2016-09-27 23:31:21 +02:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Chapter 10 –
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"_This notebook contains all the sample code and solutions to the exercices in chapter 10._"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Setup"
]
},
{
"cell_type": "markdown",
"metadata": {},
"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
},
"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 = \"ann\"\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": {},
"source": [
"# Perceptrons"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from sklearn.datasets import load_iris\n",
"iris = load_iris()\n",
"X = iris.data[:, (2, 3)] # petal length, petal width\n",
"y = (iris.target == 0).astype(np.int)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"from sklearn.linear_model import Perceptron\n",
"\n",
"per_clf = Perceptron(random_state=42)\n",
"per_clf.fit(X, y)\n",
"\n",
"y_pred = per_clf.predict([[2, 0.5]])\n",
"y_pred"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"a = -per_clf.coef_[0][0] / per_clf.coef_[0][1]\n",
"b = -per_clf.intercept_ / per_clf.coef_[0][1]\n",
"\n",
"axes = [0, 5, 0, 2]\n",
"\n",
"x0, x1 = np.meshgrid(\n",
" np.linspace(axes[0], axes[1], 500).reshape(-1, 1),\n",
" np.linspace(axes[2], axes[3], 200).reshape(-1, 1),\n",
" )\n",
"X_new = np.c_[x0.ravel(), x1.ravel()]\n",
"y_predict = per_clf.predict(X_new)\n",
"zz = y_predict.reshape(x0.shape)\n",
"\n",
"plt.figure(figsize=(10, 4))\n",
"plt.plot(X[y==0, 0], X[y==0, 1], \"bs\", label=\"Not Iris-Setosa\")\n",
"plt.plot(X[y==1, 0], X[y==1, 1], \"yo\", label=\"Iris-Setosa\")\n",
"\n",
"plt.plot([axes[0], axes[1]], [a * axes[0] + b, a * axes[1] + b], \"k-\", linewidth=3)\n",
"from matplotlib.colors import ListedColormap\n",
"custom_cmap = ListedColormap(['#9898ff', '#fafab0'])\n",
"\n",
"plt.contourf(x0, x1, zz, cmap=custom_cmap, linewidth=5)\n",
"plt.xlabel(\"Petal length\", fontsize=14)\n",
"plt.ylabel(\"Petal width\", fontsize=14)\n",
"plt.legend(loc=\"lower right\", fontsize=14)\n",
"plt.axis(axes)\n",
"\n",
"save_fig(\"perceptron_iris_plot\")\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Activation functions"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def logit(z):\n",
" return 1 / (1 + np.exp(-z))\n",
"\n",
"def relu(z):\n",
" return np.maximum(0, z)\n",
"\n",
"def derivative(f, z, eps=0.000001):\n",
" return (f(z + eps) - f(z - eps))/(2 * eps)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"z = np.linspace(-5, 5, 200)\n",
"\n",
"plt.figure(figsize=(11,4))\n",
"\n",
"plt.subplot(121)\n",
"plt.plot(z, np.sign(z), \"r-\", linewidth=2, label=\"Step\")\n",
"plt.plot(z, logit(z), \"g--\", linewidth=2, label=\"Logit\")\n",
"plt.plot(z, np.tanh(z), \"b-\", linewidth=2, label=\"Tanh\")\n",
"plt.plot(z, relu(z), \"m-.\", linewidth=2, label=\"ReLU\")\n",
"plt.grid(True)\n",
"plt.legend(loc=\"center right\", fontsize=14)\n",
"plt.title(\"Activation functions\", fontsize=14)\n",
"plt.axis([-5, 5, -1.2, 1.2])\n",
"\n",
"plt.subplot(122)\n",
"plt.plot(z, derivative(np.sign, z), \"r-\", linewidth=2, label=\"Step\")\n",
"plt.plot(0, 0, \"ro\", markersize=5)\n",
"plt.plot(0, 0, \"rx\", markersize=10)\n",
"plt.plot(z, derivative(logit, z), \"g--\", linewidth=2, label=\"Logit\")\n",
"plt.plot(z, derivative(np.tanh, z), \"b-\", linewidth=2, label=\"Tanh\")\n",
"plt.plot(z, derivative(relu, z), \"m-.\", linewidth=2, label=\"ReLU\")\n",
"plt.grid(True)\n",
"#plt.legend(loc=\"center right\", fontsize=14)\n",
"plt.title(\"Derivatives\", fontsize=14)\n",
"plt.axis([-5, 5, -0.2, 1.2])\n",
"\n",
"save_fig(\"activation_functions_plot\")\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def heaviside(z):\n",
" return (z >= 0).astype(z.dtype)\n",
"\n",
"def sigmoid(z):\n",
" return 1/(1+np.exp(-z))\n",
"\n",
"def mlp_xor(x1, x2, activation=heaviside):\n",
" return activation(-activation(x1 + x2 - 1.5) + activation(x1 + x2 - 0.5) - 0.5)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"x1s = np.linspace(-0.2, 1.2, 100)\n",
"x2s = np.linspace(-0.2, 1.2, 100)\n",
"x1, x2 = np.meshgrid(x1s, x2s)\n",
"\n",
"z1 = mlp_xor(x1, x2, activation=heaviside)\n",
"z2 = mlp_xor(x1, x2, activation=sigmoid)\n",
"\n",
"plt.figure(figsize=(10,4))\n",
"\n",
"plt.subplot(121)\n",
"plt.contourf(x1, x2, z1)\n",
"plt.plot([0, 1], [0, 1], \"gs\", markersize=20)\n",
"plt.plot([0, 1], [1, 0], \"y^\", markersize=20)\n",
"plt.title(\"Activation function: heaviside\", fontsize=14)\n",
"plt.grid(True)\n",
"\n",
"plt.subplot(122)\n",
"plt.contourf(x1, x2, z2)\n",
"plt.plot([0, 1], [0, 1], \"gs\", markersize=20)\n",
"plt.plot([0, 1], [1, 0], \"y^\", markersize=20)\n",
"plt.title(\"Activation function: sigmoid\", fontsize=14)\n",
"plt.grid(True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# FNN for MNIST"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## using tf.learn"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"from tensorflow.examples.tutorials.mnist import input_data\n",
"mnist = input_data.read_data_sets(\"/tmp/data/\")\n",
"X_train = mnist.train.images\n",
"X_test = mnist.test.images\n",
"y_train = mnist.train.labels.astype(\"int\")\n",
"y_test = mnist.test.labels.astype(\"int\")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"import tensorflow as tf\n",
"\n",
"feature_columns = tf.contrib.learn.infer_real_valued_columns_from_input(X_train)\n",
"dnn_clf = tf.contrib.learn.DNNClassifier(hidden_units=[300, 100], n_classes=10,\n",
" feature_columns=feature_columns)\n",
"dnn_clf.fit(x=X_train, y=y_train, batch_size=50, steps=40000)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"from sklearn.metrics import accuracy_score\n",
"\n",
"y_pred = dnn_clf.predict(X_test)\n",
"accuracy = accuracy_score(y_test, y_pred)\n",
"accuracy"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"from sklearn.metrics import log_loss\n",
"\n",
"y_pred_proba = dnn_clf.predict_proba(X_test)\n",
"log_loss(y_test, y_pred_proba)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"dnn_clf.evaluate(X_test, y_test)"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
},
"source": [
"## Using plain TensorFlow"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import tensorflow as tf\n",
"\n",
"def neuron_layer(X, n_neurons, name, activation=None):\n",
" with tf.name_scope(name):\n",
" n_inputs = int(X.get_shape()[1])\n",
" stddev = 1 / np.sqrt(n_inputs)\n",
" init = tf.truncated_normal((n_inputs, n_neurons), stddev=stddev)\n",
" W = tf.Variable(init, name=\"weights\")\n",
" b = tf.Variable(tf.zeros([n_neurons]), name=\"biases\")\n",
" Z = tf.matmul(X, W) + b\n",
" if activation==\"relu\":\n",
" return tf.nn.relu(Z)\n",
" else:\n",
" return Z"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"tf.reset_default_graph()\n",
"\n",
"n_inputs = 28*28 # MNIST\n",
"n_hidden1 = 300\n",
"n_hidden2 = 100\n",
"n_outputs = 10\n",
"learning_rate = 0.01\n",
"\n",
"X = tf.placeholder(tf.float32, shape=(None, n_inputs), name=\"X\")\n",
"y = tf.placeholder(tf.int64, shape=(None), name=\"y\")\n",
"\n",
"with tf.name_scope(\"dnn\"):\n",
" hidden1 = neuron_layer(X, n_hidden1, \"hidden1\", activation=\"relu\")\n",
" hidden2 = neuron_layer(hidden1, n_hidden2, \"hidden2\", activation=\"relu\")\n",
" logits = neuron_layer(hidden2, n_outputs, \"output\")\n",
"\n",
"with tf.name_scope(\"loss\"):\n",
" xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits, y)\n",
" loss = tf.reduce_mean(xentropy, name=\"loss\")\n",
"\n",
"with tf.name_scope(\"train\"):\n",
" optimizer = tf.train.GradientDescentOptimizer(learning_rate)\n",
" training_op = optimizer.minimize(loss)\n",
"\n",
"with tf.name_scope(\"eval\"):\n",
" correct = tf.nn.in_top_k(logits, y, 1)\n",
" accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))\n",
" \n",
"init = tf.initialize_all_variables()\n",
"saver = tf.train.Saver()"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"n_epochs = 20\n",
"batch_size = 50\n",
"\n",
"with tf.Session() as sess:\n",
" init.run()\n",
" for epoch in range(n_epochs):\n",
2016-10-06 14:09:17 +02:00
" for iteration in range(mnist.train.num_examples // batch_size):\n",
2016-09-27 23:31:21 +02:00
" X_batch, y_batch = mnist.train.next_batch(batch_size)\n",
" sess.run(training_op, feed_dict={X: X_batch, y: y_batch})\n",
" acc_train = accuracy.eval(feed_dict={X: X_batch, y: y_batch})\n",
" acc_test = accuracy.eval(feed_dict={X: mnist.test.images, y: mnist.test.labels})\n",
" print(epoch, \"Train accuracy:\", acc_train, \"Test accuracy:\", acc_test)\n",
"\n",
" save_path = saver.save(sess, \"my_model_final.ckpt\")"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"with tf.Session() as sess:\n",
" saver.restore(sess, \"my_model_final.ckpt\")\n",
" X_new_scaled = mnist.test.images[:20]\n",
" Z = logits.eval(feed_dict={X: X_new_scaled})\n",
" print(np.argmax(Z, axis=1))\n",
" print(mnist.test.labels[:20])"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from IPython.display import clear_output, Image, display, HTML\n",
"\n",
"def strip_consts(graph_def, max_const_size=32):\n",
" \"\"\"Strip large constant values from graph_def.\"\"\"\n",
" strip_def = tf.GraphDef()\n",
" for n0 in graph_def.node:\n",
" n = strip_def.node.add() \n",
" n.MergeFrom(n0)\n",
" if n.op == 'Const':\n",
" tensor = n.attr['value'].tensor\n",
" size = len(tensor.tensor_content)\n",
" if size > max_const_size:\n",
" tensor.tensor_content = b\"<stripped %d bytes>\"%size\n",
" return strip_def\n",
"\n",
"def show_graph(graph_def, max_const_size=32):\n",
" \"\"\"Visualize TensorFlow graph.\"\"\"\n",
" if hasattr(graph_def, 'as_graph_def'):\n",
" graph_def = graph_def.as_graph_def()\n",
" strip_def = strip_consts(graph_def, max_const_size=max_const_size)\n",
" code = \"\"\"\n",
" <script>\n",
" function load() {{\n",
" document.getElementById(\"{id}\").pbtxt = {data};\n",
" }}\n",
" </script>\n",
" <link rel=\"import\" href=\"https://tensorboard.appspot.com/tf-graph-basic.build.html\" onload=load()>\n",
" <div style=\"height:600px\">\n",
" <tf-graph-basic id=\"{id}\"></tf-graph-basic>\n",
" </div>\n",
" \"\"\".format(data=repr(str(strip_def)), id='graph'+str(np.random.rand()))\n",
"\n",
" iframe = \"\"\"\n",
" <iframe seamless style=\"width:1200px;height:620px;border:0\" srcdoc=\"{}\"></iframe>\n",
" \"\"\".format(code.replace('\"', '"'))\n",
" display(HTML(iframe))"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"show_graph(tf.get_default_graph())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Using `fully_connected` instead of `neuron_layer()`"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"tf.reset_default_graph()\n",
"\n",
"from tensorflow.contrib.layers import fully_connected\n",
"\n",
"n_inputs = 28*28 # MNIST\n",
"n_hidden1 = 300\n",
"n_hidden2 = 100\n",
"n_outputs = 10\n",
"learning_rate = 0.01\n",
"\n",
"X = tf.placeholder(tf.float32, shape=(None, n_inputs), name=\"X\")\n",
"y = tf.placeholder(tf.int64, shape=(None), name=\"y\")\n",
"\n",
"with tf.name_scope(\"dnn\"):\n",
" hidden1 = fully_connected(X, n_hidden1, scope=\"hidden1\")\n",
" hidden2 = fully_connected(hidden1, n_hidden2, scope=\"hidden2\")\n",
" logits = fully_connected(hidden2, n_outputs, activation_fn=None, scope=\"outputs\")\n",
"\n",
"with tf.name_scope(\"loss\"):\n",
" xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits, y)\n",
" loss = tf.reduce_mean(xentropy, name=\"loss\")\n",
"\n",
"with tf.name_scope(\"train\"):\n",
" optimizer = tf.train.GradientDescentOptimizer(learning_rate)\n",
" training_op = optimizer.minimize(loss)\n",
"\n",
"with tf.name_scope(\"eval\"):\n",
" correct = tf.nn.in_top_k(logits, y, 1)\n",
" accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))\n",
" \n",
"init = tf.initialize_all_variables()\n",
"saver = tf.train.Saver()"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"n_epochs = 20\n",
"n_batches = 50\n",
"\n",
"with tf.Session() as sess:\n",
" init.run()\n",
" for epoch in range(n_epochs):\n",
2016-10-06 14:09:17 +02:00
" for iteration in range(mnist.train.num_examples // batch_size):\n",
2016-09-27 23:31:21 +02:00
" X_batch, y_batch = mnist.train.next_batch(batch_size)\n",
" sess.run(training_op, feed_dict={X: X_batch, y: y_batch})\n",
" acc_train = accuracy.eval(feed_dict={X: X_batch, y: y_batch})\n",
" acc_test = accuracy.eval(feed_dict={X: mnist.test.images, y: mnist.test.labels})\n",
" print(epoch, \"Train accuracy:\", acc_train, \"Test accuracy:\", acc_test)\n",
"\n",
" save_path = saver.save(sess, \"my_model_final.ckpt\")"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"show_graph(tf.get_default_graph())"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
},
"source": [
"# Exercise solutions"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Coming soon**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": 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": "3.5.1"
},
"nav_menu": {
"height": "264px",
"width": "369px"
},
"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
}
