFFEUomMlV6LECqztTxJlriWrrY2XkuNM7BsUbzl05qWRxo4x1VHUqcEzPlfVR3fl2WZR9Rw5lCtiscxxs4MptwxgnRput7g73iSBPJ1NHxe0g2fAHJ419lasrcJ1s9tFLMA4E/UITmOSLQOsMgcbNU/TkEuzj43bngWBveRFI2RDIkSEYHYJ2nVz/4tb5vf9xhjvPtRmuHO/id5jWdsdfYpIVcwGL3Cmo52suWtcZOt6TM8fkpvuGzrlgl7uDTO/5P9bP+v4DHilm+gplbmRzdHJlYW0KZW5kb2JqCjM2IDAgb2JqCjw8IC9CQm94IFsgLTEwMjEgLTQ2MyAxNzk0IDEyMzMgXSAvRmlsdGVyIC9GbGF0ZURlY29kZSAvTGVuZ3RoIDM5Ci9TdWJ0eXBlIC9Gb3JtIC9UeXBlIC9YT2JqZWN0ID4+CnN0cmVhbQp4nOMyNDBTMDY1VcjlMjc2ArNywCwjcyMgCySLYEFkM7jSABXzCnwKZW5kc3RyZWFtCmVuZG9iagozNyAwIG9iago8PCAvRmlsdGVyIC9GbGF0ZURlY29kZSAvTGVuZ3RoIDE2MyA+PgpzdHJlYW0KeJxFkDsSAyEMQ3tOoSP4IwM+z2YyKTb3b2PYbFLA01ggg7sTgtTagonogoe2Jd0F760EZ2P86TZuNRLkBHWAVqTjaJRSfbnFaZV08Wg2cysLrRMdZg56lKMZoBA6Fd7touRypu7O+UNw9V/1v2LdOZuJgcnKHQjN6lPc+TY7orq6yf6kx9ys134r7FVhaVlLywm3nbtmQAncUznaqz0/Hwo69gplbmRzdHJlYW0KZW5kb2JqCjM4IDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggMjE4ID4+CnN0cmVhbQp4nD1QuY0EMQzLXYUaWMB67alnFotLpv/0SPn2ItEWRVIqNZmSKS91lCVZU946fJbEDnmG5W5kNiUqRS+TsCX30ArxfYnmFPfd1ZazQzSXaDl+CzMqqhsd00s2mnAqE7qg3MMz+g1tdANWhx6xWyDQpGDXtiByxw8YDMGZE4siDEpNBv+uco+fXosbPsPxQxSRkg7mNf9Y/fJzDa9TjyeRbm++4l6cqQ4DERySmrwjXVixLhIRaTVBTc/AWi2Au7de/hu0I7oMQPaJxHGaUo6hv2twpc8v5SdT2AplbmRzdHJlYW0KZW5kb2JqCjM5IDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggODMgPj4Kc3RyZWFtCnicRYy7DcAwCER7pmAEfib2PlGUwt6/DRAlbrgn3T1cHQmZKW4zw0MGngwshl1xgfSWMAtcR1COneyjYdW+6gSN9aZS8+8PlJ7srOKG6wECQhpmCmVuZHN0cmVhbQplbmRvYmoKNDAgMCBvYmoKPDwgL0ZpbHRlciAvRmxhdGVEZWNvZGUgL0xlbmd0aCA1MSA+PgpzdHJlYW0KeJwzNrRQMFAwNDAHkkaGQJaRiUKKIRdIAMTM5YIJ5oBZBkAaojgHriaHK4MrDQDhtA2YCmVuZHN0cmVhbQplbmRvYmoKNDEgMCBvYmoKPDwgL0ZpbHRlciAvRmxhdGVEZWNvZGUgL0xlbmd0aCAxNjAgPj4Kc3RyZWFtCnicRZA5EgMxCARzvYInSFyC96zLtcH6/6kH1kei6QI0HLoWTcp6FGg+6bFGobrQa+gsSpJEwRaSHVCnY4g7KEhMSGOSSLYegyOaWLNdmJlUKrNS4bRpxcK/2VrVyESNcI38iekGVPxP6lyU8E2Dr5Ix+hhUvDuDjEn4XkXcWjHt/kQwsRn2CW9FJgWEibGp2b7PYIbM9wrXOMfzDUyCN+sKZW5kc3RyZWFtCmVuZG9iago0MiAwIG9iago8PCAvRmlsdGVyIC9GbGF0ZURlY29kZSAvTGVuZ3RoIDMzNCA+PgpzdHJlYW0KeJwtUktyxSAM23MKXaAz+AfkPOl0uni9/7aSk0VGDmD0MeWGiUp8WSC3o9bEt43MQIXhr6vMhc9I28g6iMuQi7iSLYV7RCzkMcQ8xILvq/EeHvmszMmzB8Yv2XcPK/bUhGUh48UZ2mEVx2EV5FiwdSGqe3hTpMOpJNjji/8+xXMtBC18RtCAX+Sfr47g+ZIWafeYbdOuerBMO6qksBxsT3NeJl9aZ7k6Hs8Hyfau2BFSuwIUhbkzznPhKNNWRrQWdjZIalxsb479WErQhW5cRoojkJ+pIjygpMnMJgrij5wecioDYeqarnRyG1Vxp57MNZuLtzNJZuu+SLGZwnldOLP+DFNmtXknz3Ki1KkI77FnS9DQOa6evZZZaHSbE7ykhM/GTk9Ovlcz6yE5FQmpYlpXwWkUmWIJ2xJfU1FTmnoZ/vvy7vE7fv4BLHN8cwplbmRzdHJlYW0KZW5kb2JqCjQzIDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggNzAgPj4Kc3RyZWFtCnicMzM2UzBQsDACEqamhgrmRpYKKYZcQD6IlcsFE8sBs8wszIEsIwuQlhwuQwtjMG1ibKRgZmIGZFkgMSC6MrjSAJiaEwMKZW5kc3RyZWFtCmVuZG9iago0NCAwIG9iago8PCAvRmlsdGVyIC9GbGF0ZURlY29kZSAvTGVuZ3RoIDMyMCA+PgpzdHJlYW0KeJw1UktuBTEI288puECl8E/O86qqi777b2sTvRVMMGDjKS9Z0ku+1CXbpcPkWx/3JbFC3o/tmsxSxfcWsxTPLa9HzxG3LQoEURM9WJkvFSLUz/ToOqhwSp+BVwi3FBu8g0kAg2r4Bx6lMyBQ50DGu2IyUgOCJNhzaXEIiXImiX+kvJ7fJ62kofQ9WZnL35NLpdAdTU7oAcXKxUmgXUn5oJmYSkSSl+t9sUL0hsCSPD5HMcmA7DaJbaIFJucepSXMxBQ6sMcCvGaa1VXoYMIehymMVwuzqB5s8lsTlaQdreMZ2TDeyzBTYqHhsAXU5mJlgu7l4zWvwojtUZNdw3Duls13CNFo/hsWyuBjFZKAR6exEg1pOMCIwJ5eOMVe8xM5DsCIY52aLAxjaCaneo6JwNCes6VhxsceWvXzD1TpfIcKZW5kc3RyZWFtCmVuZG9iago0NSAwIG9iago8PCAvRmlsdGVyIC9GbGF0ZURlY29kZSAvTGVuZ3RoIDE4ID4+CnN0cmVhbQp4nDM2tFAwgMMUQ640AB3mA1IKZW5kc3RyZWFtCmVuZG9iago0NiAwIG9iago8PCAvRmlsdGVyIC9GbGF0ZURlY29kZSAvTGVuZ3RoIDEzMyA+PgpzdHJlYW0KeJxFj0sOBCEIRPecoo7Axx/ncTLphXP/7YCdbhNjPYVUgbmCoT0uawOdFR8hGbbxt6mWjkVZPlR6UlYPyeCHrMbLIdygLPCCSSqGIVCLmBqRLWVut4DbNg2yspVTpY6wi6Mwj/a0bBUeX6JbInWSP4PEKi/c47odyKXWu96ii75/pAExCQplbmRzdHJlYW0KZW5kb2JqCjQ3IDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggMzQwID4+CnN0cmVhbQp4nDVSOW4EMQzr/Qp9IIBu2+/ZIEiR/L8NqdkUA3F0UpQ7WlR2y4eFVLXsdPm0ldoSN+R3ZYXECcmrEu1ShkiovFYh1e+ZMq+3NWcEyFKlwuSk5HHJgj/DpacLx/m2sa/lyB2PHlgVI6FEwDLFxOgals7usGZbfpZpwI94hJwr1i3HWAVSG9047Yr3oXktsgaIvZmWigodVokWfkHxoEeNffYYVFgg0e0cSXCMiVCRgHaB2kgMOXssdlEf9DMoMRPo2htF3EGBJZKYOcW6dPTf+NCxoP7YjDe/OirpW1pZY9I+G+2Uxiwy6XpY9HTz1seDCzTvovzn1QwSNGWNksYHrdo5hqKZUVZ4t0OTDc0xxyHzDp7DGQlK+jwUv48lEx2UyN8ODaF/Xx6jjJw23gLmoj9tFQcO4rPDXrmBFUoXa5L3AalM6IHp/6/xtb7X1x8d7YDGCmVuZHN0cmVhbQplbmRvYmoKNDggMCBvYmoKPDwgL0ZpbHRlciAvRmxhdGVEZWNvZGUgL0xlbmd0aCAyNTEgPj4Kc3RyZWFtCnicLVFJcgNBCLvPK/SEZqffY5crh+T/1wjKBwYNi0B0WuKgjJ8gLFe85ZGraMPfMzGC3wWHfivXbVjkQFQgSWNQNaF28Xr0HthxmAnMk9awDGasD/yMKdzoxeExGWe312XUEOxdrz2ZQcmsXMQlExdM1WEjZw4/mTIutHM9NyDnRliXYZBuVhozEo40hUghhaqbpM4EQRKMrkaNNnIU+6Uvj3SGVY2oMexzLW1fz004a9DsWKzy5JQeXXEuJxcvrBz09TYDF1FprPJASMD9bg/1c7KT33hL584W0+N7zcnywlRgxZvXbkA21eLfvIjj+4yv5+f5/ANfYFuICmVuZHN0cmVhbQplbmRvYmoKNDkgMCBvYmoKPDwgL0ZpbHRlciAvRmxhdGVEZWNvZGUgL0xlbmd0aCAxNzQgPj4Kc3RyZWFtCnicTZBJDkMhDEP3nMIXqIQzwOc8v6q6aO+/rUMHdYH85CBwPDzQcSQudGTojI4rmxzjwLMgY+LROP/JuD7EMUHdoi1Yl3bH2cwSc8IyMQK2RsnZPKLAD8dcCBJklx++wCAiXY/5VvNZk/TPtzvdj7q0Zl89osCJ7AjFsAFXgP26x4FLwvle0+SXKiVjE4fygeoiUjY7oRC1VOxyqoqz3ZsrcBX0/NFD7u0FtSM83wplbmRzdHJlYW0KZW5kb2JqCjUwIDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggNzUgPj4Kc3RyZWFtCnicM7U0UjBQMDYAEqZmRgqmJuYKKYZcQD6IlctlaGQKZuVwGVmaKVhYABkmZuZQIZiGHC5jU3OgAUBFxqZgGqo/hyuDKw0AlZAS7wplbmRzdHJlYW0KZW5kb2JqCjUxIDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggODkgPj4Kc3RyZWFtCnicNYy7DYAwDER7T+ER4r/ZByEK2L/FSXBj392TXlLiQOU6EY6mgSdB9ZleINnpAVZF4lFJzP9NvalFU8+m7atNBCczjvV1HKia03rQWihtkxbecH0AnB3tCmVuZHN0cmVhbQplbmRvYmoKNTIgMCBvYmoKPDwgL0ZpbHRlciAvRmxhdGVEZWNvZGUgL0xlbmd0aCAxNDEgPj4Kc3RyZWFtCnicPY/BDsMwCEPv+Qr/QKTYKaF8T6dqh+7/ryNLuwt6AmOMhdDQG6qaw4Zgm+PF0iVUa/gUxUAlN8iZYA6lpNIdR5F6YjgYXB60G47isej6EbuSZn3QxkK6JWiAe6xTadymcRPEHTUF6inqnKO8ELmfqWfYNJLdNLOSc7gNv3vPU9f/p6u8y/kFvXcu/gplbmRzdHJlYW0KZW5kb2JqCjUzIDAgb2JqCjw8IC9GaWx0ZXIgL0ZsYXRlRGVjb2RlIC9MZW5ndGggMjE1ID4+CnN0cmVhbQp4nDVROQ4DIQzs9xX+QCSML3hPoijN/r/NjNFWHsFchrSUIZnyUpOoIeVTPnqZLpy63NfMajTnlrQtc4C4trwvrZLAiWaIg8FpmLgBmjwBQ9fRqFFDFx7Q1KVTKLDcBD6Kt24P3WO1gZe2IeeJIGIoGSxBzalFExZtzyekNb9eixvel+3dyFOlxpYYgQYBVjgc1+jX8JU9TybRdBUy1Ks1yxgJE0UiPPmOptUT61o00jIS1MYRrGoDvDv9ME4AABNxywJkn0qUs+TEb7H0swZX+v4Bn0dUlgplbmRzdHJlYW0KZW5kb2JqCjE1IDAgb2JqCjw8IC9CYXNlRm9udCAvRGVqYVZ1U2FucyAvQ2hhclByb2NzIDE2IDAgUgovRW5jb2RpbmcgPDwKL0RpZmZlcmVuY2VzIFsgMzIgL3NwYWNlIDQ2IC9wZXJpb2QgNDggL3plcm8gL29uZSAvdHdvIC90aHJlZSAvZm91ciAvZml2ZSAvc2l4IC9zZXZlbgovZWlnaHQgNjcgL0MgNzEgL0cgNzYgL0wgODIgL1IgODUgL1UgOTcgL2EgL2IgL2MgL2QgL2UgL2YgL2cgL2ggL2kgMTA4IC9sCi9tIC9uIC9vIDExNCAvciAvcyAvdCAvdSAvdiAvdyAxMjEgL3kgXQovVHlwZSAvRW5jb2RpbmcgPj4KL0ZpcnN0Q2hhciAwIC9Gb250QkJveCBbIC0xMDIxIC00NjMgMTc5NCAxMjMzIF0gL0ZvbnREZXNjcmlwdG9yIDE0IDAgUgovRm9udE1hdHJpeCBbIDAuMDAxIDAgMCAwLjAwMSAwIDAgXSAvTGFzdENoYXIgMjU1IC9OYW1lIC9EZWphVnVTYW5zCi9TdWJ0eXBlIC9UeXBlMyAvVHlwZSAvRm9udCAvV2lkdGhzIDEzIDAgUiA+PgplbmRvYmoKMTQgMCBvYmoKPDwgL0FzY2VudCA5MjkgL0NhcEhlaWdodCAwIC9EZXNjZW50IC0yMzYgL0ZsYWdzIDMyCi9Gb250QkJveCBbIC0xMDIxIC00NjMgMTc5NCAxMjMzIF0gL0ZvbnROYW1lIC9EZWphVnVTYW5zIC9JdGFsaWNBbmdsZSAwCi9NYXhXaWR0aCAxMzQyIC9TdGVtViAwIC9UeXBlIC9Gb250RGVzY3JpcHRvciAvWEhlaWdodCAwID4+CmVuZG9iagoxMyAwIG9iagpbIDYwMCA2MDAgNjAwIDYwMCA2MDAgNjAwIDYwMCA2MDAgNjAwIDYwMCA2MDAgNjAwIDYwMCA2MDAgNjAwIDYwMCA2MDAgNjAwCjYwMCA2MDAgNjAwIDYwMCA2MDAgNjAwIDYwMCA2MDAgNjAwIDYwMCA2MDAgNjAwIDYwMCA2MDAgMzE4IDQwMSA0NjAgODM4IDYzNgo5NTAgNzgwIDI3NSAzOTAgMzkwIDUwMCA4MzggMzE4IDM2MSAzMTggMzM3IDYzNiA2MzYgNjM2IDYzNiA2MzYgNjM2IDYzNiA2MzYKNjM2IDYzNiAzMzcgMzM3IDgzOCA4MzggODM4IDUzMSAxMDAwIDY4NCA2ODYgNjk4IDc3MCA2MzIgNTc1IDc3NSA3NTIgMjk1CjI5NSA2NTYgNTU3IDg2MyA3NDggNzg3IDYwMyA3ODcgNjk1IDYzNSA2MTEgNzMyIDY4NCA5ODkgNjg1IDYxMSA2ODUgMzkwIDMzNwozOTAgODM4IDUwMCA1MDAgNjEzIDYzNSA1NTAgNjM1IDYxNSAzNTIgNjM1IDYzNCAyNzggMjc4IDU3OSAyNzggOTc0IDYzNCA2MTIKNjM1IDYzNSA0MTEgNTIxIDM5MiA2MzQgNTkyIDgxOCA1OTIgNTkyIDUyNSA2MzYgMzM3IDYzNiA4MzggNjAwIDYzNiA2MDAgMzE4CjM1MiA1MTggMTAwMCA1MDAgNTAwIDUwMCAxMzQyIDYzNSA0MDAgMTA3MCA2MDAgNjg1IDYwMCA2MDAgMzE4IDMxOCA1MTggNTE4CjU5MCA1MDAgMTAwMCA1MDAgMTAwMCA1MjEgNDAwIDEwMjMgNjAwIDUyNSA2MTEgMzE4IDQwMSA2MzYgNjM2IDYzNiA2MzYgMzM3CjUwMCA1MDAgMTAwMCA0NzEgNjEyIDgzOCAzNjEgMTAwMCA1MDAgNTAwIDgzOCA0MDEgNDAxIDUwMCA2MzYgNjM2IDMxOCA1MDAKNDAxIDQ3MSA2MTIgOTY5IDk2OSA5NjkgNTMxIDY4NCA2ODQgNjg0IDY4NCA2ODQgNjg0IDk3NCA2OTggNjMyIDYzMiA2MzIgNjMyCjI5NSAyOTUgMjk1IDI5NSA3NzUgNzQ4IDc4NyA3ODcgNzg3IDc4NyA3ODcgODM4IDc4NyA3MzIgNzMyIDczMiA3MzIgNjExIDYwNQo2MzAgNjEzIDYxMyA2MTMgNjEzIDYxMyA2MTMgOTgyIDU1MCA2MTUgNjE1IDYxNSA2MTUgMjc4IDI3OCAyNzggMjc4IDYxMiA2MzQKNjEyIDYxMiA2MTIgNjEyIDYxMiA4MzggNjEyIDYzNCA2MzQgNjM0IDYzNCA1OTIgNjM1IDU5MiBdCmVuZG9iagoxNiAwIG9iago8PCAvQyAxNyAwIFIgL0cgMTggMCBSIC9MIDE5IDAgUiAvUiAyMCAwIFIgL1UgMjEgMCBSIC9hIDIyIDAgUiAvYiAyMyAwIFIKL2MgMjQgMCBSIC9kIDI1IDAgUiAvZSAyNiAwIFIgL2VpZ2h0IDI3IDAgUiAvZiAyOCAwIFIgL2ZpdmUgMjkgMCBSCi9mb3VyIDMwIDAgUiAvZyAzMSAwIFIgL2ggMzIgMCBSIC9pIDMzIDAgUiAvbCAzNCAwIFIgL20gMzUgMCBSIC9uIDM3IDAgUgovbyAzOCAwIFIgL29uZSAzOSAwIFIgL3BlcmlvZCA0MCAwIFIgL3IgNDEgMCBSIC9zIDQyIDAgUiAvc2V2ZW4gNDMgMCBSCi9zaXggNDQgMCBSIC9zcGFjZSA0NSAwIFIgL3QgNDYgMCBSIC90aHJlZSA0NyAwIFIgL3R3byA0OCAwIFIgL3UgNDkgMCBSCi92IDUwIDAgUiAvdyA1MSAwIFIgL3kgNTIgMCBSIC96ZXJvIDUzIDAgUiA+PgplbmRvYmoKMyAwIG9iago8PCAvRjEgMTUgMCBSID4+CmVuZG9iago0IDAgb2JqCjw8IC9BMSA8PCAvQ0EgMCAvVHlwZSAvRXh0R1N0YXRlIC9jYSAxID4+Ci9BMiA8PCAvQ0EgMSAvVHlwZSAvRXh0R1N0YXRlIC9jYSAxID4+Ci9BMyA8PCAvQ0EgMSAvVHlwZSAvRXh0R1N0YXRlIC9jYSAwLjUgPj4gPj4KZW5kb2JqCjUgMCBvYmoKPDwgPj4KZW5kb2JqCjYgMCBvYmoKPDwgPj4KZW5kb2JqCjcgMCBvYmoKPDwgL0YxLURlamFWdVNhbnMtbWludXMgMzYgMCBSID4+CmVuZG9iagoyIDAgb2JqCjw8IC9Db3VudCAxIC9LaWRzIFsgMTEgMCBSIF0gL1R5cGUgL1BhZ2VzID4+CmVuZG9iago1NCAwIG9iago8PCAvQ3JlYXRpb25EYXRlIChEOjIwMjEwOTE2MTQzMzQyKzAyJzAwJykKL0NyZWF0b3IgKE1hdHBsb3RsaWIgdjMuNC4zLCBodHRwczovL21hdHBsb3RsaWIub3JnKQovUHJvZHVjZXIgKE1hdHBsb3RsaWIgcGRmIGJhY2tlbmQgdjMuNC4zKSA+PgplbmRvYmoKeHJlZgowIDU1CjAwMDAwMDAwMDAgNjU1MzUgZiAKMDAwMDAwMDAxNiAwMDAwMCBuIAowMDAwMDIwOTk2IDAwMDAwIG4gCjAwMDAwMjA3MzMgMDAwMDAgbiAKMDAwMDAyMDc2NSAwMDAwMCBuIAowMDAwMDIwOTA1IDAwMDAwIG4gCjAwMDAwMjA5MjYgMDAwMDAgbiAKMDAwMDAyMDk0NyAwMDAwMCBuIAowMDAwMDAwMDY1IDAwMDAwIG4gCjAwMDAwMDA0MDcgMDAwMDAgbiAKMDAwMDAwODk5MSAwMDAwMCBuIAowMDAwMDAwMjA4IDAwMDAwIG4gCjAwMDAwMDg5NzAgMDAwMDAgbiAKMDAwMDAxOTI2MiAwMDAwMCBuIAowMDAwMDE5MDYyIDAwMDAwIG4gCjAwMDAwMTg1ODYgMDAwMDAgbiAKMDAwMDAyMDMxNSAwMDAwMCBuIAowMDAwMDA5MDExIDAwMDAwIG4gCjAwMDAwMDkzMTkgMDAwMDAgbiAKMDAwMDAwOTYzOSAwMDAwMCBuIAowMDAwMDA5NzcyIDAwMDAwIG4gCjAwMDAwMTAwNzcgMDAwMDAgbiAKMDAwMDAxMDMwNiAwMDAwMCBuIAowMDAwMDEwNjg2IDAwMDAwIG4gCjAwMDAwMTEwMDMgMDAwMDAgbiAKMDAwMDAxMTMwOCAwMDAwMCBuIAowMDAwMDExNjEyIDAwMDAwIG4gCjAwMDAwMTE5MzQgMDAwMDAgbiAKMDAwMDAxMjQwMiAwMDAwMCBuIAowMDAwMDEyNjExIDAwMDAwIG4gCjAwMDAwMTI5MzMgMDAwMDAgbiAKMDAwMDAxMzA5OSAwMDAwMCBuIAowMDAwMDEzNTEzIDAwMDAwIG4gCjAwMDAwMTM3NTAgMDAwMDAgbiAKMDAwMDAxMzg5NCAwMDAwMCBuIAowMDAwMDE0MDEzIDAwMDAwIG4gCjAwMDAwMTQzNDQgMDAwMDAgbiAKMDAwMDAxNDUxNiAwMDAwMCBuIAowMDAwMDE0NzUyIDAwMDAwIG4gCjAwMDAwMTUwNDMgMDAwMDAgbiAKMDAwMDAxNTE5OCAwMDAwMCBuIAowMDAwMDE1MzIxIDAwMDAwIG4gCjAwMDAwMTU1NTQgMDAwMDAgbiAKMDAwMDAxNTk2MSAwMDAwMCBuIAowMDAwMDE2MTAzIDAwMDAwIG4gCjAwMDAwMTY0OTYgMDAwMDAgbiAKMDAwMDAxNjU4NiAwMDAwMCBuIAowMDAwMDE2NzkyIDAwMDAwIG4gCjAwMDAwMTcyMDUgMDAwMDAgbiAKMDAwMDAxNzUyOSAwMDAwMCBuIAowMDAwMDE3Nzc2IDAwMDAwIG4gCjAwMDAwMTc5MjMgMDAwMDAgbiAKMDAwMDAxODA4NCAwMDAwMCBuIAowMDAwMDE4Mjk4IDAwMDAwIG4gCjAwMDAwMjEwNTYgMDAwMDAgbiAKdHJhaWxlcgo8PCAvSW5mbyA1NCAwIFIgL1Jvb3QgMSAwIFIgL1NpemUgNTUgPj4Kc3RhcnR4cmVmCjIxMjEzCiUlRU9GCg==\n", "image/svg+xml": ["\n", "\n", "\n"], "text/plain": [""]}, "metadata": {}, "output_type": "display_data"}, {"data": {"application/pdf": "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\n", "image/svg+xml": ["\n", "\n", "\n"], "text/plain": [""]}, "metadata": {}, "output_type": "display_data"}, {"data": {"application/pdf": "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\n", "image/svg+xml": ["\n", "\n", "\n"], "text/plain": [""]}, "metadata": {}, "output_type": "display_data"}, {"data": {"application/pdf": "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\n", "image/svg+xml": ["\n", "\n", "\n"], "text/plain": [""]}, "metadata": {}, "output_type": "display_data"}], "source": ["# Seaborn prints warnings if histogram has small values. We can ignore them for now\n", "warnings.filterwarnings(\"ignore\")\n", "# Create a plot for every activation function\n", "for i, act_fn_name in enumerate(act_fn_by_name):\n", " # Setting the seed ensures that we have the same weight initialization for each activation function\n", " set_seed(42)\n", " act_fn = act_fn_by_name[act_fn_name]()\n", " net_actfn = BaseNetwork(act_fn=act_fn).to(device)\n", " visualize_gradients(net_actfn, color=f\"C{i}\")"]}, {"cell_type": "markdown", "id": "f73b5f3f", "metadata": {"papermill": {"duration": 0.062002, "end_time": "2021-09-16T12:33:55.677984", "exception": false, "start_time": "2021-09-16T12:33:55.615982", "status": "completed"}, "tags": []}, "source": ["The sigmoid activation function shows a clearly undesirable behavior.\n", "While the gradients for the output layer are very large with up to 0.1, the input layer has the lowest gradient norm across all activation functions with only 1e-5.\n", "This is due to its small maximum gradient of 1/4, and finding a suitable learning rate across all layers is not possible in this setup.\n", "All the other activation functions show to have similar gradient norms across all layers.\n", "Interestingly, the ReLU activation has a spike around 0 which is caused by its zero-part on the left, and dead neurons (we will take a closer look at this later on).\n", "\n", "Note that additionally to the activation, the initialization of the weight parameters can be crucial.\n", "By default, PyTorch uses the [Kaiming](https://pytorch.org/docs/stable/nn.init.html#torch.nn.init.kaiming_uniform_) initialization for linear layers optimized for Tanh activations.\n", "In Tutorial 4, we will take a closer look at initialization, but assume\n", "for now that the Kaiming initialization works for all activation\n", "functions reasonably well."]}, {"cell_type": "markdown", "id": "b6081434", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.061601, "end_time": "2021-09-16T12:33:55.800993", "exception": false, "start_time": "2021-09-16T12:33:55.739392", "status": "completed"}, "tags": []}, "source": ["### Training a model\n", "\n", "Next, we want to train our model with different activation functions on FashionMNIST and compare the gained performance.\n", "All in all, our final goal is to achieve the best possible performance on a dataset of our choice.\n", "Therefore, we write a training loop in the next cell including a\n", "validation after every epoch and a final test on the best model:"]}, {"cell_type": "code", "execution_count": 18, "id": "827e3645", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:55.937494Z", "iopub.status.busy": "2021-09-16T12:33:55.936999Z", "iopub.status.idle": "2021-09-16T12:33:55.939074Z", "shell.execute_reply": "2021-09-16T12:33:55.938676Z"}, "papermill": {"duration": 0.07601, "end_time": "2021-09-16T12:33:55.939174", "exception": false, "start_time": "2021-09-16T12:33:55.863164", "status": "completed"}, "tags": []}, "outputs": [], "source": ["def train_model(net, model_name, max_epochs=50, patience=7, batch_size=256, overwrite=False):\n", " \"\"\"Train a model on the training set of FashionMNIST.\n", "\n", " Args:\n", " net: Object of BaseNetwork\n", " model_name: (str) Name of the model, used for creating the checkpoint names\n", " max_epochs: Number of epochs we want to (maximally) train for\n", " patience: If the performance on the validation set has not improved for #patience epochs, we stop training early\n", " batch_size: Size of batches used in training\n", " overwrite: Determines how to handle the case when there already exists a checkpoint. If True, it will be overwritten. Otherwise, we skip training.\n", " \"\"\"\n", " file_exists = os.path.isfile(_get_model_file(CHECKPOINT_PATH, model_name))\n", " if file_exists and not overwrite:\n", " print(\"Model file already exists. Skipping training...\")\n", " else:\n", " if file_exists:\n", " print(\"Model file exists, but will be overwritten...\")\n", "\n", " # Defining optimizer, loss and data loader\n", " optimizer = optim.SGD(net.parameters(), lr=1e-2, momentum=0.9) # Default parameters, feel free to change\n", " loss_module = nn.CrossEntropyLoss()\n", " train_loader_local = data.DataLoader(\n", " train_set, batch_size=batch_size, shuffle=True, drop_last=True, pin_memory=True\n", " )\n", "\n", " val_scores = []\n", " best_val_epoch = -1\n", " for epoch in range(max_epochs):\n", " ############\n", " # Training #\n", " ############\n", " net.train()\n", " true_preds, count = 0.0, 0\n", " for imgs, labels in tqdm(train_loader_local, desc=f\"Epoch {epoch+1}\", leave=False):\n", " imgs, labels = imgs.to(device), labels.to(device) # To GPU\n", " optimizer.zero_grad() # Zero-grad can be placed anywhere before \"loss.backward()\"\n", " preds = net(imgs)\n", " loss = loss_module(preds, labels)\n", " loss.backward()\n", " optimizer.step()\n", " # Record statistics during training\n", " true_preds += (preds.argmax(dim=-1) == labels).sum()\n", " count += labels.shape[0]\n", " train_acc = true_preds / count\n", "\n", " ##############\n", " # Validation #\n", " ##############\n", " val_acc = test_model(net, val_loader)\n", " val_scores.append(val_acc)\n", " print(\n", " f\"[Epoch {epoch+1:2i}] Training accuracy: {train_acc*100.0:05.2f}%, Validation accuracy: {val_acc*100.0:05.2f}%\"\n", " )\n", "\n", " if len(val_scores) == 1 or val_acc > val_scores[best_val_epoch]:\n", " print(\"\\t (New best performance, saving model...)\")\n", " save_model(net, CHECKPOINT_PATH, model_name)\n", " best_val_epoch = epoch\n", " elif best_val_epoch <= epoch - patience:\n", " print(f\"Early stopping due to no improvement over the last {patience} epochs\")\n", " break\n", "\n", " # Plot a curve of the validation accuracy\n", " plt.plot([i for i in range(1, len(val_scores) + 1)], val_scores)\n", " plt.xlabel(\"Epochs\")\n", " plt.ylabel(\"Validation accuracy\")\n", " plt.title(f\"Validation performance of {model_name}\")\n", " plt.show()\n", " plt.close()\n", "\n", " load_model(CHECKPOINT_PATH, model_name, net=net)\n", " test_acc = test_model(net, test_loader)\n", " print((f\" Test accuracy: {test_acc*100.0:4.2f}% \").center(50, \"=\") + \"\\n\")\n", " return test_acc\n", "\n", "\n", "def test_model(net, data_loader):\n", " \"\"\"Test a model on a specified dataset.\n", "\n", " Args:\n", " net: Trained model of type BaseNetwork\n", " data_loader: DataLoader object of the dataset to test on (validation or test)\n", " \"\"\"\n", " net.eval()\n", " true_preds, count = 0.0, 0\n", " for imgs, labels in data_loader:\n", " imgs, labels = imgs.to(device), labels.to(device)\n", " with torch.no_grad():\n", " preds = net(imgs).argmax(dim=-1)\n", " true_preds += (preds == labels).sum().item()\n", " count += labels.shape[0]\n", " test_acc = true_preds / count\n", " return test_acc"]}, {"cell_type": "markdown", "id": "685326ae", "metadata": {"papermill": {"duration": 0.06232, "end_time": "2021-09-16T12:33:56.062996", "exception": false, "start_time": "2021-09-16T12:33:56.000676", "status": "completed"}, "tags": []}, "source": ["We train one model for each activation function.\n", "We recommend using the pretrained models to save time if you are running this notebook on CPU."]}, {"cell_type": "code", "execution_count": 19, "id": "1a2237a5", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:33:56.192395Z", "iopub.status.busy": "2021-09-16T12:33:56.191926Z", "iopub.status.idle": "2021-09-16T12:34:06.194481Z", "shell.execute_reply": "2021-09-16T12:34:06.193995Z"}, "papermill": {"duration": 10.068153, "end_time": "2021-09-16T12:34:06.194591", "exception": false, "start_time": "2021-09-16T12:33:56.126438", "status": "completed"}, "tags": []}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Training BaseNetwork with sigmoid activation...\n", "Model file already exists. Skipping training...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["============= Test accuracy: 10.00% ==============\n", "\n", "Training BaseNetwork with tanh activation...\n", "Model file already exists. Skipping training...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["============= Test accuracy: 87.59% ==============\n", "\n", "Training BaseNetwork with relu activation...\n", "Model file already exists. Skipping training...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["============= Test accuracy: 88.62% ==============\n", "\n", "Training BaseNetwork with leakyrelu activation...\n", "Model file already exists. Skipping training...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["============= Test accuracy: 88.92% ==============\n", "\n", "Training BaseNetwork with elu activation...\n", "Model file already exists. Skipping training...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["============= Test accuracy: 87.27% ==============\n", "\n", "Training BaseNetwork with swish activation...\n", "Model file already exists. Skipping training...\n"]}, {"name": "stdout", "output_type": "stream", "text": ["============= Test accuracy: 88.73% ==============\n", "\n"]}], "source": ["for act_fn_name in act_fn_by_name:\n", " print(f\"Training BaseNetwork with {act_fn_name} activation...\")\n", " set_seed(42)\n", " act_fn = act_fn_by_name[act_fn_name]()\n", " net_actfn = BaseNetwork(act_fn=act_fn).to(device)\n", " train_model(net_actfn, f\"FashionMNIST_{act_fn_name}\", overwrite=False)"]}, {"cell_type": "markdown", "id": "34dd5b86", "metadata": {"papermill": {"duration": 0.062788, "end_time": "2021-09-16T12:34:06.322278", "exception": false, "start_time": "2021-09-16T12:34:06.259490", "status": "completed"}, "tags": []}, "source": ["Not surprisingly, the model using the sigmoid activation function shows to fail and does not improve upon random performance (10 classes => 1/10 for random chance).\n", "\n", "All the other activation functions gain similar performance.\n", "To have a more accurate conclusion, we would have to train the models for multiple seeds and look at the averages.\n", "However, the \"optimal\" activation function also depends on many other factors (hidden sizes, number of layers, type of layers, task, dataset, optimizer, learning rate, etc.)\n", "so that a thorough grid search would not be useful in our case.\n", "In the literature, activation functions that have shown to work well\n", "with deep networks are all types of ReLU functions we experiment with\n", "here, with small gains for specific activation functions in specific\n", "networks."]}, {"cell_type": "markdown", "id": "5a74d87d", "metadata": {"papermill": {"duration": 0.063695, "end_time": "2021-09-16T12:34:06.449135", "exception": false, "start_time": "2021-09-16T12:34:06.385440", "status": "completed"}, "tags": []}, "source": ["### Visualizing the activation distribution"]}, {"cell_type": "markdown", "id": "68596e03", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.062527, "end_time": "2021-09-16T12:34:06.574529", "exception": false, "start_time": "2021-09-16T12:34:06.512002", "status": "completed"}, "tags": []}, "source": ["After we have trained the models, we can look at the actual activation values that find inside the model.\n", "For instance, how many neurons are set to zero in ReLU?\n", "Where do we find most values in Tanh?\n", "To answer these questions, we can write a simple function which takes a\n", "trained model, applies it to a batch of images, and plots the histogram\n", "of the activations inside the network:"]}, {"cell_type": "code", "execution_count": 20, "id": "24bf9b21", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:34:06.708975Z", "iopub.status.busy": "2021-09-16T12:34:06.708490Z", "iopub.status.idle": "2021-09-16T12:34:06.710629Z", "shell.execute_reply": "2021-09-16T12:34:06.710158Z"}, "papermill": {"duration": 0.073035, "end_time": "2021-09-16T12:34:06.710735", "exception": false, "start_time": "2021-09-16T12:34:06.637700", "status": "completed"}, "tags": []}, "outputs": [], "source": ["def visualize_activations(net, color=\"C0\"):\n", " activations = {}\n", "\n", " net.eval()\n", " small_loader = data.DataLoader(train_set, batch_size=1024)\n", " imgs, labels = next(iter(small_loader))\n", " with torch.no_grad():\n", " layer_index = 0\n", " imgs = imgs.to(device)\n", " imgs = imgs.view(imgs.size(0), -1)\n", " # We need to manually loop through the layers to save all activations\n", " for layer_index, layer in enumerate(net.layers[:-1]):\n", " imgs = layer(imgs)\n", " activations[layer_index] = imgs.view(-1).cpu().numpy()\n", "\n", " # Plotting\n", " columns = 4\n", " rows = math.ceil(len(activations) / columns)\n", " fig, ax = plt.subplots(rows, columns, figsize=(columns * 2.7, rows * 2.5))\n", " fig_index = 0\n", " for key in activations:\n", " key_ax = ax[fig_index // columns][fig_index % columns]\n", " sns.histplot(data=activations[key], bins=50, ax=key_ax, color=color, kde=True, stat=\"density\")\n", " key_ax.set_title(f\"Layer {key} - {net.layers[key].__class__.__name__}\")\n", " fig_index += 1\n", " fig.suptitle(f\"Activation distribution for activation function {net.config['act_fn']['name']}\", fontsize=14)\n", " fig.subplots_adjust(hspace=0.4, wspace=0.4)\n", " plt.show()\n", " plt.close()"]}, {"cell_type": "code", "execution_count": 21, "id": "d8f346ab", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:34:06.842909Z", "iopub.status.busy": "2021-09-16T12:34:06.842437Z", "iopub.status.idle": "2021-09-16T12:35:27.581742Z", "shell.execute_reply": "2021-09-16T12:35:27.582143Z"}, "papermill": {"duration": 80.807, "end_time": "2021-09-16T12:35:27.582289", "exception": false, "start_time": "2021-09-16T12:34:06.775289", "status": "completed"}, "tags": []}, "outputs": [{"data": {"application/pdf": "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\n", "image/svg+xml": ["\n", "\n", "\n"], "text/plain": [""]}, "metadata": {}, "output_type": "display_data"}, {"data": {"application/pdf": "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\n", "image/svg+xml": ["\n", "\n", "\n"], "text/plain": [""]}, "metadata": {}, "output_type": "display_data"}, {"data": {"application/pdf": "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\n", "image/svg+xml": ["\n", "\n", "\n"], "text/plain": [""]}, "metadata": {}, "output_type": "display_data"}, {"data": {"application/pdf": "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\n", "image/svg+xml": ["\n", "\n", "\n"], "text/plain": [""]}, "metadata": {}, "output_type": "display_data"}, {"data": {"application/pdf": "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\n", "image/svg+xml": ["\n", "\n", "\n"], "text/plain": [""]}, "metadata": {}, "output_type": "display_data"}, {"data": {"application/pdf": "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\n", "image/svg+xml": ["\n", "\n", "\n"], "text/plain": [""]}, "metadata": {}, "output_type": "display_data"}], "source": ["for i, act_fn_name in enumerate(act_fn_by_name):\n", " net_actfn = load_model(model_path=CHECKPOINT_PATH, model_name=f\"FashionMNIST_{act_fn_name}\").to(device)\n", " visualize_activations(net_actfn, color=f\"C{i}\")"]}, {"cell_type": "markdown", "id": "1a945558", "metadata": {"papermill": {"duration": 0.111895, "end_time": "2021-09-16T12:35:27.806164", "exception": false, "start_time": "2021-09-16T12:35:27.694269", "status": "completed"}, "tags": []}, "source": ["As the model with sigmoid activation was not able to train properly, the activations are also less informative and all gathered around 0.5 (the activation at input 0).\n", "\n", "The tanh shows a more diverse behavior.\n", "While for the input layer we experience a larger amount of neurons to be close to -1 and 1, where the gradients are close to zero, the activations in the two consecutive layers are closer to zero.\n", "This is probably because the input layers look for specific features in the input image, and the consecutive layers combine those together.\n", "The activations for the last layer are again more biased to the extreme points because the classification layer can be seen as a weighted average of those values (the gradients push the activations to those extremes).\n", "\n", "The ReLU has a strong peak at 0, as we initially expected.\n", "The effect of having no gradients for negative values is that the network does not have a Gaussian-like distribution after the linear layers, but a longer tail towards the positive values.\n", "The LeakyReLU shows a very similar behavior while ELU follows again a more Gaussian-like distribution.\n", "The Swish activation seems to lie in between, although it is worth noting that Swish uses significantly higher values than other activation functions (up to 20).\n", "\n", "As all activation functions show slightly different behavior although\n", "obtaining similar performance for our simple network, it becomes\n", "apparent that the selection of the \"optimal\" activation function really\n", "depends on many factors, and is not the same for all possible networks."]}, {"cell_type": "markdown", "id": "57bfc158", "metadata": {"papermill": {"duration": 0.110593, "end_time": "2021-09-16T12:35:28.026614", "exception": false, "start_time": "2021-09-16T12:35:27.916021", "status": "completed"}, "tags": []}, "source": ["### Finding dead neurons in ReLU networks"]}, {"cell_type": "markdown", "id": "3dbcab2c", "metadata": {"lines_to_next_cell": 2, "papermill": {"duration": 0.114666, "end_time": "2021-09-16T12:35:28.251636", "exception": false, "start_time": "2021-09-16T12:35:28.136970", "status": "completed"}, "tags": []}, "source": ["One known drawback of the ReLU activation is the occurrence of \"dead neurons\", i.e. neurons with no gradient for any training input.\n", "The issue of dead neurons is that as no gradient is provided for the layer, we cannot train the parameters of this neuron in the previous layer to obtain output values besides zero.\n", "For dead neurons to happen, the output value of a specific neuron of the linear layer before the ReLU has to be negative for all input images.\n", "Considering the large number of neurons we have in a neural network, it is not unlikely for this to happen.\n", "\n", "To get a better understanding of how much of a problem this is, and when we need to be careful, we will measure how many dead neurons different networks have.\n", "For this, we implement a function which runs the network on the whole\n", "training set and records whether a neuron is exactly 0 for all data\n", "points or not:"]}, {"cell_type": "code", "execution_count": 22, "id": "edc02b80", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:35:28.479594Z", "iopub.status.busy": "2021-09-16T12:35:28.479110Z", "iopub.status.idle": "2021-09-16T12:35:28.481273Z", "shell.execute_reply": "2021-09-16T12:35:28.481901Z"}, "papermill": {"duration": 0.119951, "end_time": "2021-09-16T12:35:28.482036", "exception": false, "start_time": "2021-09-16T12:35:28.362085", "status": "completed"}, "tags": []}, "outputs": [], "source": ["@torch.no_grad()\n", "def measure_number_dead_neurons(net):\n", " \"\"\"Function to measure the number of dead neurons in a trained neural network.\n", "\n", " For each neuron, we create a boolean variable initially set to 1. If it has an activation unequals 0 at any time, we\n", " set this variable to 0. After running through the whole training set, only dead neurons will have a 1.\n", " \"\"\"\n", " neurons_dead = [\n", " torch.ones(layer.weight.shape[0], device=device, dtype=torch.bool)\n", " for layer in net.layers[:-1]\n", " if isinstance(layer, nn.Linear)\n", " ] # Same shapes as hidden size in BaseNetwork\n", "\n", " net.eval()\n", " for imgs, labels in tqdm(train_loader, leave=False): # Run through whole training set\n", " layer_index = 0\n", " imgs = imgs.to(device)\n", " imgs = imgs.view(imgs.size(0), -1)\n", " for layer in net.layers[:-1]:\n", " imgs = layer(imgs)\n", " if isinstance(layer, ActivationFunction):\n", " # Are all activations == 0 in the batch, and we did not record the opposite in the last batches?\n", " neurons_dead[layer_index] = torch.logical_and(neurons_dead[layer_index], (imgs == 0).all(dim=0))\n", " layer_index += 1\n", " number_neurons_dead = [t.sum().item() for t in neurons_dead]\n", " print(\"Number of dead neurons:\", number_neurons_dead)\n", " print(\n", " \"In percentage:\",\n", " \", \".join(\n", " [f\"{(100.0 * num_dead / tens.shape[0]):4.2f}%\" for tens, num_dead in zip(neurons_dead, number_neurons_dead)]\n", " ),\n", " )"]}, {"cell_type": "markdown", "id": "39be5f1b", "metadata": {"papermill": {"duration": 0.109828, "end_time": "2021-09-16T12:35:28.702763", "exception": false, "start_time": "2021-09-16T12:35:28.592935", "status": "completed"}, "tags": []}, "source": ["First, we can measure the number of dead neurons for an untrained network:"]}, {"cell_type": "code", "execution_count": 23, "id": "1f83d14a", "metadata": {"execution": {"iopub.execute_input": "2021-09-16T12:35:28.929900Z", "iopub.status.busy": "2021-09-16T12:35:28.929410Z", "iopub.status.idle": "2021-09-16T12:35:37.256636Z", "shell.execute_reply": "2021-09-16T12:35:37.256221Z"}, "papermill": {"duration": 8.441781, "end_time": "2021-09-16T12:35:37.256748", "exception": false, "start_time": "2021-09-16T12:35:28.814967", "status": "completed"}, "tags": []}, "outputs": [{"data": {"application/vnd.jupyter.widget-view+json": {"model_id": "4f3bb9c6b5c64d568faac8e14240eab4", "version_major": 2, "version_minor": 0}, "text/plain": [" 0%| | 0/49 [00:00