As time passed, computing resources became cheaper, and more data has become available, the neural network approaches started demonstrating great performance in competing with human beings in many areas, such as computer vision, or speech understanding. In the last decade, the term Artificial Intelligence is mostly used as a synonym for Neural Networks, because most of the AI successes that we hear about are based on them.
@@ -76,5 +75,27 @@ Similarly, we can see how the approach towards creating “talking programs” (
* Early program of this kind, [Eliza](https://en.wikipedia.org/wiki/ELIZA), was based on very simple grammatical rule and re-formulation of the input sentence into a question.
* Modern assistants, such as Cortana, Siri or Google Assistant, are all hybrid systems, that use Neural networks to convert speech into text and to recognize our intent, and then employ some reasoning or explicit algorithms to perform required actions
-* In the future, we may expect complete neural-based model to handle dialogue by itself, recent GPT family of neural networks show great success in this.
+* In the future, we may expect complete neural-based model to handle dialogue by itself. Recent GPT and [Turing-NLG](https://turing.microsoft.com/) family of neural networks show great success in this.
+
+
+
+## Recent AI Research
+
+Recent huge growth in neural network research started around 2010, when large public datasets started to become available. A huge collection of images called [ImageNet](https://en.wikipedia.org/wiki/ImageNet), which contains around 14 million annotated images, gave birth to [ImageNet Large Scale Visual Recognition Challenge](https://image-net.org/challenges/LSVRC/).
+
+
+
+In 2012, [Convolutional Neural Networks](../4-ComputerVision/07-ConvNets/README.md) were first used in image classification, which lead to significant drop in classification errors (from almost 30% to 16.4%). In 2015, ResNet architecture from Microsoft Research [achieved human-level accuracy](https://doi.org/10.1109/ICCV.2015.123).
+
+Since then, Neural Networks demonstrated very successful behaviour in many tasks:
+
+------|-------
+Year | Human Parity in
+-----|--------
+2015 | [Image Classification](https://doi.org/10.1109/ICCV.2015.123)
+2016 | [Conversational Speech Recognition](https://arxiv.org/abs/1610.05256)
+2018 | [Automatic Machine Translation](https://arxiv.org/abs/1803.05567) (Chinese-to-English)
+2020 | [Image Captioning](https://arxiv.org/abs/2009.13682)
+
+Last years witnessed huge successes with large language models, such as BERT and GPT-3. This happens mainly due to the fact that there is a lot of general text data available, which allows us to train models that capture the structure and meaning of texts, pre-train them on general text collections, and then specialize those models for more specific tasks. We will learn more about [Natural Language Processing](../5-NLP/README.md) later in this course.
diff --git a/1-Intro/images/history-of-ai.png b/1-Intro/images/history-of-ai.png
index ae42232b..4a5a2d69 100644
Binary files a/1-Intro/images/history-of-ai.png and b/1-Intro/images/history-of-ai.png differ
diff --git a/1-Intro/images/ilsvrc.gif b/1-Intro/images/ilsvrc.gif
new file mode 100644
index 00000000..36410467
Binary files /dev/null and b/1-Intro/images/ilsvrc.gif differ
diff --git a/1-Intro/images/turing-test-evol.png b/1-Intro/images/turing-test-evol.png
new file mode 100644
index 00000000..7883f7e1
Binary files /dev/null and b/1-Intro/images/turing-test-evol.png differ
diff --git a/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb b/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb
index 8b4aad8e..bc3442fe 100644
--- a/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb
+++ b/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb
@@ -1048,11 +1048,6 @@
"This notebook is a part of [AI for Beginners Curricula](http://github.com/microsoft/ai-for-beginners), and has been prepared by [Dmitry Soshnikov](http://soshnikov.com). It is inspired by Neural Network Workshop at Microsoft Research Cambridge. Some code and illustrative materials are taken from presentations by [Katja Hoffmann](https://www.microsoft.com/en-us/research/people/kahofman/), [Matthew Johnson](https://www.microsoft.com/en-us/research/people/matjoh/) and [Ryoto Tomioka](https://www.microsoft.com/en-us/research/people/ryoto/), and from [NeuroWorkshop](http://github.com/shwars/NeuroWorkshop) repository."
],
"metadata": {}
- },
- {
- "cell_type": "markdown",
- "source": [],
- "metadata": {}
}
],
"metadata": {
diff --git a/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb b/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb
index 81883322..6bdc2341 100644
--- a/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb
+++ b/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb
@@ -2,1097 +2,1316 @@
"cells": [
{
"cell_type": "markdown",
- "source": [
- "## Multi-Layered Perceptrons\r\n",
- "## Building our own Neural Framework\r\n",
- "\r\n",
- "> This notebook is a part of [AI for Beginners Curricula](http://github.com/microsoft/ai-for-beginners). Visit the repository for complete set of learning materials.\r\n",
- "\r\n",
- "In this notebook, we will gradually build our own neural framework capable of solving multi-class classification tasks as well as regression with multi-layered preceptrons.\r\n",
- "\r\n",
- "First, let's import some required libraries."
- ],
"metadata": {
"slideshow": {
"slide_type": "slide"
}
- }
+ },
+ "source": [
+ "## Multi-Layered Perceptrons\n",
+ "## Building our own Neural Framework\n",
+ "\n",
+ "> This notebook is a part of [AI for Beginners Curricula](http://github.com/microsoft/ai-for-beginners). Visit the repository for complete set of learning materials.\n",
+ "\n",
+ "In this notebook, we will gradually build our own neural framework capable of solving multi-class classification tasks as well as regression with multi-layered preceptrons.\n",
+ "\n",
+ "First, let's import some required libraries."
+ ]
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 14,
+ "metadata": {
+ "slideshow": {
+ "slide_type": "skip"
+ }
+ },
+ "outputs": [],
"source": [
- "%matplotlib nbagg\r\n",
- "import matplotlib.pyplot as plt \r\n",
- "from matplotlib import gridspec\r\n",
- "from sklearn.datasets import make_classification\r\n",
- "import numpy as np\r\n",
- "# pick the seed for reproducability - change it to explore the effects of random variations\r\n",
- "np.random.seed(0)\r\n",
+ "%matplotlib nbagg\n",
+ "import matplotlib.pyplot as plt \n",
+ "from matplotlib import gridspec\n",
+ "from sklearn.datasets import make_classification\n",
+ "import numpy as np\n",
+ "# pick the seed for reproducibility - change it to explore the effects of random variations\n",
+ "np.random.seed(0)\n",
"import random"
- ],
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
+ "source": [
+ "## Sample Dataset\n",
+ "\n",
+ "As before, we will start with a simple sample dataset with two parameters.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {
+ "scrolled": false,
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
+ "outputs": [],
+ "source": [
+ "n = 100\n",
+ "X, Y = make_classification(n_samples = n, n_features=2,\n",
+ " n_redundant=0, n_informative=2, flip_y=0.2)\n",
+ "X = X.astype(np.float32)\n",
+ "Y = Y.astype(np.int32)\n",
+ "\n",
+ "# Разбиваем на обучающую и тестовые выборки\n",
+ "train_x, test_x = np.split(X, [n*8//10])\n",
+ "train_labels, test_labels = np.split(Y, [n*8//10])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {
+ "scrolled": false,
+ "slideshow": {
+ "slide_type": "skip"
+ }
+ },
+ "outputs": [],
+ "source": [
+ "def plot_dataset(suptitle, features, labels):\n",
+ " # prepare the plot\n",
+ " fig, ax = plt.subplots(1, 1)\n",
+ " #pylab.subplots_adjust(bottom=0.2, wspace=0.4)\n",
+ " fig.suptitle(suptitle, fontsize = 16)\n",
+ " ax.set_xlabel('$x_i[0]$ -- (feature 1)')\n",
+ " ax.set_ylabel('$x_i[1]$ -- (feature 2)')\n",
+ "\n",
+ " colors = ['r' if l else 'b' for l in labels]\n",
+ " ax.scatter(features[:, 0], features[:, 1], marker='o', c=colors, s=100, alpha = 0.5)\n",
+ " fig.show()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "metadata": {
+ "scrolled": false,
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
"outputs": [
{
- "output_type": "error",
- "ename": "ImportError",
- "evalue": "cannot import name 'animation' from partially initialized module 'matplotlib' (most likely due to a circular import) (C:\\winapp\\Miniconda3\\lib\\site-packages\\matplotlib\\__init__.py)",
- "traceback": [
- "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[1;31mImportError\u001b[0m Traceback (most recent call last)",
- "\u001b[1;32m![](\"images/NeuroArch.png\")
\r\n",
- "\r\n",
- "Two outputs of the network correspond to two classes, and the class with highest value among two outputs corresponds to the right solution.\r\n",
- "\r\n",
- "The model is defined as\r\n",
- "$$\r\n",
- "f_\\theta(x) = W\\times x + b\r\n",
- "$$\r\n",
- "where $$\\theta = \\langle W,b\\rangle$$ are parameters.\r\n",
- "\r\n",
+ "To understand logistic loss, consider two cases of the expected output:\n",
+ "* If we expect output to be 1 ($y=1$), then the loss is $-log f_\\theta(x_i)$. The loss is 0 is the network predicts 1 with probability 1, and grows larger when probability of 1 gets smaller.\n",
+ "* If we expect output to be 0 ($y=0$), the loss is $-log(1-f_\\theta(x_i))$. Here, $1-f_\\theta(x_i)$ is the probability of 0 which is predicted by the network, and the meaning of log-loss is the same as described in the previous case"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
+ "source": [
+ "## Neural Network Architecture\n",
+ "\n",
+ "We have generated a dataset for binary classification problem. However, let's consider it as multi-class classification right from the start, so that we can then easily switch our code to multi-class classification. In this case, our one-layer perceptron will have the following architecture:\n",
+ "\n",
+ "\n",
+ "\n",
+ "Two outputs of the network correspond to two classes, and the class with highest value among two outputs corresponds to the right solution.\n",
+ "\n",
+ "The model is defined as\n",
+ "$$\n",
+ "f_\\theta(x) = W\\times x + b\n",
+ "$$\n",
+ "where $$\\theta = \\langle W,b\\rangle$$ are parameters.\n",
+ "\n",
"We will define this linear layer as a Python class with a `forward` function that performs the calculation. It receives input value $x$, and produces the output of the layer. Parameters `W` and `b` are stored within the layer class, and are initialized upon creation with random values and zeroes respectively."
- ],
- "metadata": {
- "slideshow": {
- "slide_type": "slide"
- }
- }
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 23,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([[ 1.77202116, -0.25384488],\n",
+ " [ 0.28370828, -0.39610552],\n",
+ " [-0.30097433, 0.30513182],\n",
+ " [-0.8120485 , 0.56079421],\n",
+ " [-1.23519653, 0.3394973 ]])"
+ ]
+ },
+ "execution_count": 23,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "class Linear:\r\n",
- " def __init__(self,nin,nout):\r\n",
- " self.W = np.random.normal(0, 1.0/np.sqrt(nin), (nout, nin))\r\n",
- " self.b = np.zeros((1,nout))\r\n",
- " \r\n",
- " def forward(self, x):\r\n",
- " return np.dot(x, self.W.T) + self.b\r\n",
- " \r\n",
- "net = Linear(2,2)\r\n",
+ "class Linear:\n",
+ " def __init__(self,nin,nout):\n",
+ " self.W = np.random.normal(0, 1.0/np.sqrt(nin), (nout, nin))\n",
+ " self.b = np.zeros((1,nout))\n",
+ " \n",
+ " def forward(self, x):\n",
+ " return np.dot(x, self.W.T) + self.b\n",
+ " \n",
+ "net = Linear(2,2)\n",
"net.forward(train_x[0:5])"
- ],
- "outputs": [],
- "metadata": {}
+ ]
},
{
"cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
"source": [
- "Because we use Numpy operations, we can pass a vector if input values to our network, and it will give us the vector of output values.\r\n",
- "\r\n",
- "## Softmax: Turning Outputs into Probabilities\r\n",
- "\r\n",
- "As you can see, our outputs are not probabilities - they can take any values. In order to convert them into probabilities, we need to normalize the values across all classes. This is done using **softmax** function: $$\\sigma(\\mathbf{z}_c) = \\frac{e^{z_c}}{\\sum_{j} e^{z_j}}, \\quad\\mathrm{for}\\quad c\\in 1 .. |C|$$\r\n",
- "\r\n",
- "![](\"https://raw.githubusercontent.com/shwars/NeuroWorkshop/master/images/NeuroArch-softmax.PNG\")
\r\n",
- "\r\n",
- "> Output of the network $\\sigma(\\mathbf{z})$ can be interpreted as probability distribution on the set of classes $C$: $q = \\sigma(\\mathbf{z}_c) = \\hat{p}(c | x)$\r\n",
- "\r\n",
+ "In many cases, it is more efficient to operate not on the one input value, but on the vector of input values. Because we use Numpy operations, we can pass a vector of input values to our network, and it will give us the vector of output values.\n",
+ "\n",
+ "## Softmax: Turning Outputs into Probabilities\n",
+ "\n",
+ "As you can see, our outputs are not probabilities - they can take any values. In order to convert them into probabilities, we need to normalize the values across all classes. This is done using **softmax** function: $$\\sigma(\\mathbf{z}_c) = \\frac{e^{z_c}}{\\sum_{j} e^{z_j}}, \\quad\\mathrm{for}\\quad c\\in 1 .. |C|$$\n",
+ "\n",
+ "\n",
+ "\n",
+ "> Output of the network $\\sigma(\\mathbf{z})$ can be interpreted as probability distribution on the set of classes $C$: $q = \\sigma(\\mathbf{z}_c) = \\hat{p}(c | x)$\n",
+ "\n",
"We will define the `Softmax` layer in the same manner, as a class with `forward` function: "
- ],
- "metadata": {
- "slideshow": {
- "slide_type": "slide"
- }
- }
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 24,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([[0.88348621, 0.11651379],\n",
+ " [0.66369714, 0.33630286],\n",
+ " [0.35294795, 0.64705205],\n",
+ " [0.20216095, 0.79783905],\n",
+ " [0.17154828, 0.82845172],\n",
+ " [0.24279153, 0.75720847],\n",
+ " [0.18915732, 0.81084268],\n",
+ " [0.17282951, 0.82717049],\n",
+ " [0.13897531, 0.86102469],\n",
+ " [0.72746882, 0.27253118]])"
+ ]
+ },
+ "execution_count": 24,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "class Softmax:\r\n",
- " def forward(self,z):\r\n",
- " zmax = z.max(axis=1,keepdims=True)\r\n",
- " expz = np.exp(z-zmax)\r\n",
- " Z = expz.sum(axis=1,keepdims=True)\r\n",
- " return expz / Z\r\n",
- "\r\n",
- "softmax = Softmax()\r\n",
+ "class Softmax:\n",
+ " def forward(self,z):\n",
+ " zmax = z.max(axis=1,keepdims=True)\n",
+ " expz = np.exp(z-zmax)\n",
+ " Z = expz.sum(axis=1,keepdims=True)\n",
+ " return expz / Z\n",
+ "\n",
+ "softmax = Softmax()\n",
"softmax.forward(net.forward(train_x[0:10]))"
- ],
- "outputs": [],
- "metadata": {}
+ ]
},
{
"cell_type": "markdown",
- "source": [
- "You can see that we are now getting probabilities as outputs, i.e. the sum of each output vector is exactly 1. \r\n",
- "\r\n",
- "In case we have more than 2 classes, softmax will normalize probabilities across all of them. Here is a diagram of network architecture that does MNIST digit classification:\r\n",
- "\r\n",
- "\r\n"
- ],
"metadata": {
"slideshow": {
"slide_type": "slide"
}
- }
+ },
+ "source": [
+ "You can see that we are now getting probabilities as outputs, i.e. the sum of each output vector is exactly 1. \n",
+ "\n",
+ "In case we have more than 2 classes, softmax will normalize probabilities across all of them. Here is a diagram of network architecture that does MNIST digit classification:\n",
+ "\n",
+ "\n"
+ ]
},
{
"cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
"source": [
- "## Cross-Entropy Loss\r\n",
- "\r\n",
- "A loss function in classification is typically a logistic function, which can be generalized as **cross-entropy loss**. Cross-entropy loss is a function that can calculate similarity between two arbitrary probability distributions. You can find more detailed discussion about it [on Wikipedia](https://en.wikipedia.org/wiki/Cross_entropy).\r\n",
- "\r\n",
- "In our case, first distribution is the probabilistic output of our network, and the second one is so-called **one-hot** distribution, which specifies that a given class $c$ has corresponding probability 1 (all the rest being 0). In such a case cross-entropy loss can be calculated as $-\\log p_c$, where $c$ is the expected class, and $p_c$ is the corresponding probability of this class given by our neural network.\r\n",
- "\r\n",
+ "## Cross-Entropy Loss\n",
+ "\n",
+ "A loss function in classification is typically a logistic function, which can be generalized as **cross-entropy loss**. Cross-entropy loss is a function that can calculate similarity between two arbitrary probability distributions. You can find more detailed discussion about it [on Wikipedia](https://en.wikipedia.org/wiki/Cross_entropy).\n",
+ "\n",
+ "In our case, first distribution is the probabilistic output of our network, and the second one is so-called **one-hot** distribution, which specifies that a given class $c$ has corresponding probability 1 (all the rest being 0). In such a case cross-entropy loss can be calculated as $-\\log p_c$, where $c$ is the expected class, and $p_c$ is the corresponding probability of this class given by our neural network.\n",
+ "\n",
"> If the network return probability 1 for the expected class, cross-entropy loss would be 0. The closer the probability of the actual class is to 0, the higher is cross-entropy loss (and it can go up to infinity!)."
- ],
- "metadata": {
- "slideshow": {
- "slide_type": "slide"
- }
- }
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
- "source": [
- "def plot_cross_ent():\r\n",
- " p = np.linspace(0.01, 0.99, 101) # estimated probability p(y|x)\r\n",
- " cross_ent_v = np.vectorize(cross_ent)\r\n",
- " f3, ax = plt.subplots(1,1, figsize=(8, 3))\r\n",
- " l1, = plt.plot(p, cross_ent_v(p, 1), 'r--')\r\n",
- " l2, = plt.plot(p, cross_ent_v(p, 0), 'r-')\r\n",
- " plt.legend([l1, l2], ['$y = 1$', '$y = 0$'], loc = 'upper center', ncol = 2)\r\n",
- " plt.xlabel('$\\hat{p}(y|x)$', size=18)\r\n",
- " plt.ylabel('$\\mathcal{L}_{CE}$', size=18)\r\n",
- " plt.show()"
- ],
- "outputs": [],
+ "execution_count": 25,
"metadata": {
"slideshow": {
"slide_type": "skip"
}
- }
+ },
+ "outputs": [],
+ "source": [
+ "def plot_cross_ent():\n",
+ " p = np.linspace(0.01, 0.99, 101) # estimated probability p(y|x)\n",
+ " cross_ent_v = np.vectorize(cross_ent)\n",
+ " f3, ax = plt.subplots(1,1, figsize=(8, 3))\n",
+ " l1, = plt.plot(p, cross_ent_v(p, 1), 'r--')\n",
+ " l2, = plt.plot(p, cross_ent_v(p, 0), 'r-')\n",
+ " plt.legend([l1, l2], ['$y = 1$', '$y = 0$'], loc = 'upper center', ncol = 2)\n",
+ " plt.xlabel('$\\hat{p}(y|x)$', size=18)\n",
+ " plt.ylabel('$\\mathcal{L}_{CE}$', size=18)\n",
+ " plt.show()"
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
- "source": [
- "def cross_ent(prediction, ground_truth):\r\n",
- " t = 1 if ground_truth > 0.5 else 0\r\n",
- " return -t * np.log(prediction) - (1 - t) * np.log(1 - prediction)\r\n",
- "plot_cross_ent()"
- ],
- "outputs": [],
+ "execution_count": 26,
"metadata": {
"scrolled": true,
"slideshow": {
"slide_type": "slide"
}
- }
+ },
+ "outputs": [
+ {
+ "data": {
+ "application/javascript": "/* Put everything inside the global mpl namespace */\n/* global mpl */\nwindow.mpl = {};\n\nmpl.get_websocket_type = function () {\n if (typeof WebSocket !== 'undefined') {\n return WebSocket;\n } else if (typeof MozWebSocket !== 'undefined') {\n return MozWebSocket;\n } else {\n alert(\n 'Your browser does not have WebSocket support. ' +\n 'Please try Chrome, Safari or Firefox ≥ 6. ' +\n 'Firefox 4 and 5 are also supported but you ' +\n 'have to enable WebSockets in about:config.'\n );\n }\n};\n\nmpl.figure = function (figure_id, websocket, ondownload, parent_element) {\n this.id = figure_id;\n\n this.ws = websocket;\n\n this.supports_binary = this.ws.binaryType !== undefined;\n\n if (!this.supports_binary) {\n var warnings = document.getElementById('mpl-warnings');\n if (warnings) {\n warnings.style.display = 'block';\n warnings.textContent =\n 'This browser does not support binary websocket messages. ' +\n 'Performance may be slow.';\n }\n }\n\n this.imageObj = new Image();\n\n this.context = undefined;\n this.message = undefined;\n this.canvas = undefined;\n this.rubberband_canvas = undefined;\n this.rubberband_context = undefined;\n this.format_dropdown = undefined;\n\n this.image_mode = 'full';\n\n this.root = document.createElement('div');\n this.root.setAttribute('style', 'display: inline-block');\n this._root_extra_style(this.root);\n\n parent_element.appendChild(this.root);\n\n this._init_header(this);\n this._init_canvas(this);\n this._init_toolbar(this);\n\n var fig = this;\n\n this.waiting = false;\n\n this.ws.onopen = function () {\n fig.send_message('supports_binary', { value: fig.supports_binary });\n fig.send_message('send_image_mode', {});\n if (fig.ratio !== 1) {\n fig.send_message('set_dpi_ratio', { dpi_ratio: fig.ratio });\n }\n fig.send_message('refresh', {});\n };\n\n this.imageObj.onload = function () {\n if (fig.image_mode === 'full') {\n // Full images could contain transparency (where diff images\n // almost always do), so we need to clear the canvas so that\n // there is no ghosting.\n fig.context.clearRect(0, 0, fig.canvas.width, fig.canvas.height);\n }\n fig.context.drawImage(fig.imageObj, 0, 0);\n };\n\n this.imageObj.onunload = function () {\n fig.ws.close();\n };\n\n this.ws.onmessage = this._make_on_message_function(this);\n\n this.ondownload = ondownload;\n};\n\nmpl.figure.prototype._init_header = function () {\n var titlebar = document.createElement('div');\n titlebar.classList =\n 'ui-dialog-titlebar ui-widget-header ui-corner-all ui-helper-clearfix';\n var titletext = document.createElement('div');\n titletext.classList = 'ui-dialog-title';\n titletext.setAttribute(\n 'style',\n 'width: 100%; text-align: center; padding: 3px;'\n );\n titlebar.appendChild(titletext);\n this.root.appendChild(titlebar);\n this.header = titletext;\n};\n\nmpl.figure.prototype._canvas_extra_style = function (_canvas_div) {};\n\nmpl.figure.prototype._root_extra_style = function (_canvas_div) {};\n\nmpl.figure.prototype._init_canvas = function () {\n var fig = this;\n\n var canvas_div = (this.canvas_div = document.createElement('div'));\n canvas_div.setAttribute(\n 'style',\n 'border: 1px solid #ddd;' +\n 'box-sizing: content-box;' +\n 'clear: both;' +\n 'min-height: 1px;' +\n 'min-width: 1px;' +\n 'outline: 0;' +\n 'overflow: hidden;' +\n 'position: relative;' +\n 'resize: both;'\n );\n\n function on_keyboard_event_closure(name) {\n return function (event) {\n return fig.key_event(event, name);\n };\n }\n\n canvas_div.addEventListener(\n 'keydown',\n on_keyboard_event_closure('key_press')\n );\n canvas_div.addEventListener(\n 'keyup',\n on_keyboard_event_closure('key_release')\n );\n\n this._canvas_extra_style(canvas_div);\n this.root.appendChild(canvas_div);\n\n var canvas = (this.canvas = document.createElement('canvas'));\n canvas.classList.add('mpl-canvas');\n canvas.setAttribute('style', 'box-sizing: content-box;');\n\n this.context = canvas.getContext('2d');\n\n var backingStore =\n this.context.backingStorePixelRatio ||\n this.context.webkitBackingStorePixelRatio ||\n this.context.mozBackingStorePixelRatio ||\n this.context.msBackingStorePixelRatio ||\n this.context.oBackingStorePixelRatio ||\n this.context.backingStorePixelRatio ||\n 1;\n\n this.ratio = (window.devicePixelRatio || 1) / backingStore;\n\n var rubberband_canvas = (this.rubberband_canvas = document.createElement(\n 'canvas'\n ));\n rubberband_canvas.setAttribute(\n 'style',\n 'box-sizing: content-box; position: absolute; left: 0; top: 0; z-index: 1;'\n );\n\n // Apply a ponyfill if ResizeObserver is not implemented by browser.\n if (this.ResizeObserver === undefined) {\n if (window.ResizeObserver !== undefined) {\n this.ResizeObserver = window.ResizeObserver;\n } else {\n var obs = _JSXTOOLS_RESIZE_OBSERVER({});\n this.ResizeObserver = obs.ResizeObserver;\n }\n }\n\n this.resizeObserverInstance = new this.ResizeObserver(function (entries) {\n var nentries = entries.length;\n for (var i = 0; i < nentries; i++) {\n var entry = entries[i];\n var width, height;\n if (entry.contentBoxSize) {\n if (entry.contentBoxSize instanceof Array) {\n // Chrome 84 implements new version of spec.\n width = entry.contentBoxSize[0].inlineSize;\n height = entry.contentBoxSize[0].blockSize;\n } else {\n // Firefox implements old version of spec.\n width = entry.contentBoxSize.inlineSize;\n height = entry.contentBoxSize.blockSize;\n }\n } else {\n // Chrome <84 implements even older version of spec.\n width = entry.contentRect.width;\n height = entry.contentRect.height;\n }\n\n // Keep the size of the canvas and rubber band canvas in sync with\n // the canvas container.\n if (entry.devicePixelContentBoxSize) {\n // Chrome 84 implements new version of spec.\n canvas.setAttribute(\n 'width',\n entry.devicePixelContentBoxSize[0].inlineSize\n );\n canvas.setAttribute(\n 'height',\n entry.devicePixelContentBoxSize[0].blockSize\n );\n } else {\n canvas.setAttribute('width', width * fig.ratio);\n canvas.setAttribute('height', height * fig.ratio);\n }\n canvas.setAttribute(\n 'style',\n 'width: ' + width + 'px; height: ' + height + 'px;'\n );\n\n rubberband_canvas.setAttribute('width', width);\n rubberband_canvas.setAttribute('height', height);\n\n // And update the size in Python. We ignore the initial 0/0 size\n // that occurs as the element is placed into the DOM, which should\n // otherwise not happen due to the minimum size styling.\n if (fig.ws.readyState == 1 && width != 0 && height != 0) {\n fig.request_resize(width, height);\n }\n }\n });\n this.resizeObserverInstance.observe(canvas_div);\n\n function on_mouse_event_closure(name) {\n return function (event) {\n return fig.mouse_event(event, name);\n };\n }\n\n rubberband_canvas.addEventListener(\n 'mousedown',\n on_mouse_event_closure('button_press')\n );\n rubberband_canvas.addEventListener(\n 'mouseup',\n on_mouse_event_closure('button_release')\n );\n rubberband_canvas.addEventListener(\n 'dblclick',\n on_mouse_event_closure('dblclick')\n );\n // Throttle sequential mouse events to 1 every 20ms.\n rubberband_canvas.addEventListener(\n 'mousemove',\n on_mouse_event_closure('motion_notify')\n );\n\n rubberband_canvas.addEventListener(\n 'mouseenter',\n on_mouse_event_closure('figure_enter')\n );\n rubberband_canvas.addEventListener(\n 'mouseleave',\n on_mouse_event_closure('figure_leave')\n );\n\n canvas_div.addEventListener('wheel', function (event) {\n if (event.deltaY < 0) {\n event.step = 1;\n } else {\n event.step = -1;\n }\n on_mouse_event_closure('scroll')(event);\n });\n\n canvas_div.appendChild(canvas);\n canvas_div.appendChild(rubberband_canvas);\n\n this.rubberband_context = rubberband_canvas.getContext('2d');\n this.rubberband_context.strokeStyle = '#000000';\n\n this._resize_canvas = function (width, height, forward) {\n if (forward) {\n canvas_div.style.width = width + 'px';\n canvas_div.style.height = height + 'px';\n }\n };\n\n // Disable right mouse context menu.\n this.rubberband_canvas.addEventListener('contextmenu', function (_e) {\n event.preventDefault();\n return false;\n });\n\n function set_focus() {\n canvas.focus();\n canvas_div.focus();\n }\n\n window.setTimeout(set_focus, 100);\n};\n\nmpl.figure.prototype._init_toolbar = function () {\n var fig = this;\n\n var toolbar = document.createElement('div');\n toolbar.classList = 'mpl-toolbar';\n this.root.appendChild(toolbar);\n\n function on_click_closure(name) {\n return function (_event) {\n return fig.toolbar_button_onclick(name);\n };\n }\n\n function on_mouseover_closure(tooltip) {\n return function (event) {\n if (!event.currentTarget.disabled) {\n return fig.toolbar_button_onmouseover(tooltip);\n }\n };\n }\n\n fig.buttons = {};\n var buttonGroup = document.createElement('div');\n buttonGroup.classList = 'mpl-button-group';\n for (var toolbar_ind in mpl.toolbar_items) {\n var name = mpl.toolbar_items[toolbar_ind][0];\n var tooltip = mpl.toolbar_items[toolbar_ind][1];\n var image = mpl.toolbar_items[toolbar_ind][2];\n var method_name = mpl.toolbar_items[toolbar_ind][3];\n\n if (!name) {\n /* Instead of a spacer, we start a new button group. */\n if (buttonGroup.hasChildNodes()) {\n toolbar.appendChild(buttonGroup);\n }\n buttonGroup = document.createElement('div');\n buttonGroup.classList = 'mpl-button-group';\n continue;\n }\n\n var button = (fig.buttons[name] = document.createElement('button'));\n button.classList = 'mpl-widget';\n button.setAttribute('role', 'button');\n button.setAttribute('aria-disabled', 'false');\n button.addEventListener('click', on_click_closure(method_name));\n button.addEventListener('mouseover', on_mouseover_closure(tooltip));\n\n var icon_img = document.createElement('img');\n icon_img.src = '_images/' + image + '.png';\n icon_img.srcset = '_images/' + image + '_large.png 2x';\n icon_img.alt = tooltip;\n button.appendChild(icon_img);\n\n buttonGroup.appendChild(button);\n }\n\n if (buttonGroup.hasChildNodes()) {\n toolbar.appendChild(buttonGroup);\n }\n\n var fmt_picker = document.createElement('select');\n fmt_picker.classList = 'mpl-widget';\n toolbar.appendChild(fmt_picker);\n this.format_dropdown = fmt_picker;\n\n for (var ind in mpl.extensions) {\n var fmt = mpl.extensions[ind];\n var option = document.createElement('option');\n option.selected = fmt === mpl.default_extension;\n option.innerHTML = fmt;\n fmt_picker.appendChild(option);\n }\n\n var status_bar = document.createElement('span');\n status_bar.classList = 'mpl-message';\n toolbar.appendChild(status_bar);\n this.message = status_bar;\n};\n\nmpl.figure.prototype.request_resize = function (x_pixels, y_pixels) {\n // Request matplotlib to resize the figure. Matplotlib will then trigger a resize in the client,\n // which will in turn request a refresh of the image.\n this.send_message('resize', { width: x_pixels, height: y_pixels });\n};\n\nmpl.figure.prototype.send_message = function (type, properties) {\n properties['type'] = type;\n properties['figure_id'] = this.id;\n this.ws.send(JSON.stringify(properties));\n};\n\nmpl.figure.prototype.send_draw_message = function () {\n if (!this.waiting) {\n this.waiting = true;\n this.ws.send(JSON.stringify({ type: 'draw', figure_id: this.id }));\n }\n};\n\nmpl.figure.prototype.handle_save = function (fig, _msg) {\n var format_dropdown = fig.format_dropdown;\n var format = format_dropdown.options[format_dropdown.selectedIndex].value;\n fig.ondownload(fig, format);\n};\n\nmpl.figure.prototype.handle_resize = function (fig, msg) {\n var size = msg['size'];\n if (size[0] !== fig.canvas.width || size[1] !== fig.canvas.height) {\n fig._resize_canvas(size[0], size[1], msg['forward']);\n fig.send_message('refresh', {});\n }\n};\n\nmpl.figure.prototype.handle_rubberband = function (fig, msg) {\n var x0 = msg['x0'] / fig.ratio;\n var y0 = (fig.canvas.height - msg['y0']) / fig.ratio;\n var x1 = msg['x1'] / fig.ratio;\n var y1 = (fig.canvas.height - msg['y1']) / fig.ratio;\n x0 = Math.floor(x0) + 0.5;\n y0 = Math.floor(y0) + 0.5;\n x1 = Math.floor(x1) + 0.5;\n y1 = Math.floor(y1) + 0.5;\n var min_x = Math.min(x0, x1);\n var min_y = Math.min(y0, y1);\n var width = Math.abs(x1 - x0);\n var height = Math.abs(y1 - y0);\n\n fig.rubberband_context.clearRect(\n 0,\n 0,\n fig.canvas.width / fig.ratio,\n fig.canvas.height / fig.ratio\n );\n\n fig.rubberband_context.strokeRect(min_x, min_y, width, height);\n};\n\nmpl.figure.prototype.handle_figure_label = function (fig, msg) {\n // Updates the figure title.\n fig.header.textContent = msg['label'];\n};\n\nmpl.figure.prototype.handle_cursor = function (fig, msg) {\n var cursor = msg['cursor'];\n switch (cursor) {\n case 0:\n cursor = 'pointer';\n break;\n case 1:\n cursor = 'default';\n break;\n case 2:\n cursor = 'crosshair';\n break;\n case 3:\n cursor = 'move';\n break;\n }\n fig.rubberband_canvas.style.cursor = cursor;\n};\n\nmpl.figure.prototype.handle_message = function (fig, msg) {\n fig.message.textContent = msg['message'];\n};\n\nmpl.figure.prototype.handle_draw = function (fig, _msg) {\n // Request the server to send over a new figure.\n fig.send_draw_message();\n};\n\nmpl.figure.prototype.handle_image_mode = function (fig, msg) {\n fig.image_mode = msg['mode'];\n};\n\nmpl.figure.prototype.handle_history_buttons = function (fig, msg) {\n for (var key in msg) {\n if (!(key in fig.buttons)) {\n continue;\n }\n fig.buttons[key].disabled = !msg[key];\n fig.buttons[key].setAttribute('aria-disabled', !msg[key]);\n }\n};\n\nmpl.figure.prototype.handle_navigate_mode = function (fig, msg) {\n if (msg['mode'] === 'PAN') {\n fig.buttons['Pan'].classList.add('active');\n fig.buttons['Zoom'].classList.remove('active');\n } else if (msg['mode'] === 'ZOOM') {\n fig.buttons['Pan'].classList.remove('active');\n fig.buttons['Zoom'].classList.add('active');\n } else {\n fig.buttons['Pan'].classList.remove('active');\n fig.buttons['Zoom'].classList.remove('active');\n }\n};\n\nmpl.figure.prototype.updated_canvas_event = function () {\n // Called whenever the canvas gets updated.\n this.send_message('ack', {});\n};\n\n// A function to construct a web socket function for onmessage handling.\n// Called in the figure constructor.\nmpl.figure.prototype._make_on_message_function = function (fig) {\n return function socket_on_message(evt) {\n if (evt.data instanceof Blob) {\n var img = evt.data;\n if (img.type !== 'image/png') {\n /* FIXME: We get \"Resource interpreted as Image but\n * transferred with MIME type text/plain:\" errors on\n * Chrome. But how to set the MIME type? It doesn't seem\n * to be part of the websocket stream */\n img.type = 'image/png';\n }\n\n /* Free the memory for the previous frames */\n if (fig.imageObj.src) {\n (window.URL || window.webkitURL).revokeObjectURL(\n fig.imageObj.src\n );\n }\n\n fig.imageObj.src = (window.URL || window.webkitURL).createObjectURL(\n img\n );\n fig.updated_canvas_event();\n fig.waiting = false;\n return;\n } else if (\n typeof evt.data === 'string' &&\n evt.data.slice(0, 21) === 'data:image/png;base64'\n ) {\n fig.imageObj.src = evt.data;\n fig.updated_canvas_event();\n fig.waiting = false;\n return;\n }\n\n var msg = JSON.parse(evt.data);\n var msg_type = msg['type'];\n\n // Call the \"handle_{type}\" callback, which takes\n // the figure and JSON message as its only arguments.\n try {\n var callback = fig['handle_' + msg_type];\n } catch (e) {\n console.log(\n \"No handler for the '\" + msg_type + \"' message type: \",\n msg\n );\n return;\n }\n\n if (callback) {\n try {\n // console.log(\"Handling '\" + msg_type + \"' message: \", msg);\n callback(fig, msg);\n } catch (e) {\n console.log(\n \"Exception inside the 'handler_\" + msg_type + \"' callback:\",\n e,\n e.stack,\n msg\n );\n }\n }\n };\n};\n\n// from http://stackoverflow.com/questions/1114465/getting-mouse-location-in-canvas\nmpl.findpos = function (e) {\n //this section is from http://www.quirksmode.org/js/events_properties.html\n var targ;\n if (!e) {\n e = window.event;\n }\n if (e.target) {\n targ = e.target;\n } else if (e.srcElement) {\n targ = e.srcElement;\n }\n if (targ.nodeType === 3) {\n // defeat Safari bug\n targ = targ.parentNode;\n }\n\n // pageX,Y are the mouse positions relative to the document\n var boundingRect = targ.getBoundingClientRect();\n var x = e.pageX - (boundingRect.left + document.body.scrollLeft);\n var y = e.pageY - (boundingRect.top + document.body.scrollTop);\n\n return { x: x, y: y };\n};\n\n/*\n * return a copy of an object with only non-object keys\n * we need this to avoid circular references\n * http://stackoverflow.com/a/24161582/3208463\n */\nfunction simpleKeys(original) {\n return Object.keys(original).reduce(function (obj, key) {\n if (typeof original[key] !== 'object') {\n obj[key] = original[key];\n }\n return obj;\n }, {});\n}\n\nmpl.figure.prototype.mouse_event = function (event, name) {\n var canvas_pos = mpl.findpos(event);\n\n if (name === 'button_press') {\n this.canvas.focus();\n this.canvas_div.focus();\n }\n\n var x = canvas_pos.x * this.ratio;\n var y = canvas_pos.y * this.ratio;\n\n this.send_message(name, {\n x: x,\n y: y,\n button: event.button,\n step: event.step,\n guiEvent: simpleKeys(event),\n });\n\n /* This prevents the web browser from automatically changing to\n * the text insertion cursor when the button is pressed. We want\n * to control all of the cursor setting manually through the\n * 'cursor' event from matplotlib */\n event.preventDefault();\n return false;\n};\n\nmpl.figure.prototype._key_event_extra = function (_event, _name) {\n // Handle any extra behaviour associated with a key event\n};\n\nmpl.figure.prototype.key_event = function (event, name) {\n // Prevent repeat events\n if (name === 'key_press') {\n if (event.key === this._key) {\n return;\n } else {\n this._key = event.key;\n }\n }\n if (name === 'key_release') {\n this._key = null;\n }\n\n var value = '';\n if (event.ctrlKey && event.key !== 'Control') {\n value += 'ctrl+';\n }\n else if (event.altKey && event.key !== 'Alt') {\n value += 'alt+';\n }\n else if (event.shiftKey && event.key !== 'Shift') {\n value += 'shift+';\n }\n\n value += 'k' + event.key;\n\n this._key_event_extra(event, name);\n\n this.send_message(name, { key: value, guiEvent: simpleKeys(event) });\n return false;\n};\n\nmpl.figure.prototype.toolbar_button_onclick = function (name) {\n if (name === 'download') {\n this.handle_save(this, null);\n } else {\n this.send_message('toolbar_button', { name: name });\n }\n};\n\nmpl.figure.prototype.toolbar_button_onmouseover = function (tooltip) {\n this.message.textContent = tooltip;\n};\n\n///////////////// REMAINING CONTENT GENERATED BY embed_js.py /////////////////\n// prettier-ignore\nvar _JSXTOOLS_RESIZE_OBSERVER=function(A){var t,i=new WeakMap,n=new WeakMap,a=new WeakMap,r=new WeakMap,o=new Set;function s(e){if(!(this instanceof s))throw new TypeError(\"Constructor requires 'new' operator\");i.set(this,e)}function h(){throw new TypeError(\"Function is not a constructor\")}function c(e,t,i,n){e=0 in arguments?Number(arguments[0]):0,t=1 in arguments?Number(arguments[1]):0,i=2 in arguments?Number(arguments[2]):0,n=3 in arguments?Number(arguments[3]):0,this.right=(this.x=this.left=e)+(this.width=i),this.bottom=(this.y=this.top=t)+(this.height=n),Object.freeze(this)}function d(){t=requestAnimationFrame(d);var s=new WeakMap,p=new Set;o.forEach((function(t){r.get(t).forEach((function(i){var r=t instanceof window.SVGElement,o=a.get(t),d=r?0:parseFloat(o.paddingTop),f=r?0:parseFloat(o.paddingRight),l=r?0:parseFloat(o.paddingBottom),u=r?0:parseFloat(o.paddingLeft),g=r?0:parseFloat(o.borderTopWidth),m=r?0:parseFloat(o.borderRightWidth),w=r?0:parseFloat(o.borderBottomWidth),b=u+f,F=d+l,v=(r?0:parseFloat(o.borderLeftWidth))+m,W=g+w,y=r?0:t.offsetHeight-W-t.clientHeight,E=r?0:t.offsetWidth-v-t.clientWidth,R=b+v,z=F+W,M=r?t.width:parseFloat(o.width)-R-E,O=r?t.height:parseFloat(o.height)-z-y;if(n.has(t)){var k=n.get(t);if(k[0]===M&&k[1]===O)return}n.set(t,[M,O]);var S=Object.create(h.prototype);S.target=t,S.contentRect=new c(u,d,M,O),s.has(i)||(s.set(i,[]),p.add(i)),s.get(i).push(S)}))})),p.forEach((function(e){i.get(e).call(e,s.get(e),e)}))}return s.prototype.observe=function(i){if(i instanceof window.Element){r.has(i)||(r.set(i,new Set),o.add(i),a.set(i,window.getComputedStyle(i)));var n=r.get(i);n.has(this)||n.add(this),cancelAnimationFrame(t),t=requestAnimationFrame(d)}},s.prototype.unobserve=function(i){if(i instanceof window.Element&&r.has(i)){var n=r.get(i);n.has(this)&&(n.delete(this),n.size||(r.delete(i),o.delete(i))),n.size||r.delete(i),o.size||cancelAnimationFrame(t)}},A.DOMRectReadOnly=c,A.ResizeObserver=s,A.ResizeObserverEntry=h,A}; // eslint-disable-line\nmpl.toolbar_items = [[\"Home\", \"Reset original view\", \"fa fa-home icon-home\", \"home\"], [\"Back\", \"Back to previous view\", \"fa fa-arrow-left icon-arrow-left\", \"back\"], [\"Forward\", \"Forward to next view\", \"fa fa-arrow-right icon-arrow-right\", \"forward\"], [\"\", \"\", \"\", \"\"], [\"Pan\", \"Left button pans, Right button zooms\\nx/y fixes axis, CTRL fixes aspect\", \"fa fa-arrows icon-move\", \"pan\"], [\"Zoom\", \"Zoom to rectangle\\nx/y fixes axis, CTRL fixes aspect\", \"fa fa-square-o icon-check-empty\", \"zoom\"], [\"\", \"\", \"\", \"\"], [\"Download\", \"Download plot\", \"fa fa-floppy-o icon-save\", \"download\"]];\n\nmpl.extensions = [\"eps\", \"jpeg\", \"pgf\", \"pdf\", \"png\", \"ps\", \"raw\", \"svg\", \"tif\"];\n\nmpl.default_extension = \"png\";/* global mpl */\n\nvar comm_websocket_adapter = function (comm) {\n // Create a \"websocket\"-like object which calls the given IPython comm\n // object with the appropriate methods. Currently this is a non binary\n // socket, so there is still some room for performance tuning.\n var ws = {};\n\n ws.binaryType = comm.kernel.ws.binaryType;\n ws.readyState = comm.kernel.ws.readyState;\n function updateReadyState(_event) {\n if (comm.kernel.ws) {\n ws.readyState = comm.kernel.ws.readyState;\n } else {\n ws.readyState = 3; // Closed state.\n }\n }\n comm.kernel.ws.addEventListener('open', updateReadyState);\n comm.kernel.ws.addEventListener('close', updateReadyState);\n comm.kernel.ws.addEventListener('error', updateReadyState);\n\n ws.close = function () {\n comm.close();\n };\n ws.send = function (m) {\n //console.log('sending', m);\n comm.send(m);\n };\n // Register the callback with on_msg.\n comm.on_msg(function (msg) {\n //console.log('receiving', msg['content']['data'], msg);\n var data = msg['content']['data'];\n if (data['blob'] !== undefined) {\n data = {\n data: new Blob(msg['buffers'], { type: data['blob'] }),\n };\n }\n // Pass the mpl event to the overridden (by mpl) onmessage function.\n ws.onmessage(data);\n });\n return ws;\n};\n\nmpl.mpl_figure_comm = function (comm, msg) {\n // This is the function which gets called when the mpl process\n // starts-up an IPython Comm through the \"matplotlib\" channel.\n\n var id = msg.content.data.id;\n // Get hold of the div created by the display call when the Comm\n // socket was opened in Python.\n var element = document.getElementById(id);\n var ws_proxy = comm_websocket_adapter(comm);\n\n function ondownload(figure, _format) {\n window.open(figure.canvas.toDataURL());\n }\n\n var fig = new mpl.figure(id, ws_proxy, ondownload, element);\n\n // Call onopen now - mpl needs it, as it is assuming we've passed it a real\n // web socket which is closed, not our websocket->open comm proxy.\n ws_proxy.onopen();\n\n fig.parent_element = element;\n fig.cell_info = mpl.find_output_cell(\"\");\n if (!fig.cell_info) {\n console.error('Failed to find cell for figure', id, fig);\n return;\n }\n fig.cell_info[0].output_area.element.on(\n 'cleared',\n { fig: fig },\n fig._remove_fig_handler\n );\n};\n\nmpl.figure.prototype.handle_close = function (fig, msg) {\n var width = fig.canvas.width / fig.ratio;\n fig.cell_info[0].output_area.element.off(\n 'cleared',\n fig._remove_fig_handler\n );\n fig.resizeObserverInstance.unobserve(fig.canvas_div);\n\n // Update the output cell to use the data from the current canvas.\n fig.push_to_output();\n var dataURL = fig.canvas.toDataURL();\n // Re-enable the keyboard manager in IPython - without this line, in FF,\n // the notebook keyboard shortcuts fail.\n IPython.keyboard_manager.enable();\n fig.parent_element.innerHTML =\n '![](\"images/ComputeGraph.png\")
\r\n",
- "\r\n",
+ "> **IMPORTANT**: Loss function returns a number that shows how good (or bad) our network performs. It should return us one number for the whole dataset, or for the part of the dataset (minibatch). Thus after calculating cross-entropy loss for each individual component of the input vector, we need to average (or add) all components together - which is done by the call to `.mean()`.\n",
+ "\n",
+ "## Computational Graph\n",
+ "\n",
+ "\n",
+ "\n",
"Up to this moment, we have defined different classes for different layers of the network. Composition of those layers can be represented as **computational graph**. Now we can compute the loss for a given training dataset (or part of it) in the following manner:"
- ],
- "metadata": {
- "slideshow": {
- "slide_type": "slide"
- }
- }
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 28,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "1.429664938969559\n"
+ ]
+ }
+ ],
"source": [
- "z = net.forward(train_x[0:10])\r\n",
- "p = softmax.forward(z)\r\n",
- "loss = cross_ent_loss.forward(p,train_labels[0:10])\r\n",
+ "z = net.forward(train_x[0:10])\n",
+ "p = softmax.forward(z)\n",
+ "loss = cross_ent_loss.forward(p,train_labels[0:10])\n",
"print(loss)"
- ],
- "outputs": [],
- "metadata": {}
+ ]
},
{
"cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
"source": [
- "## Loss Minimization Problem and Network Training\r\n",
- "\r\n",
- "Once we have defined out network as $f_\\theta$, and given the loss function $\\mathcal{L}(Y,f_\\theta(X))$, we can consider $\\mathcal{L}$ as a function of $\\theta$ under our fixed training dataset: $\\mathcal{L}(\\theta) = \\mathcal{L}(Y,f_\\theta(X))$\r\n",
- "\r\n",
- "In this case, the network training would be a minimization problem of $\\mathcal{L}$ under argument $\\theta$:\r\n",
- "$$\r\n",
- "\\theta = \\mathrm{argmin}_{\\theta} \\mathcal{L}(Y,f_\\theta(X))\r\n",
- "$$\r\n",
- "\r\n",
- "There is a well-known method of function optimization called **gradient descent**. The idea is that we can compute a derivative (in multi-dimensional case call **gradient**) of loss function with respect to parameters, and vary parameters in such a way that the error would decrease.\r\n",
- "\r\n",
- "Gradient descent works as follows:\r\n",
- " * Initialize parameters by some random values $w^{(0)}$, $b^{(0)}$\r\n",
- " * Repeat the following step many times:\r\n",
- "\r\n",
- " $$\\begin{align}\r\n",
- " W^{(i+1)}&=W^{(i)}-\\eta\\frac{\\partial\\mathcal{L}}{\\partial W}\\\\\r\n",
- " b^{(i+1)}&=b^{(i)}-\\eta\\frac{\\partial\\mathcal{L}}{\\partial b}\r\n",
- " \\end{align}\r\n",
- " $$\r\n",
- "\r\n",
- "During training, the optimization steps are supposed to be calculated considering the whole dataset (remember that loss is calculated as a sum/average through all training samples). However, in real life we take small portions of the dataset called **minibatches**, and calculate gradients based on a subset of data. Because subset is taken randomly each time, such method is called **stochastic gradient descent** (SGD).\r\n",
+ "## Loss Minimization Problem and Network Training\n",
+ "\n",
+ "Once we have defined out network as $f_\\theta$, and given the loss function $\\mathcal{L}(Y,f_\\theta(X))$, we can consider $\\mathcal{L}$ as a function of $\\theta$ under our fixed training dataset: $\\mathcal{L}(\\theta) = \\mathcal{L}(Y,f_\\theta(X))$\n",
+ "\n",
+ "In this case, the network training would be a minimization problem of $\\mathcal{L}$ under argument $\\theta$:\n",
+ "$$\n",
+ "\\theta = \\mathrm{argmin}_{\\theta} \\mathcal{L}(Y,f_\\theta(X))\n",
+ "$$\n",
+ "\n",
+ "There is a well-known method of function optimization called **gradient descent**. The idea is that we can compute a derivative (in multi-dimensional case call **gradient**) of loss function with respect to parameters, and vary parameters in such a way that the error would decrease.\n",
+ "\n",
+ "Gradient descent works as follows:\n",
+ " * Initialize parameters by some random values $w^{(0)}$, $b^{(0)}$\n",
+ " * Repeat the following step many times:\n",
+ "\n",
+ " $$\\begin{align}\n",
+ " W^{(i+1)}&=W^{(i)}-\\eta\\frac{\\partial\\mathcal{L}}{\\partial W}\\\\\n",
+ " b^{(i+1)}&=b^{(i)}-\\eta\\frac{\\partial\\mathcal{L}}{\\partial b}\n",
+ " \\end{align}\n",
+ " $$\n",
+ "\n",
+ "During training, the optimization steps are supposed to be calculated considering the whole dataset (remember that loss is calculated as a sum/average through all training samples). However, in real life we take small portions of the dataset called **minibatches**, and calculate gradients based on a subset of data. Because subset is taken randomly each time, such method is called **stochastic gradient descent** (SGD).\n",
" "
- ],
+ ]
+ },
+ {
+ "cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "slide"
}
- }
- },
- {
- "cell_type": "markdown",
+ },
"source": [
- "## Backward Propagation\r\n",
- "\r\n",
- "\r\n",
- "\r\n",
- "$$\\def\\L{\\mathcal{L}}\\def\\zz#1#2{\\frac{\\partial#1}{\\partial#2}}\r\n",
- "\\begin{align}\r\n",
- "\\zz{\\L}{W} =& \\zz{\\L}{p}\\zz{p}{z}\\zz{z}{W}\\cr\r\n",
- "\\zz{\\L}{b} =& \\zz{\\L}{p}\\zz{p}{z}\\zz{z}{b}\r\n",
- "\\end{align}\r\n",
+ "## Backward Propagation\n",
+ "\n",
+ "\n",
+ "\n",
+ "$$\\def\\L{\\mathcal{L}}\\def\\zz#1#2{\\frac{\\partial#1}{\\partial#2}}\n",
+ "\\begin{align}\n",
+ "\\zz{\\L}{W} =& \\zz{\\L}{p}\\zz{p}{z}\\zz{z}{W}\\cr\n",
+ "\\zz{\\L}{b} =& \\zz{\\L}{p}\\zz{p}{z}\\zz{z}{b}\n",
+ "\\end{align}\n",
"$$"
- ],
+ ]
+ },
+ {
+ "cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "slide"
}
- }
- },
- {
- "cell_type": "markdown",
+ },
"source": [
- "To compute $\\partial\\mathcal{L}/\\partial W$ we can use the **chaining rule** for computing derivatives of a composite function, as you can see in the formulae above. It corresponds to the following idea:\r\n",
- "\r\n",
- "* Suppose under given input we have obtanes loss $\\Delta\\mathcal{L}$\r\n",
- "* To minimize it, we would have to adjust softmax output $p$ by value $\\Delta p = (\\partial\\mathcal{L}/\\partial p)\\Delta\\mathcal{L}$ \r\n",
- "* This corresponds to the changes to node $z$ by $\\Delta z = (\\partial\\mathcal{p}/\\partial z)\\Delta p$\r\n",
- "* To minimize this error, we need to adjust parameters accordingly: $\\Delta W = (\\partial\\mathcal{z}/\\partial W)\\Delta z$ (and the same for $b$)\r\n",
- "\r\n",
- "![](\"images/ComputeGraphGrad.PNG\")
\r\n",
- "\r\n",
- "This process starts distributing the loss error from the output of the network back to its parameters. Thus the process is called **back propagation**.\r\n",
- "\r\n",
- "One pass of the network training consists of two parts:\r\n",
- "* **Forward pass**, when we calculate the value of loss function for a given input minibatch\r\n",
+ "To compute $\\partial\\mathcal{L}/\\partial W$ we can use the **chaining rule** for computing derivatives of a composite function, as you can see in the formulae above. It corresponds to the following idea:\n",
+ "\n",
+ "* Suppose under given input we have obtanes loss $\\Delta\\mathcal{L}$\n",
+ "* To minimize it, we would have to adjust softmax output $p$ by value $\\Delta p = (\\partial\\mathcal{L}/\\partial p)\\Delta\\mathcal{L}$ \n",
+ "* This corresponds to the changes to node $z$ by $\\Delta z = (\\partial\\mathcal{p}/\\partial z)\\Delta p$\n",
+ "* To minimize this error, we need to adjust parameters accordingly: $\\Delta W = (\\partial\\mathcal{z}/\\partial W)\\Delta z$ (and the same for $b$)\n",
+ "\n",
+ "\n",
+ "\n",
+ "This process starts distributing the loss error from the output of the network back to its parameters. Thus the process is called **back propagation**.\n",
+ "\n",
+ "One pass of the network training consists of two parts:\n",
+ "* **Forward pass**, when we calculate the value of loss function for a given input minibatch\n",
"* **Backward pass**, when we try to minimize this error by distributing it back to the model parameters through the computational graph."
- ],
- "metadata": {
- "slideshow": {
- "slide_type": "slide"
- }
- }
+ ]
},
{
"cell_type": "markdown",
+ "metadata": {},
"source": [
- "### Implementation of Back Propagation\r\n",
- "\r\n",
- "* Let's add `backward` function to each of our nodes that will compute the derivative and propagate the error during the backward pass.\r\n",
- "* We also need to implement parameter updates according to the procedure described above\r\n",
- "\r\n",
- "We need to compute derivatives for each layer manually, for example for linear layer $z = x\\times W+b$:\r\n",
- "$$\\begin{align}\r\n",
- "\\frac{\\partial z}{\\partial W} &= x \\\\\r\n",
- "\\frac{\\partial z}{\\partial b} &= 1 \\\\\r\n",
- "\\end{align}$$\r\n",
- "\r\n",
- "If we need to compensate for the error $\\Delta z$ at the output of the layer, we need to update the weights accordingly:\r\n",
- "$$\\begin{align}\r\n",
- "\\Delta x &= \\Delta z \\times W \\\\\r\n",
- "\\Delta W &= \\frac{\\partial z}{\\partial W} \\Delta z = \\Delta z \\times x \\\\\r\n",
- "\\Delta b &= \\frac{\\partial z}{\\partial b} \\Delta z = \\Delta z \\\\\r\n",
- "\\end{align}$$\r\n",
- "\r\n",
+ "### Implementation of Back Propagation\n",
+ "\n",
+ "* Let's add `backward` function to each of our nodes that will compute the derivative and propagate the error during the backward pass.\n",
+ "* We also need to implement parameter updates according to the procedure described above\n",
+ "\n",
+ "We need to compute derivatives for each layer manually, for example for linear layer $z = x\\times W+b$:\n",
+ "$$\\begin{align}\n",
+ "\\frac{\\partial z}{\\partial W} &= x \\\\\n",
+ "\\frac{\\partial z}{\\partial b} &= 1 \\\\\n",
+ "\\end{align}$$\n",
+ "\n",
+ "If we need to compensate for the error $\\Delta z$ at the output of the layer, we need to update the weights accordingly:\n",
+ "$$\\begin{align}\n",
+ "\\Delta x &= \\Delta z \\times W \\\\\n",
+ "\\Delta W &= \\frac{\\partial z}{\\partial W} \\Delta z = \\Delta z \\times x \\\\\n",
+ "\\Delta b &= \\frac{\\partial z}{\\partial b} \\Delta z = \\Delta z \\\\\n",
+ "\\end{align}$$\n",
+ "\n",
"**IMPORTANT:** Calculations are done not for each training sample independently, but rather for a whole **minibatch**. Required parameter updates $\\Delta W$ and $\\Delta b$ are computed across the whole minibatch, and the respective vectors have dimensions: $x\\in\\mathbb{R}^{\\mathrm{minibatch}\\, \\times\\, \\mathrm{nclass}}$"
- ],
- "metadata": {}
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
- "source": [
- "class Linear:\r\n",
- " def __init__(self,nin,nout):\r\n",
- " self.W = np.random.normal(0, 1.0/np.sqrt(nin), (nout, nin))\r\n",
- " self.b = np.zeros((1,nout))\r\n",
- " self.dW = np.zeros_like(self.W)\r\n",
- " self.db = np.zeros_like(self.b)\r\n",
- " \r\n",
- " def forward(self, x):\r\n",
- " self.x=x\r\n",
- " return np.dot(x, self.W.T) + self.b\r\n",
- " \r\n",
- " def backward(self, dz):\r\n",
- " dx = np.dot(dz, self.W)\r\n",
- " dW = np.dot(dz.T, self.x)\r\n",
- " db = dz.sum(axis=0)\r\n",
- " self.dW = dW\r\n",
- " self.db = db\r\n",
- " return dx\r\n",
- " \r\n",
- " def update(self,lr):\r\n",
- " self.W -= lr*self.dW\r\n",
- " self.b -= lr*self.db"
- ],
+ "execution_count": 29,
+ "metadata": {},
"outputs": [],
- "metadata": {}
+ "source": [
+ "class Linear:\n",
+ " def __init__(self,nin,nout):\n",
+ " self.W = np.random.normal(0, 1.0/np.sqrt(nin), (nout, nin))\n",
+ " self.b = np.zeros((1,nout))\n",
+ " self.dW = np.zeros_like(self.W)\n",
+ " self.db = np.zeros_like(self.b)\n",
+ " \n",
+ " def forward(self, x):\n",
+ " self.x=x\n",
+ " return np.dot(x, self.W.T) + self.b\n",
+ " \n",
+ " def backward(self, dz):\n",
+ " dx = np.dot(dz, self.W)\n",
+ " dW = np.dot(dz.T, self.x)\n",
+ " db = dz.sum(axis=0)\n",
+ " self.dW = dW\n",
+ " self.db = db\n",
+ " return dx\n",
+ " \n",
+ " def update(self,lr):\n",
+ " self.W -= lr*self.dW\n",
+ " self.b -= lr*self.db"
+ ]
},
{
"cell_type": "markdown",
+ "metadata": {},
"source": [
"In the same manner we can define `backward` function for the rest of our layers:"
- ],
- "metadata": {}
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 30,
+ "metadata": {},
+ "outputs": [],
"source": [
- "class Softmax:\r\n",
- " def forward(self,z):\r\n",
- " self.z = z\r\n",
- " zmax = z.max(axis=1,keepdims=True)\r\n",
- " expz = np.exp(z-zmax)\r\n",
- " Z = expz.sum(axis=1,keepdims=True)\r\n",
- " return expz / Z\r\n",
- " def backward(self,dp):\r\n",
- " p = self.forward(self.z)\r\n",
- " pdp = p * dp\r\n",
- " return pdp - p * pdp.sum(axis=1, keepdims=True)\r\n",
- " \r\n",
- "class CrossEntropyLoss:\r\n",
- " def forward(self,p,y):\r\n",
- " self.p = p\r\n",
- " self.y = y\r\n",
- " p_of_y = p[np.arange(len(y)), y]\r\n",
- " log_prob = np.log(p_of_y)\r\n",
- " return -log_prob.mean()\r\n",
- " def backward(self,loss):\r\n",
- " dlog_softmax = np.zeros_like(self.p)\r\n",
- " dlog_softmax[np.arange(len(self.y)), self.y] -= 1.0/len(self.y)\r\n",
+ "class Softmax:\n",
+ " def forward(self,z):\n",
+ " self.z = z\n",
+ " zmax = z.max(axis=1,keepdims=True)\n",
+ " expz = np.exp(z-zmax)\n",
+ " Z = expz.sum(axis=1,keepdims=True)\n",
+ " return expz / Z\n",
+ " def backward(self,dp):\n",
+ " p = self.forward(self.z)\n",
+ " pdp = p * dp\n",
+ " return pdp - p * pdp.sum(axis=1, keepdims=True)\n",
+ " \n",
+ "class CrossEntropyLoss:\n",
+ " def forward(self,p,y):\n",
+ " self.p = p\n",
+ " self.y = y\n",
+ " p_of_y = p[np.arange(len(y)), y]\n",
+ " log_prob = np.log(p_of_y)\n",
+ " return -log_prob.mean()\n",
+ " def backward(self,loss):\n",
+ " dlog_softmax = np.zeros_like(self.p)\n",
+ " dlog_softmax[np.arange(len(self.y)), self.y] -= 1.0/len(self.y)\n",
" return dlog_softmax / self.p"
- ],
- "outputs": [],
- "metadata": {}
+ ]
},
{
"cell_type": "markdown",
+ "metadata": {},
"source": [
- "## Training the Model\r\n",
- "\r\n",
+ "## Training the Model\n",
+ "\n",
"Now we are ready to write the **training loop**, which will go through our dataset, and perform the optimization minibatch by minibatch.One complete pass through the dataset is often called **an epoch**:"
- ],
- "metadata": {}
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
- "source": [
- "lin = Linear(2,2)\r\n",
- "softmax = Softmax()\r\n",
- "cross_ent_loss = CrossEntropyLoss()\r\n",
- "\r\n",
- "learning_rate = 0.1\r\n",
- "\r\n",
- "pred = np.argmax(lin.forward(train_x),axis=1)\r\n",
- "acc = (pred==train_labels).mean()\r\n",
- "print(\"Initial accuracy: \",acc)\r\n",
- "\r\n",
- "batch_size=4\r\n",
- "for i in range(0,len(train_x),batch_size):\r\n",
- " xb = train_x[i:i+batch_size]\r\n",
- " yb = train_labels[i:i+batch_size]\r\n",
- " \r\n",
- " # forward pass\r\n",
- " z = lin.forward(xb)\r\n",
- " p = softmax.forward(z)\r\n",
- " loss = cross_ent_loss.forward(p,yb)\r\n",
- " \r\n",
- " # backward pass\r\n",
- " dp = cross_ent_loss.backward(loss)\r\n",
- " dz = softmax.backward(dp)\r\n",
- " dx = lin.backward(dz)\r\n",
- " lin.update(learning_rate)\r\n",
- " \r\n",
- "pred = np.argmax(lin.forward(train_x),axis=1)\r\n",
- "acc = (pred==train_labels).mean()\r\n",
- "print(\"Final accuracy: \",acc)\r\n",
- " "
+ "execution_count": 31,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Initial accuracy: 0.725\n",
+ "Final accuracy: 0.825\n"
+ ]
+ }
],
- "outputs": [],
- "metadata": {}
+ "source": [
+ "lin = Linear(2,2)\n",
+ "softmax = Softmax()\n",
+ "cross_ent_loss = CrossEntropyLoss()\n",
+ "\n",
+ "learning_rate = 0.1\n",
+ "\n",
+ "pred = np.argmax(lin.forward(train_x),axis=1)\n",
+ "acc = (pred==train_labels).mean()\n",
+ "print(\"Initial accuracy: \",acc)\n",
+ "\n",
+ "batch_size=4\n",
+ "for i in range(0,len(train_x),batch_size):\n",
+ " xb = train_x[i:i+batch_size]\n",
+ " yb = train_labels[i:i+batch_size]\n",
+ " \n",
+ " # forward pass\n",
+ " z = lin.forward(xb)\n",
+ " p = softmax.forward(z)\n",
+ " loss = cross_ent_loss.forward(p,yb)\n",
+ " \n",
+ " # backward pass\n",
+ " dp = cross_ent_loss.backward(loss)\n",
+ " dz = softmax.backward(dp)\n",
+ " dx = lin.backward(dz)\n",
+ " lin.update(learning_rate)\n",
+ " \n",
+ "pred = np.argmax(lin.forward(train_x),axis=1)\n",
+ "acc = (pred==train_labels).mean()\n",
+ "print(\"Final accuracy: \",acc)\n",
+ " "
+ ]
},
{
"cell_type": "markdown",
+ "metadata": {},
"source": [
- "Nice to see how we can increase accuracy of the model from about 50% to around 80% in one epoch.\r\n",
- "\r\n",
- "## Network Class\r\n",
- "\r\n",
+ "Nice to see how we can increase accuracy of the model from about 50% to around 80% in one epoch.\n",
+ "\n",
+ "## Network Class\n",
+ "\n",
"Since in many cases neural network is just a composition of layers, we can build a class that will allow us to stack layers together and make forward and backward passes through them without explicitly programming that logic. We will store the list of layers inside the `Net` class, and use `add()` function to add new layers:"
- ],
- "metadata": {}
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
- "source": [
- "class Net:\r\n",
- " def __init__(self):\r\n",
- " self.layers = []\r\n",
- " \r\n",
- " def add(self,l):\r\n",
- " self.layers.append(l)\r\n",
- " \r\n",
- " def forward(self,x):\r\n",
- " for l in self.layers:\r\n",
- " x = l.forward(x)\r\n",
- " return x\r\n",
- " \r\n",
- " def backward(self,z):\r\n",
- " for l in self.layers[::-1]:\r\n",
- " z = l.backward(z)\r\n",
- " return z\r\n",
- " \r\n",
- " def update(self,lr):\r\n",
- " for l in self.layers:\r\n",
- " if 'update' in l.__dir__():\r\n",
- " l.update(lr)"
- ],
- "outputs": [],
+ "execution_count": 32,
"metadata": {
"scrolled": true,
"slideshow": {
"slide_type": "skip"
}
- }
+ },
+ "outputs": [],
+ "source": [
+ "class Net:\n",
+ " def __init__(self):\n",
+ " self.layers = []\n",
+ " \n",
+ " def add(self,l):\n",
+ " self.layers.append(l)\n",
+ " \n",
+ " def forward(self,x):\n",
+ " for l in self.layers:\n",
+ " x = l.forward(x)\n",
+ " return x\n",
+ " \n",
+ " def backward(self,z):\n",
+ " for l in self.layers[::-1]:\n",
+ " z = l.backward(z)\n",
+ " return z\n",
+ " \n",
+ " def update(self,lr):\n",
+ " for l in self.layers:\n",
+ " if 'update' in l.__dir__():\n",
+ " l.update(lr)"
+ ]
},
{
"cell_type": "markdown",
+ "metadata": {},
"source": [
"With this `Net` class our model definition and training becomes more neat:"
- ],
- "metadata": {}
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 33,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Initial loss=0.6212072429381601, accuracy=0.6875: \n",
+ "Final loss=0.44369925927417986, accuracy=0.8: \n",
+ "Test loss=0.4767711377257787, accuracy=0.85: \n"
+ ]
+ }
+ ],
"source": [
- "net = Net()\r\n",
- "net.add(Linear(2,2))\r\n",
- "net.add(Softmax())\r\n",
- "loss = CrossEntropyLoss()\r\n",
- "\r\n",
- "def get_loss_acc(x,y,loss=CrossEntropyLoss()):\r\n",
- " p = net.forward(x)\r\n",
- " l = loss.forward(p,y)\r\n",
- " pred = np.argmax(p,axis=1)\r\n",
- " acc = (pred==y).mean()\r\n",
- " return l,acc\r\n",
- "\r\n",
- "print(\"Initial loss={}, accuracy={}: \".format(*get_loss_acc(train_x,train_labels)))\r\n",
- "\r\n",
- "def train_epoch(net, train_x, train_labels, loss=CrossEntropyLoss(), batch_size=4, lr=0.1):\r\n",
- " for i in range(0,len(train_x),batch_size):\r\n",
- " xb = train_x[i:i+batch_size]\r\n",
- " yb = train_labels[i:i+batch_size]\r\n",
- "\r\n",
- " p = net.forward(xb)\r\n",
- " l = loss.forward(p,yb)\r\n",
- " dp = loss.backward(l)\r\n",
- " dx = net.backward(dp)\r\n",
- " net.update(lr)\r\n",
- " \r\n",
- "train_epoch(net,train_x,train_labels)\r\n",
- " \r\n",
- "print(\"Final loss={}, accuracy={}: \".format(*get_loss_acc(train_x,train_labels)))\r\n",
+ "net = Net()\n",
+ "net.add(Linear(2,2))\n",
+ "net.add(Softmax())\n",
+ "loss = CrossEntropyLoss()\n",
+ "\n",
+ "def get_loss_acc(x,y,loss=CrossEntropyLoss()):\n",
+ " p = net.forward(x)\n",
+ " l = loss.forward(p,y)\n",
+ " pred = np.argmax(p,axis=1)\n",
+ " acc = (pred==y).mean()\n",
+ " return l,acc\n",
+ "\n",
+ "print(\"Initial loss={}, accuracy={}: \".format(*get_loss_acc(train_x,train_labels)))\n",
+ "\n",
+ "def train_epoch(net, train_x, train_labels, loss=CrossEntropyLoss(), batch_size=4, lr=0.1):\n",
+ " for i in range(0,len(train_x),batch_size):\n",
+ " xb = train_x[i:i+batch_size]\n",
+ " yb = train_labels[i:i+batch_size]\n",
+ "\n",
+ " p = net.forward(xb)\n",
+ " l = loss.forward(p,yb)\n",
+ " dp = loss.backward(l)\n",
+ " dx = net.backward(dp)\n",
+ " net.update(lr)\n",
+ " \n",
+ "train_epoch(net,train_x,train_labels)\n",
+ " \n",
+ "print(\"Final loss={}, accuracy={}: \".format(*get_loss_acc(train_x,train_labels)))\n",
"print(\"Test loss={}, accuracy={}: \".format(*get_loss_acc(test_x,test_labels)))"
- ],
- "outputs": [],
- "metadata": {}
+ ]
},
{
"cell_type": "markdown",
+ "metadata": {},
"source": [
- "## Plotting the Training Process\r\n",
- "\r\n",
- "It would be nice to see visually how the network is being trained! We will define a `train_and_plot` function for that. To visualize the state of the network we will use level map, i.e. we will represent different values of the network output using different colors.\r\n",
- "\r\n",
+ "## Plotting the Training Process\n",
+ "\n",
+ "It would be nice to see visually how the network is being trained! We will define a `train_and_plot` function for that. To visualize the state of the network we will use level map, i.e. we will represent different values of the network output using different colors.\n",
+ "\n",
"> Do not worry if you do not understand some of the plotting code below - it is more important to understand the underlying neural network concepts."
- ],
- "metadata": {}
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 34,
+ "metadata": {
+ "slideshow": {
+ "slide_type": "skip"
+ }
+ },
+ "outputs": [],
"source": [
- "def train_and_plot(n_epoch, net, loss=CrossEntropyLoss(), batch_size=4, lr=0.1):\r\n",
- " fig, ax = plt.subplots(2, 1)\r\n",
- " ax[0].set_xlim(0, n_epoch + 1)\r\n",
- " ax[0].set_ylim(0,1)\r\n",
- "\r\n",
- " train_acc = np.empty((n_epoch, 3))\r\n",
- " train_acc[:] = np.NAN\r\n",
- " valid_acc = np.empty((n_epoch, 3))\r\n",
- " valid_acc[:] = np.NAN\r\n",
- "\r\n",
- " for epoch in range(1, n_epoch + 1):\r\n",
- "\r\n",
- " train_epoch(net,train_x,train_labels,loss,batch_size,lr)\r\n",
- " tloss, taccuracy = get_loss_acc(train_x,train_labels,loss)\r\n",
- " train_acc[epoch-1, :] = [epoch, tloss, taccuracy]\r\n",
- " vloss, vaccuracy = get_loss_acc(test_x,test_labels,loss)\r\n",
- " valid_acc[epoch-1, :] = [epoch, vloss, vaccuracy]\r\n",
- " \r\n",
- " ax[0].set_ylim(0, max(max(train_acc[:, 2]), max(valid_acc[:, 2])) * 1.1)\r\n",
- "\r\n",
- " plot_training_progress(train_acc[:, 0], (train_acc[:, 2],\r\n",
- " valid_acc[:, 2]), fig, ax[0])\r\n",
- " plot_decision_boundary(net, fig, ax[1])\r\n",
- " fig.canvas.draw()\r\n",
- " fig.canvas.flush_events()\r\n",
- "\r\n",
+ "def train_and_plot(n_epoch, net, loss=CrossEntropyLoss(), batch_size=4, lr=0.1):\n",
+ " fig, ax = plt.subplots(2, 1)\n",
+ " ax[0].set_xlim(0, n_epoch + 1)\n",
+ " ax[0].set_ylim(0,1)\n",
+ "\n",
+ " train_acc = np.empty((n_epoch, 3))\n",
+ " train_acc[:] = np.NAN\n",
+ " valid_acc = np.empty((n_epoch, 3))\n",
+ " valid_acc[:] = np.NAN\n",
+ "\n",
+ " for epoch in range(1, n_epoch + 1):\n",
+ "\n",
+ " train_epoch(net,train_x,train_labels,loss,batch_size,lr)\n",
+ " tloss, taccuracy = get_loss_acc(train_x,train_labels,loss)\n",
+ " train_acc[epoch-1, :] = [epoch, tloss, taccuracy]\n",
+ " vloss, vaccuracy = get_loss_acc(test_x,test_labels,loss)\n",
+ " valid_acc[epoch-1, :] = [epoch, vloss, vaccuracy]\n",
+ " \n",
+ " ax[0].set_ylim(0, max(max(train_acc[:, 2]), max(valid_acc[:, 2])) * 1.1)\n",
+ "\n",
+ " plot_training_progress(train_acc[:, 0], (train_acc[:, 2],\n",
+ " valid_acc[:, 2]), fig, ax[0])\n",
+ " plot_decision_boundary(net, fig, ax[1])\n",
+ " fig.canvas.draw()\n",
+ " fig.canvas.flush_events()\n",
+ "\n",
" return train_acc, valid_acc"
- ],
- "outputs": [],
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 35,
"metadata": {
"slideshow": {
"slide_type": "skip"
}
- }
- },
- {
- "cell_type": "code",
- "execution_count": null,
+ },
+ "outputs": [],
"source": [
- "import matplotlib.cm as cm\r\n",
- "\r\n",
- "def plot_decision_boundary(net, fig, ax):\r\n",
- " draw_colorbar = True\r\n",
- " # remove previous plot\r\n",
- " while ax.collections:\r\n",
- " ax.collections.pop()\r\n",
- " draw_colorbar = False\r\n",
- "\r\n",
- " # generate countour grid\r\n",
- " x_min, x_max = train_x[:, 0].min() - 1, train_x[:, 0].max() + 1\r\n",
- " y_min, y_max = train_x[:, 1].min() - 1, train_x[:, 1].max() + 1\r\n",
- " xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.1),\r\n",
- " np.arange(y_min, y_max, 0.1))\r\n",
- " grid_points = np.c_[xx.ravel().astype('float32'), yy.ravel().astype('float32')]\r\n",
- " n_classes = max(train_labels)+1\r\n",
- " while train_x.shape[1] > grid_points.shape[1]:\r\n",
- " # pad dimensions (plot only the first two)\r\n",
- " grid_points = np.c_[grid_points,\r\n",
- " np.empty(len(xx.ravel())).astype('float32')]\r\n",
- " grid_points[:, -1].fill(train_x[:, grid_points.shape[1]-1].mean())\r\n",
- "\r\n",
- " # evaluate predictions\r\n",
- " prediction = np.array(net.forward(grid_points))\r\n",
- " # for two classes: prediction difference\r\n",
- " if (n_classes == 2):\r\n",
- " Z = np.array([0.5+(p[0]-p[1])/2.0 for p in prediction]).reshape(xx.shape)\r\n",
- " else:\r\n",
- " Z = np.array([p.argsort()[-1]/float(n_classes-1) for p in prediction]).reshape(xx.shape)\r\n",
- " \r\n",
- " # draw contour\r\n",
- " levels = np.linspace(0, 1, 40)\r\n",
- " cs = ax.contourf(xx, yy, Z, alpha=0.4, levels = levels)\r\n",
- " if draw_colorbar:\r\n",
- " fig.colorbar(cs, ax=ax, ticks = [0, 0.5, 1])\r\n",
- " c_map = [cm.jet(x) for x in np.linspace(0.0, 1.0, n_classes) ]\r\n",
- " colors = [c_map[l] for l in train_labels]\r\n",
+ "import matplotlib.cm as cm\n",
+ "\n",
+ "def plot_decision_boundary(net, fig, ax):\n",
+ " draw_colorbar = True\n",
+ " # remove previous plot\n",
+ " while ax.collections:\n",
+ " ax.collections.pop()\n",
+ " draw_colorbar = False\n",
+ "\n",
+ " # generate countour grid\n",
+ " x_min, x_max = train_x[:, 0].min() - 1, train_x[:, 0].max() + 1\n",
+ " y_min, y_max = train_x[:, 1].min() - 1, train_x[:, 1].max() + 1\n",
+ " xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.1),\n",
+ " np.arange(y_min, y_max, 0.1))\n",
+ " grid_points = np.c_[xx.ravel().astype('float32'), yy.ravel().astype('float32')]\n",
+ " n_classes = max(train_labels)+1\n",
+ " while train_x.shape[1] > grid_points.shape[1]:\n",
+ " # pad dimensions (plot only the first two)\n",
+ " grid_points = np.c_[grid_points,\n",
+ " np.empty(len(xx.ravel())).astype('float32')]\n",
+ " grid_points[:, -1].fill(train_x[:, grid_points.shape[1]-1].mean())\n",
+ "\n",
+ " # evaluate predictions\n",
+ " prediction = np.array(net.forward(grid_points))\n",
+ " # for two classes: prediction difference\n",
+ " if (n_classes == 2):\n",
+ " Z = np.array([0.5+(p[0]-p[1])/2.0 for p in prediction]).reshape(xx.shape)\n",
+ " else:\n",
+ " Z = np.array([p.argsort()[-1]/float(n_classes-1) for p in prediction]).reshape(xx.shape)\n",
+ " \n",
+ " # draw contour\n",
+ " levels = np.linspace(0, 1, 40)\n",
+ " cs = ax.contourf(xx, yy, Z, alpha=0.4, levels = levels)\n",
+ " if draw_colorbar:\n",
+ " fig.colorbar(cs, ax=ax, ticks = [0, 0.5, 1])\n",
+ " c_map = [cm.jet(x) for x in np.linspace(0.0, 1.0, n_classes) ]\n",
+ " colors = [c_map[l] for l in train_labels]\n",
" ax.scatter(train_x[:, 0], train_x[:, 1], marker='o', c=colors, s=60, alpha = 0.5)"
- ],
- "outputs": [],
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
"metadata": {
"slideshow": {
"slide_type": "skip"
}
- }
- },
- {
- "cell_type": "code",
- "execution_count": null,
+ },
+ "outputs": [],
"source": [
- "def plot_training_progress(x, y_data, fig, ax):\r\n",
- " styles = ['k--', 'g-']\r\n",
- " # remove previous plot\r\n",
- " while ax.lines:\r\n",
- " ax.lines.pop()\r\n",
- " # draw updated lines\r\n",
- " for i in range(len(y_data)):\r\n",
- " ax.plot(x, y_data[i], styles[i])\r\n",
- " ax.legend(ax.lines, ['training accuracy', 'validation accuracy'],\r\n",
+ "def plot_training_progress(x, y_data, fig, ax):\n",
+ " styles = ['k--', 'g-']\n",
+ " # remove previous plot\n",
+ " while ax.lines:\n",
+ " ax.lines.pop()\n",
+ " # draw updated lines\n",
+ " for i in range(len(y_data)):\n",
+ " ax.plot(x, y_data[i], styles[i])\n",
+ " ax.legend(ax.lines, ['training accuracy', 'validation accuracy'],\n",
" loc='upper center', ncol = 2)"
- ],
- "outputs": [],
- "metadata": {
- "slideshow": {
- "slide_type": "skip"
- }
- }
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 37,
+ "metadata": {
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "application/javascript": "/* Put everything inside the global mpl namespace */\n/* global mpl */\nwindow.mpl = {};\n\nmpl.get_websocket_type = function () {\n if (typeof WebSocket !== 'undefined') {\n return WebSocket;\n } else if (typeof MozWebSocket !== 'undefined') {\n return MozWebSocket;\n } else {\n alert(\n 'Your browser does not have WebSocket support. ' +\n 'Please try Chrome, Safari or Firefox ≥ 6. ' +\n 'Firefox 4 and 5 are also supported but you ' +\n 'have to enable WebSockets in about:config.'\n );\n }\n};\n\nmpl.figure = function (figure_id, websocket, ondownload, parent_element) {\n this.id = figure_id;\n\n this.ws = websocket;\n\n this.supports_binary = this.ws.binaryType !== undefined;\n\n if (!this.supports_binary) {\n var warnings = document.getElementById('mpl-warnings');\n if (warnings) {\n warnings.style.display = 'block';\n warnings.textContent =\n 'This browser does not support binary websocket messages. ' +\n 'Performance may be slow.';\n }\n }\n\n this.imageObj = new Image();\n\n this.context = undefined;\n this.message = undefined;\n this.canvas = undefined;\n this.rubberband_canvas = undefined;\n this.rubberband_context = undefined;\n this.format_dropdown = undefined;\n\n this.image_mode = 'full';\n\n this.root = document.createElement('div');\n this.root.setAttribute('style', 'display: inline-block');\n this._root_extra_style(this.root);\n\n parent_element.appendChild(this.root);\n\n this._init_header(this);\n this._init_canvas(this);\n this._init_toolbar(this);\n\n var fig = this;\n\n this.waiting = false;\n\n this.ws.onopen = function () {\n fig.send_message('supports_binary', { value: fig.supports_binary });\n fig.send_message('send_image_mode', {});\n if (fig.ratio !== 1) {\n fig.send_message('set_dpi_ratio', { dpi_ratio: fig.ratio });\n }\n fig.send_message('refresh', {});\n };\n\n this.imageObj.onload = function () {\n if (fig.image_mode === 'full') {\n // Full images could contain transparency (where diff images\n // almost always do), so we need to clear the canvas so that\n // there is no ghosting.\n fig.context.clearRect(0, 0, fig.canvas.width, fig.canvas.height);\n }\n fig.context.drawImage(fig.imageObj, 0, 0);\n };\n\n this.imageObj.onunload = function () {\n fig.ws.close();\n };\n\n this.ws.onmessage = this._make_on_message_function(this);\n\n this.ondownload = ondownload;\n};\n\nmpl.figure.prototype._init_header = function () {\n var titlebar = document.createElement('div');\n titlebar.classList =\n 'ui-dialog-titlebar ui-widget-header ui-corner-all ui-helper-clearfix';\n var titletext = document.createElement('div');\n titletext.classList = 'ui-dialog-title';\n titletext.setAttribute(\n 'style',\n 'width: 100%; text-align: center; padding: 3px;'\n );\n titlebar.appendChild(titletext);\n this.root.appendChild(titlebar);\n this.header = titletext;\n};\n\nmpl.figure.prototype._canvas_extra_style = function (_canvas_div) {};\n\nmpl.figure.prototype._root_extra_style = function (_canvas_div) {};\n\nmpl.figure.prototype._init_canvas = function () {\n var fig = this;\n\n var canvas_div = (this.canvas_div = document.createElement('div'));\n canvas_div.setAttribute(\n 'style',\n 'border: 1px solid #ddd;' +\n 'box-sizing: content-box;' +\n 'clear: both;' +\n 'min-height: 1px;' +\n 'min-width: 1px;' +\n 'outline: 0;' +\n 'overflow: hidden;' +\n 'position: relative;' +\n 'resize: both;'\n );\n\n function on_keyboard_event_closure(name) {\n return function (event) {\n return fig.key_event(event, name);\n };\n }\n\n canvas_div.addEventListener(\n 'keydown',\n on_keyboard_event_closure('key_press')\n );\n canvas_div.addEventListener(\n 'keyup',\n on_keyboard_event_closure('key_release')\n );\n\n this._canvas_extra_style(canvas_div);\n this.root.appendChild(canvas_div);\n\n var canvas = (this.canvas = document.createElement('canvas'));\n canvas.classList.add('mpl-canvas');\n canvas.setAttribute('style', 'box-sizing: content-box;');\n\n this.context = canvas.getContext('2d');\n\n var backingStore =\n this.context.backingStorePixelRatio ||\n this.context.webkitBackingStorePixelRatio ||\n this.context.mozBackingStorePixelRatio ||\n this.context.msBackingStorePixelRatio ||\n this.context.oBackingStorePixelRatio ||\n this.context.backingStorePixelRatio ||\n 1;\n\n this.ratio = (window.devicePixelRatio || 1) / backingStore;\n\n var rubberband_canvas = (this.rubberband_canvas = document.createElement(\n 'canvas'\n ));\n rubberband_canvas.setAttribute(\n 'style',\n 'box-sizing: content-box; position: absolute; left: 0; top: 0; z-index: 1;'\n );\n\n // Apply a ponyfill if ResizeObserver is not implemented by browser.\n if (this.ResizeObserver === undefined) {\n if (window.ResizeObserver !== undefined) {\n this.ResizeObserver = window.ResizeObserver;\n } else {\n var obs = _JSXTOOLS_RESIZE_OBSERVER({});\n this.ResizeObserver = obs.ResizeObserver;\n }\n }\n\n this.resizeObserverInstance = new this.ResizeObserver(function (entries) {\n var nentries = entries.length;\n for (var i = 0; i < nentries; i++) {\n var entry = entries[i];\n var width, height;\n if (entry.contentBoxSize) {\n if (entry.contentBoxSize instanceof Array) {\n // Chrome 84 implements new version of spec.\n width = entry.contentBoxSize[0].inlineSize;\n height = entry.contentBoxSize[0].blockSize;\n } else {\n // Firefox implements old version of spec.\n width = entry.contentBoxSize.inlineSize;\n height = entry.contentBoxSize.blockSize;\n }\n } else {\n // Chrome <84 implements even older version of spec.\n width = entry.contentRect.width;\n height = entry.contentRect.height;\n }\n\n // Keep the size of the canvas and rubber band canvas in sync with\n // the canvas container.\n if (entry.devicePixelContentBoxSize) {\n // Chrome 84 implements new version of spec.\n canvas.setAttribute(\n 'width',\n entry.devicePixelContentBoxSize[0].inlineSize\n );\n canvas.setAttribute(\n 'height',\n entry.devicePixelContentBoxSize[0].blockSize\n );\n } else {\n canvas.setAttribute('width', width * fig.ratio);\n canvas.setAttribute('height', height * fig.ratio);\n }\n canvas.setAttribute(\n 'style',\n 'width: ' + width + 'px; height: ' + height + 'px;'\n );\n\n rubberband_canvas.setAttribute('width', width);\n rubberband_canvas.setAttribute('height', height);\n\n // And update the size in Python. We ignore the initial 0/0 size\n // that occurs as the element is placed into the DOM, which should\n // otherwise not happen due to the minimum size styling.\n if (fig.ws.readyState == 1 && width != 0 && height != 0) {\n fig.request_resize(width, height);\n }\n }\n });\n this.resizeObserverInstance.observe(canvas_div);\n\n function on_mouse_event_closure(name) {\n return function (event) {\n return fig.mouse_event(event, name);\n };\n }\n\n rubberband_canvas.addEventListener(\n 'mousedown',\n on_mouse_event_closure('button_press')\n );\n rubberband_canvas.addEventListener(\n 'mouseup',\n on_mouse_event_closure('button_release')\n );\n rubberband_canvas.addEventListener(\n 'dblclick',\n on_mouse_event_closure('dblclick')\n );\n // Throttle sequential mouse events to 1 every 20ms.\n rubberband_canvas.addEventListener(\n 'mousemove',\n on_mouse_event_closure('motion_notify')\n );\n\n rubberband_canvas.addEventListener(\n 'mouseenter',\n on_mouse_event_closure('figure_enter')\n );\n rubberband_canvas.addEventListener(\n 'mouseleave',\n on_mouse_event_closure('figure_leave')\n );\n\n canvas_div.addEventListener('wheel', function (event) {\n if (event.deltaY < 0) {\n event.step = 1;\n } else {\n event.step = -1;\n }\n on_mouse_event_closure('scroll')(event);\n });\n\n canvas_div.appendChild(canvas);\n canvas_div.appendChild(rubberband_canvas);\n\n this.rubberband_context = rubberband_canvas.getContext('2d');\n this.rubberband_context.strokeStyle = '#000000';\n\n this._resize_canvas = function (width, height, forward) {\n if (forward) {\n canvas_div.style.width = width + 'px';\n canvas_div.style.height = height + 'px';\n }\n };\n\n // Disable right mouse context menu.\n this.rubberband_canvas.addEventListener('contextmenu', function (_e) {\n event.preventDefault();\n return false;\n });\n\n function set_focus() {\n canvas.focus();\n canvas_div.focus();\n }\n\n window.setTimeout(set_focus, 100);\n};\n\nmpl.figure.prototype._init_toolbar = function () {\n var fig = this;\n\n var toolbar = document.createElement('div');\n toolbar.classList = 'mpl-toolbar';\n this.root.appendChild(toolbar);\n\n function on_click_closure(name) {\n return function (_event) {\n return fig.toolbar_button_onclick(name);\n };\n }\n\n function on_mouseover_closure(tooltip) {\n return function (event) {\n if (!event.currentTarget.disabled) {\n return fig.toolbar_button_onmouseover(tooltip);\n }\n };\n }\n\n fig.buttons = {};\n var buttonGroup = document.createElement('div');\n buttonGroup.classList = 'mpl-button-group';\n for (var toolbar_ind in mpl.toolbar_items) {\n var name = mpl.toolbar_items[toolbar_ind][0];\n var tooltip = mpl.toolbar_items[toolbar_ind][1];\n var image = mpl.toolbar_items[toolbar_ind][2];\n var method_name = mpl.toolbar_items[toolbar_ind][3];\n\n if (!name) {\n /* Instead of a spacer, we start a new button group. */\n if (buttonGroup.hasChildNodes()) {\n toolbar.appendChild(buttonGroup);\n }\n buttonGroup = document.createElement('div');\n buttonGroup.classList = 'mpl-button-group';\n continue;\n }\n\n var button = (fig.buttons[name] = document.createElement('button'));\n button.classList = 'mpl-widget';\n button.setAttribute('role', 'button');\n button.setAttribute('aria-disabled', 'false');\n button.addEventListener('click', on_click_closure(method_name));\n button.addEventListener('mouseover', on_mouseover_closure(tooltip));\n\n var icon_img = document.createElement('img');\n icon_img.src = '_images/' + image + '.png';\n icon_img.srcset = '_images/' + image + '_large.png 2x';\n icon_img.alt = tooltip;\n button.appendChild(icon_img);\n\n buttonGroup.appendChild(button);\n }\n\n if (buttonGroup.hasChildNodes()) {\n toolbar.appendChild(buttonGroup);\n }\n\n var fmt_picker = document.createElement('select');\n fmt_picker.classList = 'mpl-widget';\n toolbar.appendChild(fmt_picker);\n this.format_dropdown = fmt_picker;\n\n for (var ind in mpl.extensions) {\n var fmt = mpl.extensions[ind];\n var option = document.createElement('option');\n option.selected = fmt === mpl.default_extension;\n option.innerHTML = fmt;\n fmt_picker.appendChild(option);\n }\n\n var status_bar = document.createElement('span');\n status_bar.classList = 'mpl-message';\n toolbar.appendChild(status_bar);\n this.message = status_bar;\n};\n\nmpl.figure.prototype.request_resize = function (x_pixels, y_pixels) {\n // Request matplotlib to resize the figure. Matplotlib will then trigger a resize in the client,\n // which will in turn request a refresh of the image.\n this.send_message('resize', { width: x_pixels, height: y_pixels });\n};\n\nmpl.figure.prototype.send_message = function (type, properties) {\n properties['type'] = type;\n properties['figure_id'] = this.id;\n this.ws.send(JSON.stringify(properties));\n};\n\nmpl.figure.prototype.send_draw_message = function () {\n if (!this.waiting) {\n this.waiting = true;\n this.ws.send(JSON.stringify({ type: 'draw', figure_id: this.id }));\n }\n};\n\nmpl.figure.prototype.handle_save = function (fig, _msg) {\n var format_dropdown = fig.format_dropdown;\n var format = format_dropdown.options[format_dropdown.selectedIndex].value;\n fig.ondownload(fig, format);\n};\n\nmpl.figure.prototype.handle_resize = function (fig, msg) {\n var size = msg['size'];\n if (size[0] !== fig.canvas.width || size[1] !== fig.canvas.height) {\n fig._resize_canvas(size[0], size[1], msg['forward']);\n fig.send_message('refresh', {});\n }\n};\n\nmpl.figure.prototype.handle_rubberband = function (fig, msg) {\n var x0 = msg['x0'] / fig.ratio;\n var y0 = (fig.canvas.height - msg['y0']) / fig.ratio;\n var x1 = msg['x1'] / fig.ratio;\n var y1 = (fig.canvas.height - msg['y1']) / fig.ratio;\n x0 = Math.floor(x0) + 0.5;\n y0 = Math.floor(y0) + 0.5;\n x1 = Math.floor(x1) + 0.5;\n y1 = Math.floor(y1) + 0.5;\n var min_x = Math.min(x0, x1);\n var min_y = Math.min(y0, y1);\n var width = Math.abs(x1 - x0);\n var height = Math.abs(y1 - y0);\n\n fig.rubberband_context.clearRect(\n 0,\n 0,\n fig.canvas.width / fig.ratio,\n fig.canvas.height / fig.ratio\n );\n\n fig.rubberband_context.strokeRect(min_x, min_y, width, height);\n};\n\nmpl.figure.prototype.handle_figure_label = function (fig, msg) {\n // Updates the figure title.\n fig.header.textContent = msg['label'];\n};\n\nmpl.figure.prototype.handle_cursor = function (fig, msg) {\n var cursor = msg['cursor'];\n switch (cursor) {\n case 0:\n cursor = 'pointer';\n break;\n case 1:\n cursor = 'default';\n break;\n case 2:\n cursor = 'crosshair';\n break;\n case 3:\n cursor = 'move';\n break;\n }\n fig.rubberband_canvas.style.cursor = cursor;\n};\n\nmpl.figure.prototype.handle_message = function (fig, msg) {\n fig.message.textContent = msg['message'];\n};\n\nmpl.figure.prototype.handle_draw = function (fig, _msg) {\n // Request the server to send over a new figure.\n fig.send_draw_message();\n};\n\nmpl.figure.prototype.handle_image_mode = function (fig, msg) {\n fig.image_mode = msg['mode'];\n};\n\nmpl.figure.prototype.handle_history_buttons = function (fig, msg) {\n for (var key in msg) {\n if (!(key in fig.buttons)) {\n continue;\n }\n fig.buttons[key].disabled = !msg[key];\n fig.buttons[key].setAttribute('aria-disabled', !msg[key]);\n }\n};\n\nmpl.figure.prototype.handle_navigate_mode = function (fig, msg) {\n if (msg['mode'] === 'PAN') {\n fig.buttons['Pan'].classList.add('active');\n fig.buttons['Zoom'].classList.remove('active');\n } else if (msg['mode'] === 'ZOOM') {\n fig.buttons['Pan'].classList.remove('active');\n fig.buttons['Zoom'].classList.add('active');\n } else {\n fig.buttons['Pan'].classList.remove('active');\n fig.buttons['Zoom'].classList.remove('active');\n }\n};\n\nmpl.figure.prototype.updated_canvas_event = function () {\n // Called whenever the canvas gets updated.\n this.send_message('ack', {});\n};\n\n// A function to construct a web socket function for onmessage handling.\n// Called in the figure constructor.\nmpl.figure.prototype._make_on_message_function = function (fig) {\n return function socket_on_message(evt) {\n if (evt.data instanceof Blob) {\n var img = evt.data;\n if (img.type !== 'image/png') {\n /* FIXME: We get \"Resource interpreted as Image but\n * transferred with MIME type text/plain:\" errors on\n * Chrome. But how to set the MIME type? It doesn't seem\n * to be part of the websocket stream */\n img.type = 'image/png';\n }\n\n /* Free the memory for the previous frames */\n if (fig.imageObj.src) {\n (window.URL || window.webkitURL).revokeObjectURL(\n fig.imageObj.src\n );\n }\n\n fig.imageObj.src = (window.URL || window.webkitURL).createObjectURL(\n img\n );\n fig.updated_canvas_event();\n fig.waiting = false;\n return;\n } else if (\n typeof evt.data === 'string' &&\n evt.data.slice(0, 21) === 'data:image/png;base64'\n ) {\n fig.imageObj.src = evt.data;\n fig.updated_canvas_event();\n fig.waiting = false;\n return;\n }\n\n var msg = JSON.parse(evt.data);\n var msg_type = msg['type'];\n\n // Call the \"handle_{type}\" callback, which takes\n // the figure and JSON message as its only arguments.\n try {\n var callback = fig['handle_' + msg_type];\n } catch (e) {\n console.log(\n \"No handler for the '\" + msg_type + \"' message type: \",\n msg\n );\n return;\n }\n\n if (callback) {\n try {\n // console.log(\"Handling '\" + msg_type + \"' message: \", msg);\n callback(fig, msg);\n } catch (e) {\n console.log(\n \"Exception inside the 'handler_\" + msg_type + \"' callback:\",\n e,\n e.stack,\n msg\n );\n }\n }\n };\n};\n\n// from http://stackoverflow.com/questions/1114465/getting-mouse-location-in-canvas\nmpl.findpos = function (e) {\n //this section is from http://www.quirksmode.org/js/events_properties.html\n var targ;\n if (!e) {\n e = window.event;\n }\n if (e.target) {\n targ = e.target;\n } else if (e.srcElement) {\n targ = e.srcElement;\n }\n if (targ.nodeType === 3) {\n // defeat Safari bug\n targ = targ.parentNode;\n }\n\n // pageX,Y are the mouse positions relative to the document\n var boundingRect = targ.getBoundingClientRect();\n var x = e.pageX - (boundingRect.left + document.body.scrollLeft);\n var y = e.pageY - (boundingRect.top + document.body.scrollTop);\n\n return { x: x, y: y };\n};\n\n/*\n * return a copy of an object with only non-object keys\n * we need this to avoid circular references\n * http://stackoverflow.com/a/24161582/3208463\n */\nfunction simpleKeys(original) {\n return Object.keys(original).reduce(function (obj, key) {\n if (typeof original[key] !== 'object') {\n obj[key] = original[key];\n }\n return obj;\n }, {});\n}\n\nmpl.figure.prototype.mouse_event = function (event, name) {\n var canvas_pos = mpl.findpos(event);\n\n if (name === 'button_press') {\n this.canvas.focus();\n this.canvas_div.focus();\n }\n\n var x = canvas_pos.x * this.ratio;\n var y = canvas_pos.y * this.ratio;\n\n this.send_message(name, {\n x: x,\n y: y,\n button: event.button,\n step: event.step,\n guiEvent: simpleKeys(event),\n });\n\n /* This prevents the web browser from automatically changing to\n * the text insertion cursor when the button is pressed. We want\n * to control all of the cursor setting manually through the\n * 'cursor' event from matplotlib */\n event.preventDefault();\n return false;\n};\n\nmpl.figure.prototype._key_event_extra = function (_event, _name) {\n // Handle any extra behaviour associated with a key event\n};\n\nmpl.figure.prototype.key_event = function (event, name) {\n // Prevent repeat events\n if (name === 'key_press') {\n if (event.key === this._key) {\n return;\n } else {\n this._key = event.key;\n }\n }\n if (name === 'key_release') {\n this._key = null;\n }\n\n var value = '';\n if (event.ctrlKey && event.key !== 'Control') {\n value += 'ctrl+';\n }\n else if (event.altKey && event.key !== 'Alt') {\n value += 'alt+';\n }\n else if (event.shiftKey && event.key !== 'Shift') {\n value += 'shift+';\n }\n\n value += 'k' + event.key;\n\n this._key_event_extra(event, name);\n\n this.send_message(name, { key: value, guiEvent: simpleKeys(event) });\n return false;\n};\n\nmpl.figure.prototype.toolbar_button_onclick = function (name) {\n if (name === 'download') {\n this.handle_save(this, null);\n } else {\n this.send_message('toolbar_button', { name: name });\n }\n};\n\nmpl.figure.prototype.toolbar_button_onmouseover = function (tooltip) {\n this.message.textContent = tooltip;\n};\n\n///////////////// REMAINING CONTENT GENERATED BY embed_js.py /////////////////\n// prettier-ignore\nvar _JSXTOOLS_RESIZE_OBSERVER=function(A){var t,i=new WeakMap,n=new WeakMap,a=new WeakMap,r=new WeakMap,o=new Set;function s(e){if(!(this instanceof s))throw new TypeError(\"Constructor requires 'new' operator\");i.set(this,e)}function h(){throw new TypeError(\"Function is not a constructor\")}function c(e,t,i,n){e=0 in arguments?Number(arguments[0]):0,t=1 in arguments?Number(arguments[1]):0,i=2 in arguments?Number(arguments[2]):0,n=3 in arguments?Number(arguments[3]):0,this.right=(this.x=this.left=e)+(this.width=i),this.bottom=(this.y=this.top=t)+(this.height=n),Object.freeze(this)}function d(){t=requestAnimationFrame(d);var s=new WeakMap,p=new Set;o.forEach((function(t){r.get(t).forEach((function(i){var r=t instanceof window.SVGElement,o=a.get(t),d=r?0:parseFloat(o.paddingTop),f=r?0:parseFloat(o.paddingRight),l=r?0:parseFloat(o.paddingBottom),u=r?0:parseFloat(o.paddingLeft),g=r?0:parseFloat(o.borderTopWidth),m=r?0:parseFloat(o.borderRightWidth),w=r?0:parseFloat(o.borderBottomWidth),b=u+f,F=d+l,v=(r?0:parseFloat(o.borderLeftWidth))+m,W=g+w,y=r?0:t.offsetHeight-W-t.clientHeight,E=r?0:t.offsetWidth-v-t.clientWidth,R=b+v,z=F+W,M=r?t.width:parseFloat(o.width)-R-E,O=r?t.height:parseFloat(o.height)-z-y;if(n.has(t)){var k=n.get(t);if(k[0]===M&&k[1]===O)return}n.set(t,[M,O]);var S=Object.create(h.prototype);S.target=t,S.contentRect=new c(u,d,M,O),s.has(i)||(s.set(i,[]),p.add(i)),s.get(i).push(S)}))})),p.forEach((function(e){i.get(e).call(e,s.get(e),e)}))}return s.prototype.observe=function(i){if(i instanceof window.Element){r.has(i)||(r.set(i,new Set),o.add(i),a.set(i,window.getComputedStyle(i)));var n=r.get(i);n.has(this)||n.add(this),cancelAnimationFrame(t),t=requestAnimationFrame(d)}},s.prototype.unobserve=function(i){if(i instanceof window.Element&&r.has(i)){var n=r.get(i);n.has(this)&&(n.delete(this),n.size||(r.delete(i),o.delete(i))),n.size||r.delete(i),o.size||cancelAnimationFrame(t)}},A.DOMRectReadOnly=c,A.ResizeObserver=s,A.ResizeObserverEntry=h,A}; // eslint-disable-line\nmpl.toolbar_items = [[\"Home\", \"Reset original view\", \"fa fa-home icon-home\", \"home\"], [\"Back\", \"Back to previous view\", \"fa fa-arrow-left icon-arrow-left\", \"back\"], [\"Forward\", \"Forward to next view\", \"fa fa-arrow-right icon-arrow-right\", \"forward\"], [\"\", \"\", \"\", \"\"], [\"Pan\", \"Left button pans, Right button zooms\\nx/y fixes axis, CTRL fixes aspect\", \"fa fa-arrows icon-move\", \"pan\"], [\"Zoom\", \"Zoom to rectangle\\nx/y fixes axis, CTRL fixes aspect\", \"fa fa-square-o icon-check-empty\", \"zoom\"], [\"\", \"\", \"\", \"\"], [\"Download\", \"Download plot\", \"fa fa-floppy-o icon-save\", \"download\"]];\n\nmpl.extensions = [\"eps\", \"jpeg\", \"pgf\", \"pdf\", \"png\", \"ps\", \"raw\", \"svg\", \"tif\"];\n\nmpl.default_extension = \"png\";/* global mpl */\n\nvar comm_websocket_adapter = function (comm) {\n // Create a \"websocket\"-like object which calls the given IPython comm\n // object with the appropriate methods. Currently this is a non binary\n // socket, so there is still some room for performance tuning.\n var ws = {};\n\n ws.binaryType = comm.kernel.ws.binaryType;\n ws.readyState = comm.kernel.ws.readyState;\n function updateReadyState(_event) {\n if (comm.kernel.ws) {\n ws.readyState = comm.kernel.ws.readyState;\n } else {\n ws.readyState = 3; // Closed state.\n }\n }\n comm.kernel.ws.addEventListener('open', updateReadyState);\n comm.kernel.ws.addEventListener('close', updateReadyState);\n comm.kernel.ws.addEventListener('error', updateReadyState);\n\n ws.close = function () {\n comm.close();\n };\n ws.send = function (m) {\n //console.log('sending', m);\n comm.send(m);\n };\n // Register the callback with on_msg.\n comm.on_msg(function (msg) {\n //console.log('receiving', msg['content']['data'], msg);\n var data = msg['content']['data'];\n if (data['blob'] !== undefined) {\n data = {\n data: new Blob(msg['buffers'], { type: data['blob'] }),\n };\n }\n // Pass the mpl event to the overridden (by mpl) onmessage function.\n ws.onmessage(data);\n });\n return ws;\n};\n\nmpl.mpl_figure_comm = function (comm, msg) {\n // This is the function which gets called when the mpl process\n // starts-up an IPython Comm through the \"matplotlib\" channel.\n\n var id = msg.content.data.id;\n // Get hold of the div created by the display call when the Comm\n // socket was opened in Python.\n var element = document.getElementById(id);\n var ws_proxy = comm_websocket_adapter(comm);\n\n function ondownload(figure, _format) {\n window.open(figure.canvas.toDataURL());\n }\n\n var fig = new mpl.figure(id, ws_proxy, ondownload, element);\n\n // Call onopen now - mpl needs it, as it is assuming we've passed it a real\n // web socket which is closed, not our websocket->open comm proxy.\n ws_proxy.onopen();\n\n fig.parent_element = element;\n fig.cell_info = mpl.find_output_cell(\"\");\n if (!fig.cell_info) {\n console.error('Failed to find cell for figure', id, fig);\n return;\n }\n fig.cell_info[0].output_area.element.on(\n 'cleared',\n { fig: fig },\n fig._remove_fig_handler\n );\n};\n\nmpl.figure.prototype.handle_close = function (fig, msg) {\n var width = fig.canvas.width / fig.ratio;\n fig.cell_info[0].output_area.element.off(\n 'cleared',\n fig._remove_fig_handler\n );\n fig.resizeObserverInstance.unobserve(fig.canvas_div);\n\n // Update the output cell to use the data from the current canvas.\n fig.push_to_output();\n var dataURL = fig.canvas.toDataURL();\n // Re-enable the keyboard manager in IPython - without this line, in FF,\n // the notebook keyboard shortcuts fail.\n IPython.keyboard_manager.enable();\n fig.parent_element.innerHTML =\n '
+
+We will cover back prop in much more detail in our notebook example.
## [Proceed to Notebook](OwnFramework.ipynb)
In the accompanying notebook, we will implement our own framework for building and training multi-layered perceptrons. You will be able to see in detail how modern neural networks operate. Proceed to [OwnFramework](OwnFramework.ipynb) notebook.
diff --git a/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb b/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb
index f172f8e1..588d8652 100644
--- a/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb
+++ b/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb
@@ -691,7 +691,7 @@
},
{
"cell_type": "code",
- "execution_count": 18,
+ "execution_count": 96,
"metadata": {
"id": "j0OTPkGpwHl7",
"scrolled": false,
@@ -703,7 +703,7 @@
"\n",
"n = 100\n",
"X, Y = make_classification(n_samples = n, n_features=2,\n",
- " n_redundant=0, n_informative=2, flip_y=0.2,class_sep=1)\n",
+ " n_redundant=0, n_informative=2, flip_y=0.1,class_sep=1)\n",
"X = X.astype(np.float32)\n",
"Y = Y.astype(np.int32)\n",
"\n",
@@ -714,7 +714,7 @@
},
{
"cell_type": "code",
- "execution_count": 19,
+ "execution_count": 97,
"metadata": {
"id": "c-_BjSHPwHl8",
"scrolled": false,
@@ -743,7 +743,7 @@
},
{
"cell_type": "code",
- "execution_count": 20,
+ "execution_count": 98,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -765,7 +765,7 @@
},
{
"data": {
- "image/png": "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",
+ "image/png": "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",
"text/plain": [
"![](\"images/lmfilters.jpg\")
\n",
+ "\n",
+ "However, in deep learning we construct networks that **learn** best convolutional filters to solve classification problem. To do that, we introduce **convolutional layers**."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Covolutional layers\n",
+ "\n",
+ "To make the weights of convolutional layer trainable, we need somehow to reduce the process of applying convolutional filter window to the image to the matrix operations, which can then be subject to backward propagation training. To do this, we use a clever matrix transformation, which we call **im2col**.\n",
+ "\n",
+ "Suppose we have a small image $\\mathbf{x}$, with the following pixels:\n",
+ "\n",
+ "$$\n",
+ "\\mathbf{x} = \\left(\n",
+ " \\begin{array}{ccccc}\n",
+ " a & b & c & d & e \\\\\n",
+ " f & g & h & i & j \\\\\n",
+ " k & l & m & n & o \\\\\n",
+ " p & q & r & s & t \\\\\n",
+ " u & v & w & x & y \\\\\n",
+ " \\end{array}\n",
+ " \\right)\n",
+ "$$\n",
+ "\n",
+ "And we want to apply two conv filters, with the following weights:\n",
+ "$$\n",
+ "W^{(i)} = \\left(\\begin{array}{ccc}\n",
+ " w^{(i)}_{00} & w^{(i)}_{01} & w^{(i)}_{02} \\\\\n",
+ " w^{(i)}_{10} & w^{(i)}_{11} & w^{(i)}_{12} \\\\\n",
+ " w^{(i)}_{20} & w^{(i)}_{21} & w^{(i)}_{22} \\\\\n",
+ " \\end{array}\\right) \n",
+ "$$\n",
+ "\n",
+ "When applying the convolution, the first pixel of the result would be obtained by element-wise multiplication of \n",
+ "$\\left(\\begin{array}{ccc}\n",
+ " a & b & c \\\\\n",
+ " f & g & h \\\\\n",
+ " k & l & m \\\\\n",
+ "\\end{array}\\right)$ and $W^{(i)}$, the second element - by multiplying by $\\left(\\begin{array}{ccc}\n",
+ " b & c & d \\\\\n",
+ " g & h & i \\\\\n",
+ " l & m & n \\\\\n",
+ "\\end{array}\\right)$ by $W^{(i)}$, and so on.\n",
+ "\n",
+ "To formalize this process, let's extract all $3\\times3$ fragments of the original image $x$ into the following matrix:\n",
+ "\n",
+ "$$\n",
+ "\\mathrm{im2col}(x) = \\left[\n",
+ " \\begin{array}{cccccc}\n",
+ " a & b & \\ldots & g & \\ldots & m \\\\\n",
+ " b & c & \\ldots & h & \\ldots & n \\\\\n",
+ " c & d & \\ldots & i & \\ldots & o \\\\\n",
+ " f & g & \\ldots & l & \\ldots & r \\\\\n",
+ " g & h & \\ldots & m & \\ldots & s \\\\\n",
+ " h & i & \\ldots & n & \\ldots & t \\\\\n",
+ " k & l & \\ldots & q & \\ldots & w \\\\\n",
+ " l & m & \\ldots & r & \\ldots & x \\\\\n",
+ " m & n & \\ldots & s & \\ldots & y \\\\\n",
+ " \\end{array}\n",
+ " \\right]\n",
+ "$$\n",
+ "\n",
+ "Each column of this matrix corresponds to each $3\\times3$ subregion of the original image. Now, to get the result of the convolution, we just need to multiply this matrix by the matrix or weights\n",
+ "$$\n",
+ "\\mathbf{W} = \\left[\n",
+ " \\begin{array}{cccccccc}\n",
+ " w^{(0)}_{00} & w^{(0)}_{01} & w^{(0)}_{02} & w^{(0)}_{10} & w^{(0)}_{11} & \\ldots & w^{(0)}_{21} & w^{(0)}_{22} \\\\\n",
+ " w^{(1)}_{00} & w^{(1)}_{01} & w^{(1)}_{02} & w^{(1)}_{10} & w^{(1)}_{11} & \\ldots & w^{(1)}_{21} & w^{(1)}_{22} \\\\\n",
+ " \\end{array}\n",
+ " \\right]\n",
+ "$$\n",
+ "(each row of this matrix contains weights of $i$-th filter, flattened into one row)\n",
+ "\n",
+ "So the application of a convolution filter to the original image can be replaced by matrix multiplication, which we already know how to handle using back prop:\n",
+ "$$\n",
+ "C(x) = W\\times\\mathbf{im2col}(x)\n",
+ "$$\n",
+ "\n",
+ "Convolutional layers are defined using `Conv2d` class. We need to specify the following:\n",
+ "* `filters` - number of filters to use. We will use 9 different filters, which will give the network plenty of opportunities to explore which filters work best for our scenario.\n",
+ "* `kernel_size` is the size of the sliding window. Usually 3x3 or 5x5 filters are used.\n",
+ "\n",
+ "Simplest CNN will contain one convolutional layer. Given the input size 28x28, after applying nine 5x5 filters we will end up with a tensor of 24x24x9. The spatial dimension is smaller, because there are only 24 positions where a sliding interval of length 5 can fit into 28 pixels).\n",
+ "\n",
+ "After convolution, we flatten 24x24x9 tensor into one vector of size 5184, and then add linear layer, to produce 10 classes. We also use `relu` activation function in between layers. "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Model: \"sequential\"\n",
+ "_________________________________________________________________\n",
+ "Layer (type) Output Shape Param # \n",
+ "=================================================================\n",
+ "conv2d (Conv2D) (None, 24, 24, 9) 234 \n",
+ "_________________________________________________________________\n",
+ "flatten (Flatten) (None, 5184) 0 \n",
+ "_________________________________________________________________\n",
+ "dense (Dense) (None, 10) 51850 \n",
+ "=================================================================\n",
+ "Total params: 52,084\n",
+ "Trainable params: 52,084\n",
+ "Non-trainable params: 0\n",
+ "_________________________________________________________________\n"
+ ]
+ }
+ ],
+ "source": [
+ "model = keras.models.Sequential([\n",
+ " keras.layers.Conv2D(filters=9, kernel_size=(5,5), input_shape=(28,28,1),activation='relu'),\n",
+ " keras.layers.Flatten(),\n",
+ " keras.layers.Dense(10)\n",
+ "])\n",
+ "\n",
+ "model.compile(loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),metrics=['acc'])\n",
+ "\n",
+ "model.summary()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "You can see that this network contains around 50k trainable parameters, compared to around 80k in fully-connected multi-layered networks. This allows us to achieve good results even on smaller datasets, because convolutional networks generalize much better.\n",
+ "\n",
+ "> **Note**: In most of the practical cases, we want to apply convolutional layers to color images. Thus, `Conv2D` layer expects the input to be of the shape $W\\times H\\times C$, where $W$ and $H$ are width and height of the image, and $C$ is the number of color channels. For grayscale images, we need the same shape with $C=1$.\n",
+ "\n",
+ "We need to reshape our data before starting training:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Epoch 1/5\n",
+ "1875/1875 [==============================] - 6s 3ms/step - loss: 0.0315 - acc: 0.9903 - val_loss: 0.0358 - val_acc: 0.9894\n",
+ "Epoch 2/5\n",
+ "1875/1875 [==============================] - 6s 3ms/step - loss: 0.0282 - acc: 0.9909 - val_loss: 0.0343 - val_acc: 0.9891\n",
+ "Epoch 3/5\n",
+ "1875/1875 [==============================] - 6s 3ms/step - loss: 0.0267 - acc: 0.9920 - val_loss: 0.0379 - val_acc: 0.9891\n",
+ "Epoch 4/5\n",
+ "1875/1875 [==============================] - 6s 3ms/step - loss: 0.0253 - acc: 0.9924 - val_loss: 0.0309 - val_acc: 0.9918\n",
+ "Epoch 5/5\n",
+ "1875/1875 [==============================] - 6s 3ms/step - loss: 0.0239 - acc: 0.9930 - val_loss: 0.0341 - val_acc: 0.9896\n"
+ ]
+ }
+ ],
+ "source": [
+ "x_train_c = np.expand_dims(x_train,3)\n",
+ "x_test_c = np.expand_dims(x_test,3)\n",
+ "hist = model.fit(x_train_c,y_train,validation_data=(x_test_c,y_test),epochs=5)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "
+
+However, while we can design the filters to extract some patterns manually, we can also design the network in such a way that it will learn the patterns automatically. It is one of the main ideas behind the CNN.
+
+## Main ideas behind CNN
+
+The way CNNs work is based on the following important ideas:
+* Convolutional filters can extract patterns
+* We can design the network in such a way that filters are trained automatically
+* We can use the same approach to find patterns in high-level features, not only in the original image. Thus CNN feature extraction work on a hierarchy of features, starting from low-level pixel combinations, up to higher level combination of picture parts.
+
+
+
+## Continue in Notebook
+
+Let's continue exploring how convolutional neural networks work, and how we can achieve trainable filters, in corresponding notebooks:
+
+* [Convolutional Neural Networks - PyTorch](ConvNetsPyTorch.ipynb)
+* [Convolutional Neural Networks - Tensorflow](ConvNetsTF.ipynb)
diff --git a/4-ComputerVision/07-ConvNets/images/FeatureExtractionCNN.png b/4-ComputerVision/07-ConvNets/images/FeatureExtractionCNN.png
new file mode 100644
index 00000000..df8c813c
Binary files /dev/null and b/4-ComputerVision/07-ConvNets/images/FeatureExtractionCNN.png differ
diff --git a/4-ComputerVision/07-ConvNets/images/cnn-pyramid.png b/4-ComputerVision/07-ConvNets/images/cnn-pyramid.png
new file mode 100644
index 00000000..edc28b32
Binary files /dev/null and b/4-ComputerVision/07-ConvNets/images/cnn-pyramid.png differ
diff --git a/4-ComputerVision/07-ConvNets/images/convolutionExample.png b/4-ComputerVision/07-ConvNets/images/convolutionExample.png
new file mode 100644
index 00000000..7bfd6db5
Binary files /dev/null and b/4-ComputerVision/07-ConvNets/images/convolutionExample.png differ
diff --git a/4-ComputerVision/07-ConvNets/images/filter-horiz.png b/4-ComputerVision/07-ConvNets/images/filter-horiz.png
new file mode 100644
index 00000000..327ef6a6
Binary files /dev/null and b/4-ComputerVision/07-ConvNets/images/filter-horiz.png differ
diff --git a/4-ComputerVision/07-ConvNets/images/filter-vert.png b/4-ComputerVision/07-ConvNets/images/filter-vert.png
new file mode 100644
index 00000000..bea51b28
Binary files /dev/null and b/4-ComputerVision/07-ConvNets/images/filter-vert.png differ
diff --git a/4-ComputerVision/07-ConvNets/images/lmfilters.jpg b/4-ComputerVision/07-ConvNets/images/lmfilters.jpg
new file mode 100644
index 00000000..7b6e1372
Binary files /dev/null and b/4-ComputerVision/07-ConvNets/images/lmfilters.jpg differ
diff --git a/4-ComputerVision/07-ConvNets/pytorchcv.py b/4-ComputerVision/07-ConvNets/pytorchcv.py
new file mode 100644
index 00000000..19ff1c5c
--- /dev/null
+++ b/4-ComputerVision/07-ConvNets/pytorchcv.py
@@ -0,0 +1,169 @@
+
+# Script file to hide implementation details for PyTorch computer vision module
+
+import builtins
+import torch
+import torch.nn as nn
+from torch.utils import data
+import torchvision
+from torchvision.transforms import ToTensor
+import matplotlib.pyplot as plt
+import numpy as np
+from PIL import Image
+import glob
+import os
+import zipfile
+
+default_device = 'cuda' if torch.cuda.is_available() else 'cpu'
+
+def load_mnist(batch_size=64):
+ builtins.data_train = torchvision.datasets.MNIST('./data',
+ download=True,train=True,transform=ToTensor())
+ builtins.data_test = torchvision.datasets.MNIST('./data',
+ download=True,train=False,transform=ToTensor())
+ builtins.train_loader = torch.utils.data.DataLoader(data_train,batch_size=batch_size)
+ builtins.test_loader = torch.utils.data.DataLoader(data_test,batch_size=batch_size)
+
+def train_epoch(net,dataloader,lr=0.01,optimizer=None,loss_fn = nn.NLLLoss()):
+ optimizer = optimizer or torch.optim.Adam(net.parameters(),lr=lr)
+ net.train()
+ total_loss,acc,count = 0,0,0
+ for features,labels in dataloader:
+ optimizer.zero_grad()
+ lbls = labels.to(default_device)
+ out = net(features.to(default_device))
+ loss = loss_fn(out,lbls) #cross_entropy(out,labels)
+ loss.backward()
+ optimizer.step()
+ total_loss+=loss
+ _,predicted = torch.max(out,1)
+ acc+=(predicted==lbls).sum()
+ count+=len(labels)
+ return total_loss.item()/count, acc.item()/count
+
+def validate(net, dataloader,loss_fn=nn.NLLLoss()):
+ net.eval()
+ count,acc,loss = 0,0,0
+ with torch.no_grad():
+ for features,labels in dataloader:
+ lbls = labels.to(default_device)
+ out = net(features.to(default_device))
+ loss += loss_fn(out,lbls)
+ pred = torch.max(out,1)[1]
+ acc += (pred==lbls).sum()
+ count += len(labels)
+ return loss.item()/count, acc.item()/count
+
+def train(net,train_loader,test_loader,optimizer=None,lr=0.01,epochs=10,loss_fn=nn.NLLLoss()):
+ optimizer = optimizer or torch.optim.Adam(net.parameters(),lr=lr)
+ res = { 'train_loss' : [], 'train_acc': [], 'val_loss': [], 'val_acc': []}
+ for ep in range(epochs):
+ tl,ta = train_epoch(net,train_loader,optimizer=optimizer,lr=lr,loss_fn=loss_fn)
+ vl,va = validate(net,test_loader,loss_fn=loss_fn)
+ print(f"Epoch {ep:2}, Train acc={ta:.3f}, Val acc={va:.3f}, Train loss={tl:.3f}, Val loss={vl:.3f}")
+ res['train_loss'].append(tl)
+ res['train_acc'].append(ta)
+ res['val_loss'].append(vl)
+ res['val_acc'].append(va)
+ return res
+
+def train_long(net,train_loader,test_loader,epochs=5,lr=0.01,optimizer=None,loss_fn = nn.NLLLoss(),print_freq=10):
+ optimizer = optimizer or torch.optim.Adam(net.parameters(),lr=lr)
+ for epoch in range(epochs):
+ net.train()
+ total_loss,acc,count = 0,0,0
+ for i, (features,labels) in enumerate(train_loader):
+ lbls = labels.to(default_device)
+ optimizer.zero_grad()
+ out = net(features.to(default_device))
+ loss = loss_fn(out,lbls)
+ loss.backward()
+ optimizer.step()
+ total_loss+=loss
+ _,predicted = torch.max(out,1)
+ acc+=(predicted==lbls).sum()
+ count+=len(labels)
+ if i%print_freq==0:
+ print("Epoch {}, minibatch {}: train acc = {}, train loss = {}".format(epoch,i,acc.item()/count,total_loss.item()/count))
+ vl,va = validate(net,test_loader,loss_fn)
+ print("Epoch {} done, validation acc = {}, validation loss = {}".format(epoch,va,vl))
+
+
+def plot_results(hist):
+ plt.figure(figsize=(15,5))
+ plt.subplot(121)
+ plt.plot(hist['train_acc'], label='Training acc')
+ plt.plot(hist['val_acc'], label='Validation acc')
+ plt.legend()
+ plt.subplot(122)
+ plt.plot(hist['train_loss'], label='Training loss')
+ plt.plot(hist['val_loss'], label='Validation loss')
+ plt.legend()
+
+def plot_convolution(t,title=''):
+ with torch.no_grad():
+ c = nn.Conv2d(kernel_size=(3,3),out_channels=1,in_channels=1)
+ c.weight.copy_(t)
+ fig, ax = plt.subplots(2,6,figsize=(8,3))
+ fig.suptitle(title,fontsize=16)
+ for i in range(5):
+ im = data_train[i][0]
+ ax[0][i].imshow(im[0])
+ ax[1][i].imshow(c(im.unsqueeze(0))[0][0])
+ ax[0][i].axis('off')
+ ax[1][i].axis('off')
+ ax[0,5].imshow(t)
+ ax[0,5].axis('off')
+ ax[1,5].axis('off')
+ #plt.tight_layout()
+ plt.show()
+
+def display_dataset(dataset, n=10,classes=None):
+ fig,ax = plt.subplots(1,n,figsize=(15,3))
+ mn = min([dataset[i][0].min() for i in range(n)])
+ mx = max([dataset[i][0].max() for i in range(n)])
+ for i in range(n):
+ ax[i].imshow(np.transpose((dataset[i][0]-mn)/(mx-mn),(1,2,0)))
+ ax[i].axis('off')
+ if classes:
+ ax[i].set_title(classes[dataset[i][1]])
+
+
+def check_image(fn):
+ try:
+ im = Image.open(fn)
+ im.verify()
+ return True
+ except:
+ return False
+
+def check_image_dir(path):
+ for fn in glob.glob(path):
+ if not check_image(fn):
+ print("Corrupt image: {}".format(fn))
+ os.remove(fn)
+
+
+def common_transform():
+ std_normalize = torchvision.transforms.Normalize(mean=[0.485, 0.456, 0.406],
+ std=[0.229, 0.224, 0.225])
+ trans = torchvision.transforms.Compose([
+ torchvision.transforms.Resize(256),
+ torchvision.transforms.CenterCrop(224),
+ torchvision.transforms.ToTensor(),
+ std_normalize])
+ return trans
+
+def load_cats_dogs_dataset():
+ if not os.path.exists('data/PetImages'):
+ with zipfile.ZipFile('data/kagglecatsanddogs_3367a.zip', 'r') as zip_ref:
+ zip_ref.extractall('data')
+
+ check_image_dir('data/PetImages/Cat/*.jpg')
+ check_image_dir('data/PetImages/Dog/*.jpg')
+
+ dataset = torchvision.datasets.ImageFolder('data/PetImages',transform=common_transform())
+ trainset, testset = torch.utils.data.random_split(dataset,[20000,len(dataset)-20000])
+ trainloader = torch.utils.data.DataLoader(trainset,batch_size=32)
+ testloader = torch.utils.data.DataLoader(trainset,batch_size=32)
+ return dataset, trainloader, testloader
\ No newline at end of file
diff --git a/4-ComputerVision/07-ConvNets/tfcv.py b/4-ComputerVision/07-ConvNets/tfcv.py
new file mode 100644
index 00000000..c5aff501
--- /dev/null
+++ b/4-ComputerVision/07-ConvNets/tfcv.py
@@ -0,0 +1,86 @@
+# Tensorflow Computer Vision Helper
+
+import tensorflow as tf
+from tensorflow import keras
+import numpy as np
+import matplotlib.pyplot as plt
+from PIL import Image
+import glob
+import os
+
+def plot_convolution(data,t,title=''):
+ fig, ax = plt.subplots(2,len(data)+1,figsize=(8,3))
+ fig.suptitle(title,fontsize=16)
+ tt = np.expand_dims(np.expand_dims(t,2),2)
+ for i,im in enumerate(data):
+ ax[0][i].imshow(im)
+ ximg = np.expand_dims(np.expand_dims(im,2),0)
+ cim = tf.nn.conv2d(ximg,tt,1,'SAME')
+ ax[1][i].imshow(cim[0][:,:,0])
+ ax[0][i].axis('off')
+ ax[1][i].axis('off')
+ ax[0,-1].imshow(t)
+ ax[0,-1].axis('off')
+ ax[1,-1].axis('off')
+ #plt.tight_layout()
+ plt.show()
+
+def plot_results(hist):
+ fig,ax = plt.subplots(1,2,figsize=(15,3))
+ ax[0].set_title('Accuracy')
+ ax[1].set_title('Loss')
+ for x in ['acc','val_acc']:
+ ax[0].plot(hist.history[x])
+ for x in ['loss','val_loss']:
+ ax[1].plot(hist.history[x])
+ plt.show()
+
+def display_dataset(dataset, labels=None, n=10, classes=None):
+ fig,ax = plt.subplots(1,n,figsize=(15,3))
+ for i in range(n):
+ ax[i].imshow(dataset[i])
+ ax[i].axis('off')
+ if classes is not None and labels is not None:
+ ax[i].set_title(classes[labels[i][0]])
+
+def check_image(fn):
+ try:
+ im = Image.open(fn)
+ im.verify()
+ return im.format=='JPEG'
+ except:
+ return False
+
+def check_image_dir(path):
+ for fn in glob.glob(path):
+ if not check_image(fn):
+ print("Corrupt image or wrong format: {}".format(fn))
+ os.remove(fn)
+
+def load_cats_dogs_dataset(batch_size=64):
+ if not os.path.exists('data/PetImages'):
+ print("Extracting the dataset")
+ with zipfile.ZipFile('data/kagglecatsanddogs_3367a.zip', 'r') as zip_ref:
+ zip_ref.extractall('data')
+ print("Checking dataset")
+ check_image_dir('data/PetImages/Cat/*.jpg')
+ check_image_dir('data/PetImages/Dog/*.jpg')
+ data_dir = 'data/PetImages'
+ print("Loading dataset")
+ ds_train = keras.preprocessing.image_dataset_from_directory(
+ data_dir,
+ validation_split = 0.2,
+ subset = 'training',
+ seed = 13,
+ image_size = (224,224),
+ batch_size = batch_size
+ )
+ ds_test = keras.preprocessing.image_dataset_from_directory(
+ data_dir,
+ validation_split = 0.2,
+ subset = 'validation',
+ seed = 13,
+ image_size = (224,224),
+ batch_size = batch_size
+ )
+ return ds_train,ds_test
diff --git a/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb b/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb
new file mode 100644
index 00000000..8d0ea78e
--- /dev/null
+++ b/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb
@@ -0,0 +1,953 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Pre-trained models and transfer learning\n",
+ "\n",
+ "Training CNNs can take a lot of time, and a lot of data is required for that task. However, much of the time is spent to learn the best low-level filters that a network is using to extract patterns from images. A natural question arises - can we use a neural network trained on one dataset and adapt it to classifying different images without full training process?\n",
+ "\n",
+ "This approach is called **transfer learning**, because we transfer some knowledge from one neural network model to another. In transfer learning, we typically start with a pre-trained model, which has been trained on some large image dataset, such as **ImageNet**. Those models can already do a good job extracting different features from generic images, and in many cases just building a classifier on top of those extracted features can yield a good result."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import torch\n",
+ "import torch.nn as nn\n",
+ "import torchvision\n",
+ "import torchvision.transforms as transforms\n",
+ "import matplotlib.pyplot as plt\n",
+ "from torchinfo import summary\n",
+ "import numpy as np\n",
+ "import os\n",
+ "\n",
+ "from pytorchcv import train, plot_results, display_dataset, train_long, check_image_dir"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Cats vs. Dogs Dataset\n",
+ "\n",
+ "In this unit, we will solve a real-life problem of classifying images of cats and dogs. For this reason, we will use [Kaggle Cats vs. Dogs Dataset](https://www.kaggle.com/c/dogs-vs-cats), which can also be downloaded [from Microsoft](https://www.microsoft.com/en-us/download/details.aspx?id=54765).\n",
+ "\n",
+ "Let's download this dataset and extract it into `data` directory (this process may take some time!):"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "if not os.path.exists('data/kagglecatsanddogs_3367a.zip'):\n",
+ " !wget -P data -q https://download.microsoft.com/download/3/E/1/3E1C3F21-ECDB-4869-8368-6DEBA77B919F/kagglecatsanddogs_3367a.zip"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import zipfile\n",
+ "if not os.path.exists('data/PetImages'):\n",
+ " with zipfile.ZipFile('data/kagglecatsanddogs_3367a.zip', 'r') as zip_ref:\n",
+ " zip_ref.extractall('data')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Unfortunately, there are some corrupt image files in the dataset. We need to do quick cleaning to check for corrupted files. In order not to clobber this tutorial, we moved the code to verify dataset into a module."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Corrupt image: data/PetImages/Cat/666.jpg\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/anaconda/envs/py38_pytorch/lib/python3.8/site-packages/PIL/TiffImagePlugin.py:793: UserWarning: Truncated File Read\n",
+ " warnings.warn(str(msg))\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Corrupt image: data/PetImages/Dog/11702.jpg\n"
+ ]
+ }
+ ],
+ "source": [
+ "check_image_dir('data/PetImages/Cat/*.jpg')\n",
+ "check_image_dir('data/PetImages/Dog/*.jpg')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Next, let's load the images into PyTorch dataset, converting them to tensors and doing some normalization. We will apply `std_normalize` transform to bring images to the range expected by pre-trained VGG network:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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\n",
+ "text/plain": [
+ "