Handwritten Digits Recognition 02 - TensorFlow.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Handwritten Digits Recognition 02 - TensorFlow\n",
    "\n",
    "From the table below, we see that MNIST database is way larger than scikit-learn database, which we modelled in the previous notebook. Both number of samples and size of each sample are significantly higher. The good new is that, with TensorFlow and Keras, we can build neural networks, which are powerful enough to handle MNIST database! In this notebook, we are going to use Convolutional Neural Network (CNN) to perform image recognition.\n",
    "\n",
    "|           | Scikit-learn database | MNIST database |\n",
    "|-----------|-----------------------|----------------|\n",
    "| Samples   | 1797                  | 70,000         |\n",
    "| Dimensions | 64 (8x8)              | 784 (28x28)    |\n",
    "\n",
    "1. More information about Scikit-learn Database: https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html\n",
    "2. More information about MNIST Database: https://en.wikipedia.org/wiki/MNIST_database"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Loading MNIST database\n",
    "\n",
    "We are going to load MNIST database using utilities provided by TensorFlow. When importing TensorFlow, I always first check if it is using the GPU. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": "TensorFlow Version 2.1.0\nDevice: /device:GPU:0\n"
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "print(\"TensorFlow Version\", tf.__version__)\n",
    "\n",
    "if tf.test.is_gpu_available:\n",
    "    print(\"Device:\" ,tf.test.gpu_device_name())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now, load the MNIST database using TensorFlow. From the output, we can see that the images are 28x28. The database contains 60,000 training and 10,000 testing images. There is no missing entries."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": "(60000, 28, 28) (60000,)\n(10000, 28, 28) (10000,)\n"
    }
   ],
   "source": [
    "(X_train, y_train), (X_test, y_test) = tf.keras.datasets.mnist.load_data()\n",
    "\n",
    "print(X_train.shape, y_train.shape)\n",
    "print(X_test.shape, y_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Before we get our hands dirty with all the hardwork, let's just take a moment and look at some digits in the dataset. The digits displayed are the first eight digits in the set. We can see that the image quality is quite high, significantly better than the ones in scikit-learn digits set."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "output_type": "display_data",
     "data": {
      "text/plain": "<Figure size 432x288 with 8 Axes>",
      "image/svg+xml": "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\r\n<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\r\n  \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\r\n<!-- Created with matplotlib (https://matplotlib.org/) -->\r\n<svg height=\"247.613123pt\" version=\"1.1\" viewBox=\"0 0 349.2 247.613123\" width=\"349.2pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\r\n <defs>\r\n  <style type=\"text/css\">\r\n*{stroke-linecap:butt;stroke-linejoin:round;}\r\n  </style>\r\n </defs>\r\n <g id=\"figure_1\">\r\n  <g id=\"patch_1\">\r\n   <path d=\"M 0 247.613123 \r\nL 349.2 247.613123 \r\nL 349.2 0 \r\nL 0 0 \r\nz\r\n\" style=\"fill:none;\"/>\r\n  </g>\r\n  <g id=\"axes_1\">\r\n   <g clip-path=\"url(#p2718ecef10)\">\r\n    <image height=\"73\" id=\"imagec35b6deb1e\" transform=\"scale(1 -1)translate(0 -73)\" width=\"73\" x=\"7.2\" xlink:href=\"data:image/png;base64,\r\niVBORw0KGgoAAAANSUhEUgAAAEkAAABJCAYAAABxcwvcAAAABHNCSVQICAgIfAhkiAAAA7NJREFUeJztm8srdWEUxn/H/VoMKWNl4hIZKFFihP9AKaLIhKQMKANl6DIxVQwIpZRSFClJyaUYKGRASS4xcMk32utsn823fM45+6j1Gz2t3rPP2+N5nXfvd+3A29vbG8aXxPg9gd+AmaTATFJgJikwkxSYSQrMJAVx2oE9PT2ih4aGvhybl5cHQG1trdRiY2NFd3V1AZCRkaH9el+xJCkIaHfcm5ubot1J2traAuD8/Fz9pSkpKQB0dHRIrbe3F4DU1FT1dSKFJUmBmaRAvdw+4/r6GoCWlhap7ezsAHB8fKy+TllZGQCdnZ1Sq6mpEZ2cnPyTaf4IS5ICM0nBj5ebF5eXlwAcHBxIrb29XfTh4aHqOqWlpaK7u7sBqK+vl1pMTGT+xpYkBWFJkhcXFxeiJycnARgdHZXaycmJ6jolJSWinb0VQF1d3Q9n+DmWJAVmkoKILTcvjo6ORI+MjAAwOzsrNfcS9SIuLnh/XlVVBcDi4mIopwhYklT4miQvdnd3Rc/MzIh2bqSXlpY8P5efnw/A9va21EK1RbAkKTCTFETdcvsXiYmJop+fn0XHx8cD75djRUVFSL7TkqTATFKgPgjwg5ubG9ELCwsAvLy8eI4tLy8HQrfE3FiSFERdkvb29kS7n1IuLy9/GNva2irafbMbaixJCswkBVGz3Obm5gBobGyU2t3d3Ydxg4ODohsaGkRnZWWFbW6WJAVmkgJfb0vc53JFRUXA+yaKyspK0cXFxQC0tbVJLRAIhHuKgCVJhS//uB8eHgBobm6W2v39PQDT09NSq66ujuzEPsGSpMBMUuDLcuvv7wdgdXVVas6NqfNAP5qwJCkIa5LcO+b09HTRt7e3H8Y2NTUBkTvf/w7RN6MoxExSEJYd9/z8PBB8mghQWFgo2t1Q6lBQUADA2tqa1NxNpvv7+wAMDw9LbXx8PEQz/hpLkgIzSUHIlpvTYArBDrXvNJb+/VmAzMxM0SsrKwAkJCRIzetXMhxYkhSEbJ90enoq+urq6r+v437zwAv3kdLExIRorzcJsrOzgfeJzM3N/facLEkKzCQFYdknnZ2dAfD09CS1jY0N0evr68D7E1p3L5KWnJwc0c6TS+dAASAtLQ0I9i4BDAwMiNae9lqSFPj6jPv19VX0v37OnXbmx8dHqbl7LsfGxoDgC4cAU1NTACQlJUnN/XJjX1+fap6WJAVmkoJf1+nmB5YkBWaSAjNJgZmkwExSYCYpMJMUmEkKzCQFZpICM0mBmaTgD0fSFjA7b9b1AAAAAElFTkSuQmCC\" y=\"-48.809486\"/>\r\n   </g>\r\n   <g id=\"text_1\">\r\n    <!-- Number 5 -->\r\n    <defs>\r\n     <path d=\"M 9.8125 72.90625 \r\nL 23.09375 72.90625 \r\nL 55.421875 11.921875 \r\nL 55.421875 72.90625 \r\nL 64.984375 72.90625 \r\nL 64.984375 0 \r\nL 51.703125 0 \r\nL 19.390625 60.984375 \r\nL 19.390625 0 \r\nL 9.8125 0 \r\nz\r\n\" id=\"DejaVuSans-78\"/>\r\n     <path d=\"M 8.5 21.578125 \r\nL 8.5 54.6875 \r\nL 17.484375 54.6875 \r\nL 17.484375 21.921875 \r\nQ 17.484375 14.15625 20.5 10.265625 \r\nQ 23.53125 6.390625 29.59375 6.390625 \r\nQ 36.859375 6.390625 41.078125 11.03125 \r\nQ 45.3125 15.671875 45.3125 23.6875 \r\nL 45.3125 54.6875 \r\nL 54.296875 54.6875 \r\nL 54.296875 0 \r\nL 45.3125 0 \r\nL 45.3125 8.40625 \r\nQ 42.046875 3.421875 37.71875 1 \r\nQ 33.40625 -1.421875 27.6875 -1.421875 \r\nQ 18.265625 -1.421875 13.375 4.4375 \r\nQ 8.5 10.296875 8.5 21.578125 \r\nz\r\nM 31.109375 56 \r\nz\r\n\" id=\"DejaVuSans-117\"/>\r\n     <path d=\"M 52 44.1875 \r\nQ 55.375 50.25 60.0625 53.125 \r\nQ 64.75 56 71.09375 56 \r\nQ 79.640625 56 84.28125 50.015625 \r\nQ 88.921875 44.046875 88.921875 33.015625 \r\nL 88.921875 0 \r\nL 79.890625 0 \r\nL 79.890625 32.71875 \r\nQ 79.890625 40.578125 77.09375 44.375 \r\nQ 74.3125 48.1875 68.609375 48.1875 \r\nQ 61.625 48.1875 57.5625 43.546875 \r\nQ 53.515625 38.921875 53.515625 30.90625 \r\nL 53.515625 0 \r\nL 44.484375 0 \r\nL 44.484375 32.71875 \r\nQ 44.484375 40.625 41.703125 44.40625 \r\nQ 38.921875 48.1875 33.109375 48.1875 \r\nQ 26.21875 48.1875 22.15625 43.53125 \r\nQ 18.109375 38.875 18.109375 30.90625 \r\nL 18.109375 0 \r\nL 9.078125 0 \r\nL 9.078125 54.6875 \r\nL 18.109375 54.6875 \r\nL 18.109375 46.1875 \r\nQ 21.1875 51.21875 25.484375 53.609375 \r\nQ 29.78125 56 35.6875 56 \r\nQ 41.65625 56 45.828125 52.96875 \r\nQ 50 49.953125 52 44.1875 \r\nz\r\n\" id=\"DejaVuSans-109\"/>\r\n     <path d=\"M 48.6875 27.296875 \r\nQ 48.6875 37.203125 44.609375 42.84375 \r\nQ 40.53125 48.484375 33.40625 48.484375 \r\nQ 26.265625 48.484375 22.1875 42.84375 \r\nQ 18.109375 37.203125 18.109375 27.296875 \r\nQ 18.109375 17.390625 22.1875 11.75 \r\nQ 26.265625 6.109375 33.40625 6.109375 \r\nQ 40.53125 6.109375 44.609375 11.75 \r\nQ 48.6875 17.390625 48.6875 27.296875 \r\nz\r\nM 18.109375 46.390625 \r\nQ 20.953125 51.265625 25.265625 53.625 \r\nQ 29.59375 56 35.59375 56 \r\nQ 45.5625 56 51.78125 48.09375 \r\nQ 58.015625 40.1875 58.015625 27.296875 \r\nQ 58.015625 14.40625 51.78125 6.484375 \r\nQ 45.5625 -1.421875 35.59375 -1.421875 \r\nQ 29.59375 -1.421875 25.265625 0.953125 \r\nQ 20.953125 3.328125 18.109375 8.203125 \r\nL 18.109375 0 \r\nL 9.078125 0 \r\nL 9.078125 75.984375 \r\nL 18.109375 75.984375 \r\nz\r\n\" id=\"DejaVuSans-98\"/>\r\n     <path d=\"M 56.203125 29.59375 \r\nL 56.203125 25.203125 \r\nL 14.890625 25.203125 \r\nQ 15.484375 15.921875 20.484375 11.0625 \r\nQ 25.484375 6.203125 34.421875 6.203125 \r\nQ 39.59375 6.203125 44.453125 7.46875 \r\nQ 49.3125 8.734375 54.109375 11.28125 \r\nL 54.109375 2.78125 \r\nQ 49.265625 0.734375 44.1875 -0.34375 \r\nQ 39.109375 -1.421875 33.890625 -1.421875 \r\nQ 20.796875 -1.421875 13.15625 6.1875 \r\nQ 5.515625 13.8125 5.515625 26.8125 \r\nQ 5.515625 40.234375 12.765625 48.109375 \r\nQ 20.015625 56 32.328125 56 \r\nQ 43.359375 56 49.78125 48.890625 \r\nQ 56.203125 41.796875 56.203125 29.59375 \r\nz\r\nM 47.21875 32.234375 \r\nQ 47.125 39.59375 43.09375 43.984375 \r\nQ 39.0625 48.390625 32.421875 48.390625 \r\nQ 24.90625 48.390625 20.390625 44.140625 \r\nQ 15.875 39.890625 15.1875 32.171875 \r\nz\r\n\" id=\"DejaVuSans-101\"/>\r\n     <path d=\"M 41.109375 46.296875 \r\nQ 39.59375 47.171875 37.8125 47.578125 \r\nQ 36.03125 48 33.890625 48 \r\nQ 26.265625 48 22.1875 43.046875 \r\nQ 18.109375 38.09375 18.109375 28.8125 \r\nL 18.109375 0 \r\nL 9.078125 0 \r\nL 9.078125 54.6875 \r\nL 18.109375 54.6875 \r\nL 18.109375 46.1875 \r\nQ 20.953125 51.171875 25.484375 53.578125 \r\nQ 30.03125 56 36.53125 56 \r\nQ 37.453125 56 38.578125 55.875 \r\nQ 39.703125 55.765625 41.0625 55.515625 \r\nz\r\n\" id=\"DejaVuSans-114\"/>\r\n     <path id=\"DejaVuSans-32\"/>\r\n     <path d=\"M 10.796875 72.90625 \r\nL 49.515625 72.90625 \r\nL 49.515625 64.59375 \r\nL 19.828125 64.59375 \r\nL 19.828125 46.734375 \r\nQ 21.96875 47.46875 24.109375 47.828125 \r\nQ 26.265625 48.1875 28.421875 48.1875 \r\nQ 40.625 48.1875 47.75 41.5 \r\nQ 54.890625 34.8125 54.890625 23.390625 \r\nQ 54.890625 11.625 47.5625 5.09375 \r\nQ 40.234375 -1.421875 26.90625 -1.421875 \r\nQ 22.3125 -1.421875 17.546875 -0.640625 \r\nQ 12.796875 0.140625 7.71875 1.703125 \r\nL 7.71875 11.625 \r\nQ 12.109375 9.234375 16.796875 8.0625 \r\nQ 21.484375 6.890625 26.703125 6.890625 \r\nQ 35.15625 6.890625 40.078125 11.328125 \r\nQ 45.015625 15.765625 45.015625 23.390625 \r\nQ 45.015625 31 40.078125 35.4375 \r\nQ 35.15625 39.890625 26.703125 39.890625 \r\nQ 22.75 39.890625 18.8125 39.015625 \r\nQ 14.890625 38.140625 10.796875 36.28125 \r\nz\r\n\" id=\"DejaVuSans-53\"/>\r\n    </defs>\r\n    <g transform=\"translate(13.763804 43.026877)scale(0.12 -0.12)\">\r\n     <use xlink:href=\"#DejaVuSans-78\"/>\r\n     <use x=\"74.804688\" xlink:href=\"#DejaVuSans-117\"/>\r\n     <use x=\"138.183594\" xlink:href=\"#DejaVuSans-109\"/>\r\n     <use x=\"235.595703\" xlink:href=\"#DejaVuSans-98\"/>\r\n     <use x=\"299.072266\" xlink:href=\"#DejaVuSans-101\"/>\r\n     <use x=\"360.595703\" xlink:href=\"#DejaVuSans-114\"/>\r\n     <use x=\"401.708984\" xlink:href=\"#DejaVuSans-32\"/>\r\n     <use x=\"433.496094\" xlink:href=\"#DejaVuSans-53\"/>\r\n    </g>\r\n   </g>\r\n  </g>\r\n  <g id=\"axes_2\">\r\n   <g clip-path=\"url(#p958aa2ef16)\">\r\n    <image height=\"73\" id=\"image2e766b1356\" transform=\"scale(1 -1)translate(0 -73)\" width=\"73\" x=\"94.53913\" xlink:href=\"data:image/png;base64,\r\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\" y=\"-48.809486\"/>\r\n   </g>\r\n   <g id=\"text_2\">\r\n    <!-- Number 0 -->\r\n    <defs>\r\n     <path d=\"M 31.78125 66.40625 \r\nQ 24.171875 66.40625 20.328125 58.90625 \r\nQ 16.5 51.421875 16.5 36.375 \r\nQ 16.5 21.390625 20.328125 13.890625 \r\nQ 24.171875 6.390625 31.78125 6.390625 \r\nQ 39.453125 6.390625 43.28125 13.890625 \r\nQ 47.125 21.390625 47.125 36.375 \r\nQ 47.125 51.421875 43.28125 58.90625 \r\nQ 39.453125 66.40625 31.78125 66.40625 \r\nz\r\nM 31.78125 74.21875 \r\nQ 44.046875 74.21875 50.515625 64.515625 \r\nQ 56.984375 54.828125 56.984375 36.375 \r\nQ 56.984375 17.96875 50.515625 8.265625 \r\nQ 44.046875 -1.421875 31.78125 -1.421875 \r\nQ 19.53125 -1.421875 13.0625 8.265625 \r\nQ 6.59375 17.96875 6.59375 36.375 \r\nQ 6.59375 54.828125 13.0625 64.515625 \r\nQ 19.53125 74.21875 31.78125 74.21875 \r\nz\r\n\" id=\"DejaVuSans-48\"/>\r\n    </defs>\r\n    <g transform=\"translate(101.102935 43.026877)scale(0.12 -0.12)\">\r\n     <use xlink:href=\"#DejaVuSans-78\"/>\r\n     <use x=\"74.804688\" xlink:href=\"#DejaVuSans-117\"/>\r\n     <use x=\"138.183594\" xlink:href=\"#DejaVuSans-109\"/>\r\n     <use x=\"235.595703\" xlink:href=\"#DejaVuSans-98\"/>\r\n     <use x=\"299.072266\" xlink:href=\"#DejaVuSans-101\"/>\r\n     <use x=\"360.595703\" xlink:href=\"#DejaVuSans-114\"/>\r\n     <use x=\"401.708984\" xlink:href=\"#DejaVuSans-32\"/>\r\n     <use x=\"433.496094\" xlink:href=\"#DejaVuSans-48\"/>\r\n    </g>\r\n   </g>\r\n  </g>\r\n  <g id=\"axes_3\">\r\n   <g clip-path=\"url(#pe81dc9784e)\">\r\n    <image height=\"73\" id=\"imagea92c0d3000\" transform=\"scale(1 -1)translate(0 -73)\" width=\"73\" x=\"181.878261\" xlink:href=\"data:image/png;base64,\r\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\" y=\"-48.809486\"/>\r\n   </g>\r\n   <g id=\"text_3\">\r\n    <!-- Number 4 -->\r\n    <defs>\r\n     <path d=\"M 37.796875 64.3125 \r\nL 12.890625 25.390625 \r\nL 37.796875 25.390625 \r\nz\r\nM 35.203125 72.90625 \r\nL 47.609375 72.90625 \r\nL 47.609375 25.390625 \r\nL 58.015625 25.390625 \r\nL 58.015625 17.1875 \r\nL 47.609375 17.1875 \r\nL 47.609375 0 \r\nL 37.796875 0 \r\nL 37.796875 17.1875 \r\nL 4.890625 17.1875 \r\nL 4.890625 26.703125 \r\nz\r\n\" id=\"DejaVuSans-52\"/>\r\n    </defs>\r\n    <g transform=\"translate(188.442065 43.026877)scale(0.12 -0.12)\">\r\n     <use xlink:href=\"#DejaVuSans-78\"/>\r\n     <use x=\"74.804688\" xlink:href=\"#DejaVuSans-117\"/>\r\n     <use x=\"138.183594\" xlink:href=\"#DejaVuSans-109\"/>\r\n     <use x=\"235.595703\" xlink:href=\"#DejaVuSans-98\"/>\r\n     <use x=\"299.072266\" xlink:href=\"#DejaVuSans-101\"/>\r\n     <use x=\"360.595703\" xlink:href=\"#DejaVuSans-114\"/>\r\n     <use x=\"401.708984\" xlink:href=\"#DejaVuSans-32\"/>\r\n     <use x=\"433.496094\" xlink:href=\"#DejaVuSans-52\"/>\r\n    </g>\r\n   </g>\r\n  </g>\r\n  <g id=\"axes_4\">\r\n   <g clip-path=\"url(#pa3474b9ef6)\">\r\n    <image height=\"73\" id=\"image99db99df52\" transform=\"scale(1 -1)translate(0 -73)\" width=\"73\" x=\"269.217391\" xlink:href=\"data:image/png;base64,\r\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\" y=\"-48.809486\"/>\r\n   </g>\r\n   <g id=\"text_4\">\r\n    <!-- Number 1 -->\r\n    <defs>\r\n     <path d=\"M 12.40625 8.296875 \r\nL 28.515625 8.296875 \r\nL 28.515625 63.921875 \r\nL 10.984375 60.40625 \r\nL 10.984375 69.390625 \r\nL 28.421875 72.90625 \r\nL 38.28125 72.90625 \r\nL 38.28125 8.296875 \r\nL 54.390625 8.296875 \r\nL 54.390625 0 \r\nL 12.40625 0 \r\nz\r\n\" id=\"DejaVuSans-49\"/>\r\n    </defs>\r\n    <g transform=\"translate(275.781196 43.026877)scale(0.12 -0.12)\">\r\n     <use xlink:href=\"#DejaVuSans-78\"/>\r\n     <use x=\"74.804688\" xlink:href=\"#DejaVuSans-117\"/>\r\n     <use x=\"138.183594\" xlink:href=\"#DejaVuSans-109\"/>\r\n     <use x=\"235.595703\" xlink:href=\"#DejaVuSans-98\"/>\r\n     <use x=\"299.072266\" xlink:href=\"#DejaVuSans-101\"/>\r\n     <use x=\"360.595703\" xlink:href=\"#DejaVuSans-114\"/>\r\n     <use x=\"401.708984\" xlink:href=\"#DejaVuSans-32\"/>\r\n     <use x=\"433.496094\" xlink:href=\"#DejaVuSans-49\"/>\r\n    </g>\r\n   </g>\r\n  </g>\r\n  <g id=\"axes_5\">\r\n   <g clip-path=\"url(#pe548f120d6)\">\r\n    <image height=\"73\" id=\"imageb0ca0d25f4\" transform=\"scale(1 -1)translate(0 -73)\" width=\"73\" x=\"7.2\" xlink:href=\"data:image/png;base64,\r\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\" y=\"-167.413123\"/>\r\n   </g>\r\n   <g id=\"text_5\">\r\n    <!-- Number 9 -->\r\n    <defs>\r\n     <path d=\"M 10.984375 1.515625 \r\nL 10.984375 10.5 \r\nQ 14.703125 8.734375 18.5 7.8125 \r\nQ 22.3125 6.890625 25.984375 6.890625 \r\nQ 35.75 6.890625 40.890625 13.453125 \r\nQ 46.046875 20.015625 46.78125 33.40625 \r\nQ 43.953125 29.203125 39.59375 26.953125 \r\nQ 35.25 24.703125 29.984375 24.703125 \r\nQ 19.046875 24.703125 12.671875 31.3125 \r\nQ 6.296875 37.9375 6.296875 49.421875 \r\nQ 6.296875 60.640625 12.9375 67.421875 \r\nQ 19.578125 74.21875 30.609375 74.21875 \r\nQ 43.265625 74.21875 49.921875 64.515625 \r\nQ 56.59375 54.828125 56.59375 36.375 \r\nQ 56.59375 19.140625 48.40625 8.859375 \r\nQ 40.234375 -1.421875 26.421875 -1.421875 \r\nQ 22.703125 -1.421875 18.890625 -0.6875 \r\nQ 15.09375 0.046875 10.984375 1.515625 \r\nz\r\nM 30.609375 32.421875 \r\nQ 37.25 32.421875 41.125 36.953125 \r\nQ 45.015625 41.5 45.015625 49.421875 \r\nQ 45.015625 57.28125 41.125 61.84375 \r\nQ 37.25 66.40625 30.609375 66.40625 \r\nQ 23.96875 66.40625 20.09375 61.84375 \r\nQ 16.21875 57.28125 16.21875 49.421875 \r\nQ 16.21875 41.5 20.09375 36.953125 \r\nQ 23.96875 32.421875 30.609375 32.421875 \r\nz\r\n\" id=\"DejaVuSans-57\"/>\r\n    </defs>\r\n    <g transform=\"translate(13.763804 161.630514)scale(0.12 -0.12)\">\r\n     <use xlink:href=\"#DejaVuSans-78\"/>\r\n     <use x=\"74.804688\" xlink:href=\"#DejaVuSans-117\"/>\r\n     <use x=\"138.183594\" xlink:href=\"#DejaVuSans-109\"/>\r\n     <use x=\"235.595703\" xlink:href=\"#DejaVuSans-98\"/>\r\n     <use x=\"299.072266\" xlink:href=\"#DejaVuSans-101\"/>\r\n     <use x=\"360.595703\" xlink:href=\"#DejaVuSans-114\"/>\r\n     <use x=\"401.708984\" xlink:href=\"#DejaVuSans-32\"/>\r\n     <use x=\"433.496094\" xlink:href=\"#DejaVuSans-57\"/>\r\n    </g>\r\n   </g>\r\n  </g>\r\n  <g id=\"axes_6\">\r\n   <g clip-path=\"url(#p3d63a4b617)\">\r\n    <image height=\"73\" id=\"image2401fc0d3b\" transform=\"scale(1 -1)translate(0 -73)\" width=\"73\" x=\"94.53913\" xlink:href=\"data:image/png;base64,\r\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\" y=\"-167.413123\"/>\r\n   </g>\r\n   <g id=\"text_6\">\r\n    <!-- Number 2 -->\r\n    <defs>\r\n     <path d=\"M 19.1875 8.296875 \r\nL 53.609375 8.296875 \r\nL 53.609375 0 \r\nL 7.328125 0 \r\nL 7.328125 8.296875 \r\nQ 12.9375 14.109375 22.625 23.890625 \r\nQ 32.328125 33.6875 34.8125 36.53125 \r\nQ 39.546875 41.84375 41.421875 45.53125 \r\nQ 43.3125 49.21875 43.3125 52.78125 \r\nQ 43.3125 58.59375 39.234375 62.25 \r\nQ 35.15625 65.921875 28.609375 65.921875 \r\nQ 23.96875 65.921875 18.8125 64.3125 \r\nQ 13.671875 62.703125 7.8125 59.421875 \r\nL 7.8125 69.390625 \r\nQ 13.765625 71.78125 18.9375 73 \r\nQ 24.125 74.21875 28.421875 74.21875 \r\nQ 39.75 74.21875 46.484375 68.546875 \r\nQ 53.21875 62.890625 53.21875 53.421875 \r\nQ 53.21875 48.921875 51.53125 44.890625 \r\nQ 49.859375 40.875 45.40625 35.40625 \r\nQ 44.1875 33.984375 37.640625 27.21875 \r\nQ 31.109375 20.453125 19.1875 8.296875 \r\nz\r\n\" id=\"DejaVuSans-50\"/>\r\n    </defs>\r\n    <g transform=\"translate(101.102935 161.630514)scale(0.12 -0.12)\">\r\n     <use xlink:href=\"#DejaVuSans-78\"/>\r\n     <use x=\"74.804688\" xlink:href=\"#DejaVuSans-117\"/>\r\n     <use x=\"138.183594\" xlink:href=\"#DejaVuSans-109\"/>\r\n     <use x=\"235.595703\" xlink:href=\"#DejaVuSans-98\"/>\r\n     <use x=\"299.072266\" xlink:href=\"#DejaVuSans-101\"/>\r\n     <use x=\"360.595703\" xlink:href=\"#DejaVuSans-114\"/>\r\n     <use x=\"401.708984\" xlink:href=\"#DejaVuSans-32\"/>\r\n     <use x=\"433.496094\" xlink:href=\"#DejaVuSans-50\"/>\r\n    </g>\r\n   </g>\r\n  </g>\r\n  <g id=\"axes_7\">\r\n   <g clip-path=\"url(#p4e61aeb99b)\">\r\n    <image height=\"73\" id=\"image8cb5429bc7\" transform=\"scale(1 -1)translate(0 -73)\" width=\"73\" x=\"181.878261\" xlink:href=\"data:image/png;base64,\r\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\" y=\"-167.413123\"/>\r\n   </g>\r\n   <g id=\"text_7\">\r\n    <!-- Number 1 -->\r\n    <g transform=\"translate(188.442065 161.630514)scale(0.12 -0.12)\">\r\n     <use xlink:href=\"#DejaVuSans-78\"/>\r\n     <use x=\"74.804688\" xlink:href=\"#DejaVuSans-117\"/>\r\n     <use x=\"138.183594\" xlink:href=\"#DejaVuSans-109\"/>\r\n     <use x=\"235.595703\" xlink:href=\"#DejaVuSans-98\"/>\r\n     <use x=\"299.072266\" xlink:href=\"#DejaVuSans-101\"/>\r\n     <use x=\"360.595703\" xlink:href=\"#DejaVuSans-114\"/>\r\n     <use x=\"401.708984\" xlink:href=\"#DejaVuSans-32\"/>\r\n     <use x=\"433.496094\" xlink:href=\"#DejaVuSans-49\"/>\r\n    </g>\r\n   </g>\r\n  </g>\r\n  <g id=\"axes_8\">\r\n   <g clip-path=\"url(#p3a217d37d3)\">\r\n    <image height=\"73\" id=\"imageee13b55acc\" transform=\"scale(1 -1)translate(0 -73)\" width=\"73\" x=\"269.217391\" xlink:href=\"data:image/png;base64,\r\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\" y=\"-167.413123\"/>\r\n   </g>\r\n   <g id=\"text_8\">\r\n    <!-- Number 3 -->\r\n    <defs>\r\n     <path d=\"M 40.578125 39.3125 \r\nQ 47.65625 37.796875 51.625 33 \r\nQ 55.609375 28.21875 55.609375 21.1875 \r\nQ 55.609375 10.40625 48.1875 4.484375 \r\nQ 40.765625 -1.421875 27.09375 -1.421875 \r\nQ 22.515625 -1.421875 17.65625 -0.515625 \r\nQ 12.796875 0.390625 7.625 2.203125 \r\nL 7.625 11.71875 \r\nQ 11.71875 9.328125 16.59375 8.109375 \r\nQ 21.484375 6.890625 26.8125 6.890625 \r\nQ 36.078125 6.890625 40.9375 10.546875 \r\nQ 45.796875 14.203125 45.796875 21.1875 \r\nQ 45.796875 27.640625 41.28125 31.265625 \r\nQ 36.765625 34.90625 28.71875 34.90625 \r\nL 20.21875 34.90625 \r\nL 20.21875 43.015625 \r\nL 29.109375 43.015625 \r\nQ 36.375 43.015625 40.234375 45.921875 \r\nQ 44.09375 48.828125 44.09375 54.296875 \r\nQ 44.09375 59.90625 40.109375 62.90625 \r\nQ 36.140625 65.921875 28.71875 65.921875 \r\nQ 24.65625 65.921875 20.015625 65.03125 \r\nQ 15.375 64.15625 9.8125 62.3125 \r\nL 9.8125 71.09375 \r\nQ 15.4375 72.65625 20.34375 73.4375 \r\nQ 25.25 74.21875 29.59375 74.21875 \r\nQ 40.828125 74.21875 47.359375 69.109375 \r\nQ 53.90625 64.015625 53.90625 55.328125 \r\nQ 53.90625 49.265625 50.4375 45.09375 \r\nQ 46.96875 40.921875 40.578125 39.3125 \r\nz\r\n\" id=\"DejaVuSans-51\"/>\r\n    </defs>\r\n    <g transform=\"translate(275.781196 161.630514)scale(0.12 -0.12)\">\r\n     <use xlink:href=\"#DejaVuSans-78\"/>\r\n     <use x=\"74.804688\" xlink:href=\"#DejaVuSans-117\"/>\r\n     <use x=\"138.183594\" xlink:href=\"#DejaVuSans-109\"/>\r\n     <use x=\"235.595703\" xlink:href=\"#DejaVuSans-98\"/>\r\n     <use x=\"299.072266\" xlink:href=\"#DejaVuSans-101\"/>\r\n     <use x=\"360.595703\" xlink:href=\"#DejaVuSans-114\"/>\r\n     <use x=\"401.708984\" xlink:href=\"#DejaVuSans-32\"/>\r\n     <use x=\"433.496094\" xlink:href=\"#DejaVuSans-51\"/>\r\n    </g>\r\n   </g>\r\n  </g>\r\n  <g id=\"text_9\">\r\n   <!-- Image of Digits in MNIST Database -->\r\n   <defs>\r\n    <path d=\"M 9.8125 72.90625 \r\nL 19.671875 72.90625 \r\nL 19.671875 0 \r\nL 9.8125 0 \r\nz\r\n\" id=\"DejaVuSans-73\"/>\r\n    <path d=\"M 34.28125 27.484375 \r\nQ 23.390625 27.484375 19.1875 25 \r\nQ 14.984375 22.515625 14.984375 16.5 \r\nQ 14.984375 11.71875 18.140625 8.90625 \r\nQ 21.296875 6.109375 26.703125 6.109375 \r\nQ 34.1875 6.109375 38.703125 11.40625 \r\nQ 43.21875 16.703125 43.21875 25.484375 \r\nL 43.21875 27.484375 \r\nz\r\nM 52.203125 31.203125 \r\nL 52.203125 0 \r\nL 43.21875 0 \r\nL 43.21875 8.296875 \r\nQ 40.140625 3.328125 35.546875 0.953125 \r\nQ 30.953125 -1.421875 24.3125 -1.421875 \r\nQ 15.921875 -1.421875 10.953125 3.296875 \r\nQ 6 8.015625 6 15.921875 \r\nQ 6 25.140625 12.171875 29.828125 \r\nQ 18.359375 34.515625 30.609375 34.515625 \r\nL 43.21875 34.515625 \r\nL 43.21875 35.40625 \r\nQ 43.21875 41.609375 39.140625 45 \r\nQ 35.0625 48.390625 27.6875 48.390625 \r\nQ 23 48.390625 18.546875 47.265625 \r\nQ 14.109375 46.140625 10.015625 43.890625 \r\nL 10.015625 52.203125 \r\nQ 14.9375 54.109375 19.578125 55.046875 \r\nQ 24.21875 56 28.609375 56 \r\nQ 40.484375 56 46.34375 49.84375 \r\nQ 52.203125 43.703125 52.203125 31.203125 \r\nz\r\n\" id=\"DejaVuSans-97\"/>\r\n    <path d=\"M 45.40625 27.984375 \r\nQ 45.40625 37.75 41.375 43.109375 \r\nQ 37.359375 48.484375 30.078125 48.484375 \r\nQ 22.859375 48.484375 18.828125 43.109375 \r\nQ 14.796875 37.75 14.796875 27.984375 \r\nQ 14.796875 18.265625 18.828125 12.890625 \r\nQ 22.859375 7.515625 30.078125 7.515625 \r\nQ 37.359375 7.515625 41.375 12.890625 \r\nQ 45.40625 18.265625 45.40625 27.984375 \r\nz\r\nM 54.390625 6.78125 \r\nQ 54.390625 -7.171875 48.1875 -13.984375 \r\nQ 42 -20.796875 29.203125 -20.796875 \r\nQ 24.46875 -20.796875 20.265625 -20.09375 \r\nQ 16.0625 -19.390625 12.109375 -17.921875 \r\nL 12.109375 -9.1875 \r\nQ 16.0625 -11.328125 19.921875 -12.34375 \r\nQ 23.78125 -13.375 27.78125 -13.375 \r\nQ 36.625 -13.375 41.015625 -8.765625 \r\nQ 45.40625 -4.15625 45.40625 5.171875 \r\nL 45.40625 9.625 \r\nQ 42.625 4.78125 38.28125 2.390625 \r\nQ 33.9375 0 27.875 0 \r\nQ 17.828125 0 11.671875 7.65625 \r\nQ 5.515625 15.328125 5.515625 27.984375 \r\nQ 5.515625 40.671875 11.671875 48.328125 \r\nQ 17.828125 56 27.875 56 \r\nQ 33.9375 56 38.28125 53.609375 \r\nQ 42.625 51.21875 45.40625 46.390625 \r\nL 45.40625 54.6875 \r\nL 54.390625 54.6875 \r\nz\r\n\" id=\"DejaVuSans-103\"/>\r\n    <path d=\"M 30.609375 48.390625 \r\nQ 23.390625 48.390625 19.1875 42.75 \r\nQ 14.984375 37.109375 14.984375 27.296875 \r\nQ 14.984375 17.484375 19.15625 11.84375 \r\nQ 23.34375 6.203125 30.609375 6.203125 \r\nQ 37.796875 6.203125 41.984375 11.859375 \r\nQ 46.1875 17.53125 46.1875 27.296875 \r\nQ 46.1875 37.015625 41.984375 42.703125 \r\nQ 37.796875 48.390625 30.609375 48.390625 \r\nz\r\nM 30.609375 56 \r\nQ 42.328125 56 49.015625 48.375 \r\nQ 55.71875 40.765625 55.71875 27.296875 \r\nQ 55.71875 13.875 49.015625 6.21875 \r\nQ 42.328125 -1.421875 30.609375 -1.421875 \r\nQ 18.84375 -1.421875 12.171875 6.21875 \r\nQ 5.515625 13.875 5.515625 27.296875 \r\nQ 5.515625 40.765625 12.171875 48.375 \r\nQ 18.84375 56 30.609375 56 \r\nz\r\n\" id=\"DejaVuSans-111\"/>\r\n    <path d=\"M 37.109375 75.984375 \r\nL 37.109375 68.5 \r\nL 28.515625 68.5 \r\nQ 23.6875 68.5 21.796875 66.546875 \r\nQ 19.921875 64.59375 19.921875 59.515625 \r\nL 19.921875 54.6875 \r\nL 34.71875 54.6875 \r\nL 34.71875 47.703125 \r\nL 19.921875 47.703125 \r\nL 19.921875 0 \r\nL 10.890625 0 \r\nL 10.890625 47.703125 \r\nL 2.296875 47.703125 \r\nL 2.296875 54.6875 \r\nL 10.890625 54.6875 \r\nL 10.890625 58.5 \r\nQ 10.890625 67.625 15.140625 71.796875 \r\nQ 19.390625 75.984375 28.609375 75.984375 \r\nz\r\n\" id=\"DejaVuSans-102\"/>\r\n    <path d=\"M 19.671875 64.796875 \r\nL 19.671875 8.109375 \r\nL 31.59375 8.109375 \r\nQ 46.6875 8.109375 53.6875 14.9375 \r\nQ 60.6875 21.78125 60.6875 36.53125 \r\nQ 60.6875 51.171875 53.6875 57.984375 \r\nQ 46.6875 64.796875 31.59375 64.796875 \r\nz\r\nM 9.8125 72.90625 \r\nL 30.078125 72.90625 \r\nQ 51.265625 72.90625 61.171875 64.09375 \r\nQ 71.09375 55.28125 71.09375 36.53125 \r\nQ 71.09375 17.671875 61.125 8.828125 \r\nQ 51.171875 0 30.078125 0 \r\nL 9.8125 0 \r\nz\r\n\" id=\"DejaVuSans-68\"/>\r\n    <path d=\"M 9.421875 54.6875 \r\nL 18.40625 54.6875 \r\nL 18.40625 0 \r\nL 9.421875 0 \r\nz\r\nM 9.421875 75.984375 \r\nL 18.40625 75.984375 \r\nL 18.40625 64.59375 \r\nL 9.421875 64.59375 \r\nz\r\n\" id=\"DejaVuSans-105\"/>\r\n    <path d=\"M 18.3125 70.21875 \r\nL 18.3125 54.6875 \r\nL 36.8125 54.6875 \r\nL 36.8125 47.703125 \r\nL 18.3125 47.703125 \r\nL 18.3125 18.015625 \r\nQ 18.3125 11.328125 20.140625 9.421875 \r\nQ 21.96875 7.515625 27.59375 7.515625 \r\nL 36.8125 7.515625 \r\nL 36.8125 0 \r\nL 27.59375 0 \r\nQ 17.1875 0 13.234375 3.875 \r\nQ 9.28125 7.765625 9.28125 18.015625 \r\nL 9.28125 47.703125 \r\nL 2.6875 47.703125 \r\nL 2.6875 54.6875 \r\nL 9.28125 54.6875 \r\nL 9.28125 70.21875 \r\nz\r\n\" id=\"DejaVuSans-116\"/>\r\n    <path d=\"M 44.28125 53.078125 \r\nL 44.28125 44.578125 \r\nQ 40.484375 46.53125 36.375 47.5 \r\nQ 32.28125 48.484375 27.875 48.484375 \r\nQ 21.1875 48.484375 17.84375 46.4375 \r\nQ 14.5 44.390625 14.5 40.28125 \r\nQ 14.5 37.15625 16.890625 35.375 \r\nQ 19.28125 33.59375 26.515625 31.984375 \r\nL 29.59375 31.296875 \r\nQ 39.15625 29.25 43.1875 25.515625 \r\nQ 47.21875 21.78125 47.21875 15.09375 \r\nQ 47.21875 7.46875 41.1875 3.015625 \r\nQ 35.15625 -1.421875 24.609375 -1.421875 \r\nQ 20.21875 -1.421875 15.453125 -0.5625 \r\nQ 10.6875 0.296875 5.421875 2 \r\nL 5.421875 11.28125 \r\nQ 10.40625 8.6875 15.234375 7.390625 \r\nQ 20.0625 6.109375 24.8125 6.109375 \r\nQ 31.15625 6.109375 34.5625 8.28125 \r\nQ 37.984375 10.453125 37.984375 14.40625 \r\nQ 37.984375 18.0625 35.515625 20.015625 \r\nQ 33.0625 21.96875 24.703125 23.78125 \r\nL 21.578125 24.515625 \r\nQ 13.234375 26.265625 9.515625 29.90625 \r\nQ 5.8125 33.546875 5.8125 39.890625 \r\nQ 5.8125 47.609375 11.28125 51.796875 \r\nQ 16.75 56 26.8125 56 \r\nQ 31.78125 56 36.171875 55.265625 \r\nQ 40.578125 54.546875 44.28125 53.078125 \r\nz\r\n\" id=\"DejaVuSans-115\"/>\r\n    <path d=\"M 54.890625 33.015625 \r\nL 54.890625 0 \r\nL 45.90625 0 \r\nL 45.90625 32.71875 \r\nQ 45.90625 40.484375 42.875 44.328125 \r\nQ 39.84375 48.1875 33.796875 48.1875 \r\nQ 26.515625 48.1875 22.3125 43.546875 \r\nQ 18.109375 38.921875 18.109375 30.90625 \r\nL 18.109375 0 \r\nL 9.078125 0 \r\nL 9.078125 54.6875 \r\nL 18.109375 54.6875 \r\nL 18.109375 46.1875 \r\nQ 21.34375 51.125 25.703125 53.5625 \r\nQ 30.078125 56 35.796875 56 \r\nQ 45.21875 56 50.046875 50.171875 \r\nQ 54.890625 44.34375 54.890625 33.015625 \r\nz\r\n\" id=\"DejaVuSans-110\"/>\r\n    <path d=\"M 9.8125 72.90625 \r\nL 24.515625 72.90625 \r\nL 43.109375 23.296875 \r\nL 61.8125 72.90625 \r\nL 76.515625 72.90625 \r\nL 76.515625 0 \r\nL 66.890625 0 \r\nL 66.890625 64.015625 \r\nL 48.09375 14.015625 \r\nL 38.1875 14.015625 \r\nL 19.390625 64.015625 \r\nL 19.390625 0 \r\nL 9.8125 0 \r\nz\r\n\" id=\"DejaVuSans-77\"/>\r\n    <path d=\"M 53.515625 70.515625 \r\nL 53.515625 60.890625 \r\nQ 47.90625 63.578125 42.921875 64.890625 \r\nQ 37.9375 66.21875 33.296875 66.21875 \r\nQ 25.25 66.21875 20.875 63.09375 \r\nQ 16.5 59.96875 16.5 54.203125 \r\nQ 16.5 49.359375 19.40625 46.890625 \r\nQ 22.3125 44.4375 30.421875 42.921875 \r\nL 36.375 41.703125 \r\nQ 47.40625 39.59375 52.65625 34.296875 \r\nQ 57.90625 29 57.90625 20.125 \r\nQ 57.90625 9.515625 50.796875 4.046875 \r\nQ 43.703125 -1.421875 29.984375 -1.421875 \r\nQ 24.8125 -1.421875 18.96875 -0.25 \r\nQ 13.140625 0.921875 6.890625 3.21875 \r\nL 6.890625 13.375 \r\nQ 12.890625 10.015625 18.65625 8.296875 \r\nQ 24.421875 6.59375 29.984375 6.59375 \r\nQ 38.421875 6.59375 43.015625 9.90625 \r\nQ 47.609375 13.234375 47.609375 19.390625 \r\nQ 47.609375 24.75 44.3125 27.78125 \r\nQ 41.015625 30.8125 33.5 32.328125 \r\nL 27.484375 33.5 \r\nQ 16.453125 35.6875 11.515625 40.375 \r\nQ 6.59375 45.0625 6.59375 53.421875 \r\nQ 6.59375 63.09375 13.40625 68.65625 \r\nQ 20.21875 74.21875 32.171875 74.21875 \r\nQ 37.3125 74.21875 42.625 73.28125 \r\nQ 47.953125 72.359375 53.515625 70.515625 \r\nz\r\n\" id=\"DejaVuSans-83\"/>\r\n    <path d=\"M -0.296875 72.90625 \r\nL 61.375 72.90625 \r\nL 61.375 64.59375 \r\nL 35.5 64.59375 \r\nL 35.5 0 \r\nL 25.59375 0 \r\nL 25.59375 64.59375 \r\nL -0.296875 64.59375 \r\nz\r\n\" id=\"DejaVuSans-84\"/>\r\n   </defs>\r\n   <g transform=\"translate(64.84125 16.318125)scale(0.12 -0.12)\">\r\n    <use xlink:href=\"#DejaVuSans-73\"/>\r\n    <use x=\"29.492188\" xlink:href=\"#DejaVuSans-109\"/>\r\n    <use x=\"126.904297\" xlink:href=\"#DejaVuSans-97\"/>\r\n    <use x=\"188.183594\" xlink:href=\"#DejaVuSans-103\"/>\r\n    <use x=\"251.660156\" xlink:href=\"#DejaVuSans-101\"/>\r\n    <use x=\"313.183594\" xlink:href=\"#DejaVuSans-32\"/>\r\n    <use x=\"344.970703\" xlink:href=\"#DejaVuSans-111\"/>\r\n    <use x=\"406.152344\" xlink:href=\"#DejaVuSans-102\"/>\r\n    <use x=\"441.357422\" xlink:href=\"#DejaVuSans-32\"/>\r\n    <use x=\"473.144531\" xlink:href=\"#DejaVuSans-68\"/>\r\n    <use x=\"550.146484\" xlink:href=\"#DejaVuSans-105\"/>\r\n    <use x=\"577.929688\" xlink:href=\"#DejaVuSans-103\"/>\r\n    <use x=\"641.40625\" xlink:href=\"#DejaVuSans-105\"/>\r\n    <use x=\"669.189453\" xlink:href=\"#DejaVuSans-116\"/>\r\n    <use x=\"708.398438\" xlink:href=\"#DejaVuSans-115\"/>\r\n    <use x=\"760.498047\" xlink:href=\"#DejaVuSans-32\"/>\r\n    <use x=\"792.285156\" xlink:href=\"#DejaVuSans-105\"/>\r\n    <use x=\"820.068359\" xlink:href=\"#DejaVuSans-110\"/>\r\n    <use x=\"883.447266\" xlink:href=\"#DejaVuSans-32\"/>\r\n    <use x=\"915.234375\" xlink:href=\"#DejaVuSans-77\"/>\r\n    <use x=\"1001.513672\" xlink:href=\"#DejaVuSans-78\"/>\r\n    <use x=\"1076.318359\" xlink:href=\"#DejaVuSans-73\"/>\r\n    <use x=\"1105.810547\" xlink:href=\"#DejaVuSans-83\"/>\r\n    <use x=\"1169.287109\" xlink:href=\"#DejaVuSans-84\"/>\r\n    <use x=\"1230.371094\" xlink:href=\"#DejaVuSans-32\"/>\r\n    <use x=\"1262.158203\" xlink:href=\"#DejaVuSans-68\"/>\r\n    <use x=\"1339.160156\" xlink:href=\"#DejaVuSans-97\"/>\r\n    <use x=\"1400.439453\" xlink:href=\"#DejaVuSans-116\"/>\r\n    <use x=\"1439.648438\" xlink:href=\"#DejaVuSans-97\"/>\r\n    <use x=\"1500.927734\" xlink:href=\"#DejaVuSans-98\"/>\r\n    <use x=\"1564.404297\" xlink:href=\"#DejaVuSans-97\"/>\r\n    <use x=\"1625.683594\" xlink:href=\"#DejaVuSans-115\"/>\r\n    <use x=\"1677.783203\" xlink:href=\"#DejaVuSans-101\"/>\r\n   </g>\r\n  </g>\r\n </g>\r\n <defs>\r\n  <clipPath id=\"p2718ecef10\">\r\n   <rect height=\"72.782609\" width=\"72.782609\" x=\"7.2\" y=\"49.026877\"/>\r\n  </clipPath>\r\n  <clipPath id=\"p958aa2ef16\">\r\n   <rect height=\"72.782609\" width=\"72.782609\" x=\"94.53913\" y=\"49.026877\"/>\r\n  </clipPath>\r\n  <clipPath id=\"pe81dc9784e\">\r\n   <rect height=\"72.782609\" width=\"72.782609\" x=\"181.878261\" y=\"49.026877\"/>\r\n  </clipPath>\r\n  <clipPath id=\"pa3474b9ef6\">\r\n   <rect height=\"72.782609\" width=\"72.782609\" x=\"269.217391\" y=\"49.026877\"/>\r\n  </clipPath>\r\n  <clipPath id=\"pe548f120d6\">\r\n   <rect height=\"72.782609\" width=\"72.782609\" x=\"7.2\" y=\"167.630514\"/>\r\n  </clipPath>\r\n  <clipPath id=\"p3d63a4b617\">\r\n   <rect height=\"72.782609\" width=\"72.782609\" x=\"94.53913\" y=\"167.630514\"/>\r\n  </clipPath>\r\n  <clipPath id=\"p4e61aeb99b\">\r\n   <rect height=\"72.782609\" width=\"72.782609\" x=\"181.878261\" y=\"167.630514\"/>\r\n  </clipPath>\r\n  <clipPath id=\"p3a217d37d3\">\r\n   <rect height=\"72.782609\" width=\"72.782609\" x=\"269.217391\" y=\"167.630514\"/>\r\n  </clipPath>\r\n </defs>\r\n</svg>\r\n",
      "image/png": "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\n"
     },
     "metadata": {
      "needs_background": "light"
     }
    }
   ],
   "source": [
    "fig, axes = plt.subplots(2, 4)\n",
    "for i, ax in zip(range(8), axes.flatten()):\n",
    "    ax.imshow(X_train[i], cmap=plt.cm.gray_r, interpolation='nearest')\n",
    "    ax.set_title(\"Number %d\" % y_train[i])\n",
    "    ax.set_axis_off()\n",
    "\n",
    "fig.suptitle(\"Image of Digits in MNIST Database\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Training a convolutional neural network with TensorFlow\n",
    "\n",
    "Each pixel in the images is stored as integers ranging from 0 to 255. CNN requires us to normalize the numbers to be between 0 and 1. We also increased a dimension so that the images can be fed into the CNN. Also, convert the labels (*y_train, y_test*) to one-hot encoding since we are categorizing images."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Normalize and flatten the images\n",
    "x_train = X_train.reshape((60000, 28, 28, 1)).astype('float32') / 255\n",
    "x_test  = X_test.reshape((10000, 28, 28, 1)).astype('float32') / 255"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stderr",
     "text": "Using TensorFlow backend.\n"
    }
   ],
   "source": [
    "# Convert to one-hot encoding\n",
    "from keras.utils import np_utils\n",
    "y_train = np_utils.to_categorical(y_train)\n",
    "y_test  = np_utils.to_categorical(y_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is the structure of the convolutional neural network. We have two convolution layers to extract features, along with two pooling layers to reduce the dimension of the features. The dropout layer disgards 20% of the data to prevent overfitting. The multi-dimensional data is then flattened in to vectors. The two dence layers with 128 neurons are trained to do the classification. Lastly, the dense layer with 10 neurons output the results."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": "Train on 60000 samples\nEpoch 1/10\n60000/60000 [==============================] - 12s 199us/sample - loss: 0.1625 - accuracy: 0.9496\nEpoch 2/10\n60000/60000 [==============================] - 7s 120us/sample - loss: 0.0563 - accuracy: 0.9822\nEpoch 3/10\n60000/60000 [==============================] - 7s 117us/sample - loss: 0.0423 - accuracy: 0.9865\nEpoch 4/10\n60000/60000 [==============================] - 7s 121us/sample - loss: 0.0351 - accuracy: 0.9888\nEpoch 5/10\n60000/60000 [==============================] - 7s 123us/sample - loss: 0.0290 - accuracy: 0.9908\nEpoch 6/10\n60000/60000 [==============================] - 7s 121us/sample - loss: 0.0255 - accuracy: 0.9921\nEpoch 7/10\n60000/60000 [==============================] - 7s 121us/sample - loss: 0.0218 - accuracy: 0.9929\nEpoch 8/10\n60000/60000 [==============================] - 7s 122us/sample - loss: 0.0199 - accuracy: 0.9937\nEpoch 9/10\n60000/60000 [==============================] - 7s 124us/sample - loss: 0.0182 - accuracy: 0.9942\nEpoch 10/10\n60000/60000 [==============================] - 7s 122us/sample - loss: 0.0162 - accuracy: 0.9946\n"
    },
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "<tensorflow.python.keras.callbacks.History at 0x18e5940b308>"
     },
     "metadata": {},
     "execution_count": 6
    }
   ],
   "source": [
    "model = keras.Sequential([\n",
    "    \n",
    "    keras.layers.Conv2D(32, (5,5), activation = 'relu'),\n",
    "    keras.layers.MaxPool2D(pool_size = (2,2)),\n",
    "    \n",
    "    keras.layers.Conv2D(32, (5,5), activation = 'relu'),\n",
    "    keras.layers.MaxPool2D(pool_size = (2,2)),\n",
    "    \n",
    "    keras.layers.Dropout(rate = 0.2),\n",
    "    keras.layers.Flatten(),\n",
    "    \n",
    "    keras.layers.Dense(units = 128, activation = 'relu'),\n",
    "    keras.layers.Dense(units = 128, activation = 'relu'),\n",
    "    \n",
    "    keras.layers.Dense(units = 10, activation = 'softmax')\n",
    "])\n",
    "\n",
    "model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])\n",
    "\n",
    "model.fit(x_train, y_train, epochs=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": "10000/10000 - 1s - loss: 0.0290 - accuracy: 0.9921\n\nTest accuracy: 0.9921\n"
    }
   ],
   "source": [
    "# Test the accuracy of the model on the testing set\n",
    "test_loss, test_acc = model.evaluate(x_test,  y_test, verbose = 2)\n",
    "\n",
    "print()\n",
    "print('Test accuracy:', test_acc)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The accuracy of the CNN is 99.46% and its performance on the testing set is 99.21%. No overfitting. We have a robust model!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Saving the trained model\n",
    "\n",
    "Below is the summary of the model. It is amazing that we have trained 109,930 parameters! Now, save this model so we don't have to train it again in the future."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": "Model: \"sequential\"\n_________________________________________________________________\nLayer (type)                 Output Shape              Param #   \n=================================================================\nconv2d (Conv2D)              multiple                  832       \n_________________________________________________________________\nmax_pooling2d (MaxPooling2D) multiple                  0         \n_________________________________________________________________\nconv2d_1 (Conv2D)            multiple                  25632     \n_________________________________________________________________\nmax_pooling2d_1 (MaxPooling2 multiple                  0         \n_________________________________________________________________\ndropout (Dropout)            multiple                  0         \n_________________________________________________________________\nflatten (Flatten)            multiple                  0         \n_________________________________________________________________\ndense (Dense)                multiple                  65664     \n_________________________________________________________________\ndense_1 (Dense)              multiple                  16512     \n_________________________________________________________________\ndense_2 (Dense)              multiple                  1290      \n=================================================================\nTotal params: 109,930\nTrainable params: 109,930\nNon-trainable params: 0\n_________________________________________________________________\n"
    }
   ],
   "source": [
    "# Show the model architecture\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Just like in the previous notebook, we can save this model as well."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.save(\"CNN_model.h5\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.4-final"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}