arthur/handson-ml3
1
0
Fork 0
mirror of https://github.com/ArthurDanjou/handson-ml3.git synced 2026-01-27 10:10:27 +01:00
Code Issues Packages Projects Releases Wiki Activity

Upgrade notebooks to TensorFlow 1.0.0

Browse Source
This commit is contained in:
Aurélien Geron
2017-02-17 11:51:26 +01:00
parent 146fde1127
commit d8176ec2cb
43 changed files with 3615 additions and 7542 deletions
Download Patch File Download Diff File Expand all files Collapse all files

251
11_deep_learning.ipynb
View File

@@ -2,28 +2,40 @@
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"**Chapter 11 – Deep Learning**"
]
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"_This notebook contains all the sample code and solutions to the exercices in chapter 11._"
]
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"# Setup"
]
},
{
"cell_type": "markdown",
"metadata": {},
"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:"
]
@@ -32,7 +44,9 @@
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -69,7 +83,10 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"# Activation functions"
]
@@ -78,7 +95,9 @@
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -90,7 +109,9 @@
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -117,7 +138,9 @@
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -129,7 +152,9 @@
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -150,7 +175,9 @@
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -162,7 +189,9 @@
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -183,7 +212,9 @@
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -195,7 +226,9 @@
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -207,7 +240,9 @@
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -218,7 +253,9 @@
"cell_type": "code",
"execution_count": 11,
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -264,7 +301,9 @@
"cell_type": "code",
"execution_count": 12,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -287,7 +326,7 @@
" 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",
" xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y, logits=logits)\n",
" loss = tf.reduce_mean(xentropy, name=\"loss\")\n",
"\n",
"with tf.name_scope(\"train\"):\n",
@@ -298,7 +337,7 @@
" 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",
"init = tf.global_variables_initializer()\n",
"saver = tf.train.Saver()"
]
},
@@ -306,7 +345,9 @@
"cell_type": "code",
"execution_count": 13,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -328,7 +369,10 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"# Batch Normalization"
]
@@ -337,7 +381,9 @@
"cell_type": "code",
"execution_count": 14,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -377,7 +423,7 @@
" 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",
" xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y, logits=logits)\n",
" loss = tf.reduce_mean(xentropy, name=\"loss\")\n",
"\n",
"with tf.name_scope(\"train\"):\n",
@@ -388,7 +434,7 @@
" 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",
"init = tf.global_variables_initializer()\n",
"saver = tf.train.Saver()"
]
},
@@ -396,7 +442,9 @@
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -420,7 +468,9 @@
"cell_type": "code",
"execution_count": 16,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -451,7 +501,7 @@
" 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",
" xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y, logits=logits)\n",
" reg_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)\n",
" base_loss = tf.reduce_mean(xentropy, name=\"base_loss\")\n",
" loss = tf.add(base_loss, reg_losses, name=\"loss\")\n",
@@ -464,7 +514,7 @@
" 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",
"init = tf.global_variables_initializer()\n",
"saver = tf.train.Saver()"
]
},
@@ -472,7 +522,9 @@
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -496,18 +548,22 @@
"cell_type": "code",
"execution_count": 18,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
"[v.name for v in tf.all_variables()]"
"[v.name for v in tf.global_variables()]"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -521,7 +577,9 @@
"cell_type": "code",
"execution_count": 20,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -545,7 +603,9 @@
"cell_type": "code",
"execution_count": 21,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -556,7 +616,9 @@
"cell_type": "code",
"execution_count": 22,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -567,7 +629,9 @@
"cell_type": "code",
"execution_count": 23,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -578,7 +642,9 @@
"cell_type": "code",
"execution_count": 24,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -589,7 +655,9 @@
"cell_type": "code",
"execution_count": 25,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -600,7 +668,9 @@
"cell_type": "code",
"execution_count": 26,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -611,7 +681,9 @@
"cell_type": "code",
"execution_count": 27,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -639,7 +711,7 @@
"clip_all_weights = tf.get_collection(\"max_norm\")\n",
" \n",
"with tf.name_scope(\"loss\"):\n",
" xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits, y)\n",
" xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y, logits=logits)\n",
" loss = tf.reduce_mean(xentropy, name=\"loss\")\n",
"\n",
"with tf.name_scope(\"train\"):\n",
@@ -654,7 +726,7 @@
" 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",
"init = tf.global_variables_initializer()\n",
"saver = tf.train.Saver()"
]
},
@@ -662,7 +734,9 @@
"cell_type": "code",
"execution_count": 28,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -686,7 +760,9 @@
"cell_type": "code",
"execution_count": 29,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -697,7 +773,9 @@
"cell_type": "code",
"execution_count": 30,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -732,7 +810,7 @@
" logits = fully_connected(hidden2_drop, 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",
" xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y, logits=logits)\n",
" loss = tf.reduce_mean(xentropy, name=\"loss\")\n",
"\n",
"with tf.name_scope(\"train\"):\n",
@@ -743,7 +821,7 @@
" 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",
"init = tf.global_variables_initializer()\n",
"saver = tf.train.Saver()"
]
},
@@ -751,7 +829,9 @@
"cell_type": "code",
"execution_count": 31,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -775,7 +855,9 @@
"cell_type": "code",
"execution_count": 32,
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -787,7 +869,9 @@
"cell_type": "code",
"execution_count": 33,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -798,11 +882,13 @@
"cell_type": "code",
"execution_count": 34,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
"for i in tf.all_variables():\n",
"for i in tf.global_variables():\n",
" print(i.name)"
]
},
@@ -810,7 +896,9 @@
"cell_type": "code",
"execution_count": 35,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -822,7 +910,9 @@
"cell_type": "code",
"execution_count": 36,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -830,48 +920,12 @@
" print(i.name)"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"X_train = mnist.train.images\n",
"y_train = mnist.train.labels.astype(\"int\")\n",
"X_val = mnist.test.images[8000:]\n",
"y_val = mnist.test.labels[8000:].astype(\"int\")\n",
"\n",
"feature_columns = tf.contrib.learn.infer_real_valued_columns_from_input(X_train)\n",
"dnn_clf = tf.contrib.learn.DNNClassifier(\n",
" feature_columns = feature_columns,\n",
" hidden_units=[300, 100],\n",
" n_classes=10,\n",
" model_dir=\"/tmp/my_model\",\n",
" config=tf.contrib.learn.RunConfig(save_checkpoints_secs=60)\n",
" )\n",
"\n",
"validation_monitor = tf.contrib.learn.monitors.ValidationMonitor(\n",
" X_val,\n",
" y_val,\n",
" every_n_steps=50,\n",
" early_stopping_metric=\"loss\",\n",
" early_stopping_metric_minimize=True,\n",
" early_stopping_rounds=2000\n",
" )\n",
"\n",
"dnn_clf.fit(x=X_train,\n",
" y=y_train,\n",
" steps=40000,\n",
" monitors=[validation_monitor]\n",
" )\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"source": [
"# Exercise solutions"
@@ -879,7 +933,10 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"**Coming soon**"
]
@@ -888,7 +945,9 @@
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": []
@@ -910,7 +969,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.2"
"version": "3.5.2+"
},
"nav_menu": {
"height": "360px",