handson-ml/13_convolutional_neural_networks.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "**Chapter 13 – Convolutional Neural Networks**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "_This notebook contains all the sample code and solutions to the exercices in chapter 13._"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "# Setup"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "First, let's make sure this notebook works well in both python 2 and 3, import a few common modules, ensure MatplotLib plots figures inline and prepare a function to save the figures:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "# To support both python 2 and python 3\n",
    "from __future__ import division, print_function, unicode_literals\n",
    "\n",
    "# Common imports\n",
    "import numpy as np\n",
    "import numpy.random as rnd\n",
    "import os\n",
    "\n",
    "# to make this notebook's output stable across runs\n",
    "rnd.seed(42)\n",
    "\n",
    "# To plot pretty figures\n",
    "%matplotlib inline\n",
    "import matplotlib\n",
    "import matplotlib.pyplot as plt\n",
    "plt.rcParams['axes.labelsize'] = 14\n",
    "plt.rcParams['xtick.labelsize'] = 12\n",
    "plt.rcParams['ytick.labelsize'] = 12\n",
    "\n",
    "# Where to save the figures\n",
    "PROJECT_ROOT_DIR = \".\"\n",
    "CHAPTER_ID = \"cnn\"\n",
    "\n",
    "def save_fig(fig_id, tight_layout=True):\n",
    "    path = os.path.join(PROJECT_ROOT_DIR, \"images\", CHAPTER_ID, fig_id + \".png\")\n",
    "    print(\"Saving figure\", fig_id)\n",
    "    if tight_layout:\n",
    "        plt.tight_layout()\n",
    "    plt.savefig(path, format='png', dpi=300)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "A couple utility functions to plot grayscale and RGB images:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "def plot_image(image):\n",
    "    plt.imshow(image, cmap=\"gray\", interpolation=\"nearest\")\n",
    "    plt.axis(\"off\")\n",
    "\n",
    "def plot_color_image(image):\n",
    "    plt.imshow(image.astype(np.uint8),interpolation=\"nearest\")\n",
    "    plt.axis(\"off\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "And of course we will need TensorFlow:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "import tensorflow as tf"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "# Convolutional layer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "from sklearn.datasets import load_sample_image\n",
    "china = load_sample_image(\"china.jpg\")\n",
    "flower = load_sample_image(\"flower.jpg\")\n",
    "image = china[150:220, 130:250]\n",
    "height, width, channels = image.shape\n",
    "image_grayscale = image.mean(axis=2).astype(np.float32)\n",
    "images = image_grayscale.reshape(1, height, width, 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "fmap = np.zeros(shape=(7, 7, 1, 2), dtype=np.float32)\n",
    "fmap[:, 3, 0, 0] = 1\n",
    "fmap[3, :, 0, 1] = 1\n",
    "fmap[:, :, 0, 0]\n",
    "plot_image(fmap[:, :, 0, 0])\n",
    "plt.show()\n",
    "plot_image(fmap[:, :, 0, 1])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "tf.reset_default_graph()\n",
    "\n",
    "X = tf.placeholder(tf.float32, shape=(None, height, width, 1))\n",
    "feature_maps = tf.constant(fmap)\n",
    "convolution = tf.nn.conv2d(X, feature_maps, strides=[1,1,1,1], padding=\"SAME\", use_cudnn_on_gpu=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "with tf.Session() as sess:\n",
    "    output = convolution.eval(feed_dict={X: images})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "plot_image(images[0, :, :, 0])\n",
    "save_fig(\"china_original\", tight_layout=False)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "plot_image(output[0, :, :, 0])\n",
    "save_fig(\"china_vertical\", tight_layout=False)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "plot_image(output[0, :, :, 1])\n",
    "save_fig(\"china_horizontal\", tight_layout=False)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "## Simple example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "dataset = np.array([china, flower], dtype=np.float32)\n",
    "batch_size, height, width, channels = dataset.shape\n",
    "\n",
    "filters = np.zeros(shape=(7, 7, channels, 2), dtype=np.float32)\n",
    "filters[:, 3, :, 0] = 1  # vertical line\n",
    "filters[3, :, :, 1] = 1  # horizontal line\n",
    "\n",
    "X = tf.placeholder(tf.float32, shape=(None, height, width, channels))\n",
    "convolution = tf.nn.conv2d(X, filters, strides=[1,2,2,1], padding=\"SAME\")\n",
    "\n",
    "with tf.Session() as sess:\n",
    "    output = sess.run(convolution, feed_dict={X: dataset})\n",
    "\n",
    "for image_index in (0, 1):\n",
    "    for feature_map_index in (0, 1):\n",
    "        plot_image(output[image_index, :, :, feature_map_index])\n",
    "        plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "## VALID vs SAME padding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "tf.reset_default_graph()\n",
    "\n",
    "filter_primes = np.array([2., 3., 5., 7., 11., 13.], dtype=np.float32)\n",
    "x = tf.constant(np.arange(1, 13+1, dtype=np.float32).reshape([1, 1, 13, 1]))\n",
    "filters = tf.constant(filter_primes.reshape(1, 6, 1, 1))\n",
    "\n",
    "valid_conv = tf.nn.conv2d(x, filters, strides=[1, 1, 5, 1], padding='VALID')\n",
    "same_conv = tf.nn.conv2d(x, filters, strides=[1, 1, 5, 1], padding='SAME')\n",
    "\n",
    "with tf.Session() as sess:\n",
    "    print(\"VALID:\\n\", valid_conv.eval())\n",
    "    print(\"SAME:\\n\", same_conv.eval())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "print(\"VALID:\")\n",
    "print(np.array([1,2,3,4,5,6]).T.dot(filter_primes))\n",
    "print(np.array([6,7,8,9,10,11]).T.dot(filter_primes))\n",
    "print(\"SAME:\")\n",
    "print(np.array([0,1,2,3,4,5]).T.dot(filter_primes))\n",
    "print(np.array([5,6,7,8,9,10]).T.dot(filter_primes))\n",
    "print(np.array([10,11,12,13,0,0]).T.dot(filter_primes))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "# Pooling layer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "batch_size, height, width, channels = dataset.shape\n",
    "\n",
    "filters = np.zeros(shape=(7, 7, channels, 2), dtype=np.float32)\n",
    "filters[:, 3, :, 0] = 1  # vertical line\n",
    "filters[3, :, :, 1] = 1  # horizontal line\n",
    "\n",
    "X = tf.placeholder(tf.float32, shape=(None, height, width, channels))\n",
    "max_pool = tf.nn.max_pool(X, ksize=[1, 2, 2, 1], strides=[1,2,2,1], padding=\"VALID\")\n",
    "\n",
    "with tf.Session() as sess:\n",
    "    output = sess.run(max_pool, feed_dict={X: dataset})\n",
    "\n",
    "plot_color_image(dataset[0])\n",
    "save_fig(\"china_original\")\n",
    "plt.show()\n",
    "    \n",
    "plot_color_image(output[0])\n",
    "save_fig(\"china_max_pool\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "# MNIST"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "from sklearn.datasets import fetch_mldata\n",
    "\n",
    "mnist = fetch_mldata('MNIST original')\n",
    "X_train, X_test = mnist[\"data\"][:60000].astype(np.float64), mnist[\"data\"][60000:].astype(np.float64)\n",
    "y_train, y_test = mnist[\"target\"][:60000].astype(np.int64), mnist[\"target\"][60000:].astype(np.int64)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "height, width = 28, 28\n",
    "images = X_test[5000].reshape(1, height, width, 1)\n",
    "plot_image(images[0, :, :, 0])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "# Inception v3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "import sys\n",
    "import tarfile\n",
    "from six.moves import urllib\n",
    "\n",
    "TF_MODELS_URL = \"http://download.tensorflow.org/models\"\n",
    "INCEPTION_V3_URL = TF_MODELS_URL + \"/inception_v3_2016_08_28.tar.gz\"\n",
    "INCEPTION_PATH = os.path.join(\"datasets\", \"inception\")\n",
    "INCEPTION_V3_CHECKPOINT_PATH = os.path.join(INCEPTION_PATH, \"inception_v3.ckpt\")\n",
    "\n",
    "def download_progress(count, block_size, total_size):\n",
    "    percent = count * block_size * 100 // total_size\n",
    "    sys.stdout.write(\"\\rDownloading: {}%\".format(percent))\n",
    "    sys.stdout.flush()\n",
    "\n",
    "def fetch_pretrained_inception_v3(url=INCEPTION_V3_URL, path=INCEPTION_PATH):\n",
    "    if os.path.exists(INCEPTION_V3_CHECKPOINT_PATH):\n",
    "        return\n",
    "    os.makedirs(path, exist_ok=True)\n",
    "    tgz_path = os.path.join(path, \"inception_v3.tgz\")\n",
    "    urllib.request.urlretrieve(url, tgz_path, reporthook=download_progress)\n",
    "    inception_tgz = tarfile.open(tgz_path)\n",
    "    inception_tgz.extractall(path=path)\n",
    "    inception_tgz.close()\n",
    "    os.remove(tgz_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "fetch_pretrained_inception_v3()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "import re\n",
    "\n",
    "CLASS_NAME_REGEX = re.compile(r\"^n\\d+\\s+(.*)\\s*$\", re.M | re.U)\n",
    "\n",
    "def load_class_names():\n",
    "    with open(os.path.join(\"datasets\",\"inception\",\"imagenet_class_names.txt\"), \"rb\") as f:\n",
    "        content = f.read().decode(\"utf-8\")\n",
    "        return CLASS_NAME_REGEX.findall(content)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "class_names = load_class_names()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "width = 299\n",
    "height = 299\n",
    "channels = 3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "import matplotlib.image as mpimg\n",
    "test_image = mpimg.imread(os.path.join(\"images\",\"cnn\",\"test_image.png\"))[:, :, :channels]\n",
    "plt.imshow(test_image)\n",
    "plt.axis(\"off\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "from tensorflow.contrib.slim.nets import inception\n",
    "import tensorflow.contrib.slim as slim\n",
    "\n",
    "tf.reset_default_graph()\n",
    "\n",
    "X = tf.placeholder(tf.float32, shape=[None, height, width, channels], name=\"X\")\n",
    "with slim.arg_scope(inception.inception_v3_arg_scope()):\n",
    "    logits, end_points = inception.inception_v3(X, num_classes=1001, is_training=False)\n",
    "predictions = end_points[\"Predictions\"]\n",
    "saver = tf.train.Saver()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "X_test = test_image.reshape(-1, height, width, channels)\n",
    "\n",
    "with tf.Session() as sess:\n",
    "    saver.restore(sess, INCEPTION_V3_CHECKPOINT_PATH)\n",
    "    predictions_val = predictions.eval(feed_dict={X: X_test})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "class_names[np.argmax(predictions_val[0])]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "np.argmax(predictions_val, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "top_5 = np.argpartition(predictions_val[0], -5)[-5:]\n",
    "top_5 = top_5[np.argsort(predictions_val[0][top_5])]\n",
    "for i in top_5:\n",
    "    print(\"{0}: {1:.2f}%\".format(class_names[i], 100*predictions_val[0][i]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "source": [
    "# Exercise solutions"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "**Coming soon**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.5.2+"
  },
  "nav_menu": {},
  "toc": {
   "navigate_menu": true,
   "number_sections": true,
   "sideBar": true,
   "threshold": 6,
   "toc_cell": false,
   "toc_section_display": "block",
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}