Merge branch 'master' of github.com:ageron/handson-ml
Aurélien Geron
commit
b17a6c8e63
File diff suppressed because it is too large
Load Diff
|
|
@ -1494,7 +1494,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"* Yikes, only 48% **Survived**. :( That's close to 50%, so accuracy will be a reasonable metric to evaluate our model.\n",
|
||||
"* Yikes, only 38% **Survived**. :( That's close enough to 40%, so accuracy will be a reasonable metric to evaluate our model.\n",
|
||||
"* The mean **Fare** was £32.20, which does not seem so expensive (but it was probably a lot of money back then).\n",
|
||||
"* The mean **Age** was less than 30 years old."
|
||||
]
|
||||
|
|
|
|||
|
|
@ -1017,7 +1017,8 @@
|
|||
" boundary_x2s = -x1s*(w[0]/w[1])-b/w[1]\n",
|
||||
" margin_x2s_1 = -x1s*(w[0]/w[1])-(b-1)/w[1]\n",
|
||||
" margin_x2s_2 = -x1s*(w[0]/w[1])-(b+1)/w[1]\n",
|
||||
" ax.plot_surface(x1s, x2, 0, color=\"b\", alpha=0.2, cstride=100, rstride=100)\n",
|
||||
" ax.plot_surface(x1s, x2, np.zeros_like(x1),\n",
|
||||
" color=\"b\", alpha=0.2, cstride=100, rstride=100)\n",
|
||||
" ax.plot(x1s, boundary_x2s, 0, \"k-\", linewidth=2, label=r\"$h=0$\")\n",
|
||||
" ax.plot(x1s, margin_x2s_1, 0, \"k--\", linewidth=2, label=r\"$h=\\pm 1$\")\n",
|
||||
" ax.plot(x1s, margin_x2s_2, 0, \"k--\", linewidth=2)\n",
|
||||
|
|
|
|||
|
|
@ -2,40 +2,28 @@
|
|||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Chapter 10 – Introduction to Artificial Neural Networks**"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"_This notebook contains all the sample code and solutions to the exercises in chapter 10._"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Setup"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"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:"
|
||||
]
|
||||
|
|
@ -43,11 +31,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# To support both python 2 and python 3\n",
|
||||
|
|
@ -85,10 +69,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Perceptrons"
|
||||
]
|
||||
|
|
@ -97,9 +78,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -120,11 +99,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"y_pred"
|
||||
|
|
@ -133,11 +108,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"a = -per_clf.coef_[0][0] / per_clf.coef_[0][1]\n",
|
||||
|
|
@ -173,10 +144,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Activation functions"
|
||||
]
|
||||
|
|
@ -185,9 +153,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -204,11 +170,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"z = np.linspace(-5, 5, 200)\n",
|
||||
|
|
@ -245,9 +207,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -264,11 +224,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"x1s = np.linspace(-0.2, 1.2, 100)\n",
|
||||
|
|
@ -297,20 +253,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# FNN for MNIST"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## using tf.learn"
|
||||
]
|
||||
|
|
@ -318,11 +268,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from tensorflow.examples.tutorials.mnist import input_data\n",
|
||||
|
|
@ -334,9 +280,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -349,11 +293,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import tensorflow as tf\n",
|
||||
|
|
@ -370,11 +310,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.metrics import accuracy_score\n",
|
||||
|
|
@ -386,11 +322,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.metrics import log_loss\n",
|
||||
|
|
@ -402,9 +334,7 @@
|
|||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"source": [
|
||||
"## Using plain TensorFlow"
|
||||
|
|
@ -413,11 +343,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import tensorflow as tf\n",
|
||||
|
|
@ -431,11 +357,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
|
|
@ -447,11 +369,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def neuron_layer(X, n_neurons, name, activation=None):\n",
|
||||
|
|
@ -471,11 +389,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.name_scope(\"dnn\"):\n",
|
||||
|
|
@ -489,11 +403,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.name_scope(\"loss\"):\n",
|
||||
|
|
@ -505,11 +415,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 19,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"learning_rate = 0.01\n",
|
||||
|
|
@ -522,11 +428,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 20,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.name_scope(\"eval\"):\n",
|
||||
|
|
@ -537,11 +439,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"init = tf.global_variables_initializer()\n",
|
||||
|
|
@ -551,11 +449,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_epochs = 40\n",
|
||||
|
|
@ -565,11 +459,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.Session() as sess:\n",
|
||||
|
|
@ -579,9 +469,9 @@
|
|||
" 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,\n",
|
||||
" y: mnist.test.labels})\n",
|
||||
" print(epoch, \"Train accuracy:\", acc_train, \"Test accuracy:\", acc_test)\n",
|
||||
" acc_val = accuracy.eval(feed_dict={X: mnist.validation.images,\n",
|
||||
" y: mnist.validation.labels})\n",
|
||||
" print(epoch, \"Train accuracy:\", acc_train, \"Val accuracy:\", acc_val)\n",
|
||||
"\n",
|
||||
" save_path = saver.save(sess, \"./my_model_final.ckpt\")"
|
||||
]
|
||||
|
|
@ -589,11 +479,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 24,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.Session() as sess:\n",
|
||||
|
|
@ -606,11 +492,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 25,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"Predicted classes:\", y_pred)\n",
|
||||
|
|
@ -621,9 +503,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 26,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -668,11 +548,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 27,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"show_graph(tf.get_default_graph())"
|
||||
|
|
@ -680,20 +556,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using `dense()` instead of `neuron_layer()`"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Note: the book uses `tensorflow.contrib.layers.fully_connected()` rather than `tf.layers.dense()` (which did not exist when this chapter was written). It is now preferable to use `tf.layers.dense()`, because anything in the contrib module may change or be deleted without notice. The `dense()` function is almost identical to the `fully_connected()` function, except for a few minor differences:\n",
|
||||
"* several parameters are renamed: `scope` becomes `name`, `activation_fn` becomes `activation` (and similarly the `_fn` suffix is removed from other parameters such as `normalizer_fn`), `weights_initializer` becomes `kernel_initializer`, etc.\n",
|
||||
|
|
@ -704,11 +574,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 28,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_inputs = 28*28 # MNIST\n",
|
||||
|
|
@ -721,9 +587,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -736,11 +600,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 30,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.name_scope(\"dnn\"):\n",
|
||||
|
|
@ -755,9 +615,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 31,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -770,9 +628,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 32,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -787,9 +643,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 33,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -802,9 +656,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 34,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -815,11 +667,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 35,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_epochs = 20\n",
|
||||
|
|
@ -841,11 +689,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 36,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"show_graph(tf.get_default_graph())"
|
||||
|
|
@ -854,9 +698,7 @@
|
|||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"source": [
|
||||
"# Exercise solutions"
|
||||
|
|
@ -864,10 +706,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 1. to 8."
|
||||
]
|
||||
|
|
@ -875,9 +714,7 @@
|
|||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"source": [
|
||||
"See appendix A."
|
||||
|
|
@ -885,30 +722,21 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 9."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"_Train a deep MLP on the MNIST dataset and see if you can get over 98% precision. Just like in the last exercise of chapter 9, try adding all the bells and whistles (i.e., save checkpoints, restore the last checkpoint in case of an interruption, add summaries, plot learning curves using TensorBoard, and so on)._"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"First let's create the deep net. It's exactly the same as earlier, with just one addition: we add a `tf.summary.scalar()` to track the loss and the accuracy during training, so we can view nice learning curves using TensorBoard."
|
||||
]
|
||||
|
|
@ -916,11 +744,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 37,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_inputs = 28*28 # MNIST\n",
|
||||
|
|
@ -933,9 +757,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 38,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -948,11 +770,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 39,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.name_scope(\"dnn\"):\n",
|
||||
|
|
@ -967,9 +785,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 40,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -983,9 +799,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 41,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -1000,9 +814,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 42,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -1016,9 +828,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 43,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -1028,10 +838,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now we need to define the directory to write the TensorBoard logs to:"
|
||||
]
|
||||
|
|
@ -1040,9 +847,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 44,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -1061,9 +866,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 45,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -1072,10 +875,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now we can create the `FileWriter` that we will use to write the TensorBoard logs:"
|
||||
]
|
||||
|
|
@ -1084,9 +884,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 46,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -1095,10 +893,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Hey! Why don't we implement early stopping? For this, we are going to need a validation set. Luckily, the dataset returned by TensorFlow's `input_data()` function (see above) is already split into a training set (60,000 instances, already shuffled for us), a validation set (5,000 instances) and a test set (5,000 instances). So we can easily define `X_valid` and `y_valid`:"
|
||||
]
|
||||
|
|
@ -1106,11 +901,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 47,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_valid = mnist.validation.images\n",
|
||||
|
|
@ -1121,9 +912,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 48,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -1133,11 +922,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 49,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_epochs = 10001\n",
|
||||
|
|
@ -1190,11 +975,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 50,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"os.remove(checkpoint_epoch_path)"
|
||||
|
|
@ -1203,11 +984,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 51,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.Session() as sess:\n",
|
||||
|
|
@ -1218,11 +995,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 52,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"accuracy_val"
|
||||
|
|
@ -1232,9 +1005,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
|
|
@ -1256,7 +1027,7 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.5.3"
|
||||
"version": "3.6.2"
|
||||
},
|
||||
"nav_menu": {
|
||||
"height": "264px",
|
||||
|
|
@ -1273,5 +1044,5 @@
|
|||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 0
|
||||
"nbformat_minor": 1
|
||||
}
|
||||
|
|
|
|||
|
|
@ -3312,7 +3312,14 @@
|
|||
"rnd_search = RandomizedSearchCV(DNNClassifier(random_state=42), param_distribs, n_iter=50,\n",
|
||||
" fit_params={\"X_valid\": X_valid1, \"y_valid\": y_valid1, \"n_epochs\": 1000},\n",
|
||||
" random_state=42, verbose=2)\n",
|
||||
"rnd_search.fit(X_train1, y_train1)"
|
||||
"rnd_search.fit(X_train1, y_train1)\n",
|
||||
"\n",
|
||||
"# fit_params as a constructor argument was deprecated in Scikit-Learn version 0.19 and will\n",
|
||||
"# be removed in version 0.21. Pass fit parameters to the fit() method instead:\n",
|
||||
"# rnd_search = RandomizedSearchCV(DNNClassifier(random_state=42), param_distribs, n_iter=50,\n",
|
||||
"# random_state=42, verbose=2)\n",
|
||||
"# fit_params={\"X_valid\": X_valid1, \"y_valid\": y_valid1, \"n_epochs\": 1000}\n",
|
||||
"# rnd_search.fit(X_train1, y_train1, **fit_params)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -4934,7 +4941,7 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.5.3"
|
||||
"version": "3.6.2"
|
||||
},
|
||||
"nav_menu": {
|
||||
"height": "360px",
|
||||
|
|
|
|||
|
|
@ -144,7 +144,6 @@
|
|||
"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",
|
||||
|
|
@ -501,6 +500,17 @@
|
|||
" saver = tf.train.Saver()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"source": [
|
||||
"Note: if you are using Python 3.6 on OSX, you need to run the following command on terminal to install the certifi package of certificates because Python 3.6 on OSX has no certificates to validate SSL connections (see this [StackOverflow question](https://stackoverflow.com/questions/27835619/urllib-and-ssl-certificate-verify-failed-error)):\n",
|
||||
"\n",
|
||||
" $ /Applications/Python\\ 3.6/Install\\ Certificates.command"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
|
|
@ -1949,7 +1959,7 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.5.2"
|
||||
"version": "3.6.2"
|
||||
},
|
||||
"nav_menu": {},
|
||||
"toc": {
|
||||
|
|
|
|||
|
|
@ -31,9 +31,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# To support both python 2 and python 3\n",
|
||||
|
|
@ -79,9 +77,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import tensorflow as tf"
|
||||
|
|
@ -104,9 +100,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
|
|
@ -130,9 +124,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
|
|
@ -173,9 +165,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_inputs = 3\n",
|
||||
|
|
@ -185,9 +175,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
|
|
@ -204,9 +192,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"init = tf.global_variables_initializer()"
|
||||
|
|
@ -215,9 +201,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X0_batch = np.array([[0, 1, 2], [3, 4, 5], [6, 7, 8], [9, 0, 1]])\n",
|
||||
|
|
@ -249,9 +233,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from IPython.display import clear_output, Image, display, HTML\n",
|
||||
|
|
@ -311,9 +293,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_steps = 2\n",
|
||||
|
|
@ -324,9 +304,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
|
|
@ -343,9 +321,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"init = tf.global_variables_initializer()"
|
||||
|
|
@ -354,9 +330,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_batch = np.array([\n",
|
||||
|
|
@ -400,9 +374,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_steps = 2\n",
|
||||
|
|
@ -413,9 +385,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
|
|
@ -429,9 +399,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"init = tf.global_variables_initializer()"
|
||||
|
|
@ -440,9 +408,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 24,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_batch = np.array([\n",
|
||||
|
|
@ -485,9 +451,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 27,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_steps = 2\n",
|
||||
|
|
@ -503,9 +467,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 28,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"seq_length = tf.placeholder(tf.int32, [None])\n",
|
||||
|
|
@ -516,9 +478,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"init = tf.global_variables_initializer()"
|
||||
|
|
@ -527,9 +487,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 30,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_batch = np.array([\n",
|
||||
|
|
@ -545,9 +503,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 31,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.Session() as sess:\n",
|
||||
|
|
@ -593,9 +549,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 34,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
|
|
@ -668,9 +622,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 37,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
|
|
@ -688,9 +640,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 38,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_neurons = 100\n",
|
||||
|
|
@ -706,9 +656,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 39,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"states_concat = tf.concat(axis=1, values=states)\n",
|
||||
|
|
@ -754,9 +702,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 41,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"t_min, t_max = 0, 30\n",
|
||||
|
|
@ -808,9 +754,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 43,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_batch, y_batch = next_batch(1, n_steps)"
|
||||
|
|
@ -842,9 +786,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 45,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
|
|
@ -871,9 +813,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 46,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
|
|
@ -890,9 +830,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 47,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"cell = tf.contrib.rnn.OutputProjectionWrapper(\n",
|
||||
|
|
@ -903,9 +841,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 48,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"outputs, states = tf.nn.dynamic_rnn(cell, X, dtype=tf.float32)"
|
||||
|
|
@ -914,9 +850,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 49,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"learning_rate = 0.001\n",
|
||||
|
|
@ -931,9 +865,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 50,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"saver = tf.train.Saver()"
|
||||
|
|
@ -1009,9 +941,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 55,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
|
|
@ -1027,9 +957,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 56,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"cell = tf.contrib.rnn.BasicRNNCell(num_units=n_neurons, activation=tf.nn.relu)\n",
|
||||
|
|
@ -1039,9 +967,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 57,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_outputs = 1\n",
|
||||
|
|
@ -1051,9 +977,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 58,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"stacked_rnn_outputs = tf.reshape(rnn_outputs, [-1, n_neurons])\n",
|
||||
|
|
@ -1064,9 +988,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 59,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loss = tf.reduce_mean(tf.square(outputs - y))\n",
|
||||
|
|
@ -1216,9 +1138,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 66,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
|
|
@ -1232,9 +1152,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 67,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_neurons = 100\n",
|
||||
|
|
@ -1249,9 +1167,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 68,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"init = tf.global_variables_initializer()"
|
||||
|
|
@ -1260,9 +1176,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 69,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_batch = np.random.rand(2, n_steps, n_inputs)"
|
||||
|
|
@ -1271,9 +1185,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 70,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.Session() as sess:\n",
|
||||
|
|
@ -1307,9 +1219,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 72,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.device(\"/gpu:0\"): # BAD! This is ignored.\n",
|
||||
|
|
@ -1329,9 +1239,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 73,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import tensorflow as tf\n",
|
||||
|
|
@ -1357,9 +1265,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 74,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
|
|
@ -1374,9 +1280,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 75,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"devices = [\"/cpu:0\", \"/cpu:0\", \"/cpu:0\"] # replace with [\"/gpu:0\", \"/gpu:1\", \"/gpu:2\"] if you have 3 GPUs\n",
|
||||
|
|
@ -1386,12 +1290,17 @@
|
|||
"outputs, states = tf.nn.dynamic_rnn(multi_layer_cell, X, dtype=tf.float32)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Alternatively, since TensorFlow 1.1, you can use the `tf.contrib.rnn.DeviceWrapper` class (alias `tf.nn.rnn_cell.DeviceWrapper` since TF 1.2)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 76,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"init = tf.global_variables_initializer()"
|
||||
|
|
@ -1420,9 +1329,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 78,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
|
|
@ -1431,22 +1338,33 @@
|
|||
"n_neurons = 100\n",
|
||||
"n_layers = 3\n",
|
||||
"n_steps = 20\n",
|
||||
"n_outputs = 1\n",
|
||||
"\n",
|
||||
"X = tf.placeholder(tf.float32, [None, n_steps, n_inputs])\n",
|
||||
"y = tf.placeholder(tf.float32, [None, n_steps, n_outputs])"
|
||||
"n_outputs = 1"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 79,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"keep_prob = 0.5\n",
|
||||
"\n",
|
||||
"X = tf.placeholder(tf.float32, [None, n_steps, n_inputs])\n",
|
||||
"y = tf.placeholder(tf.float32, [None, n_steps, n_outputs])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Note: the `input_keep_prob` parameter can be a placeholder, making it possible to set it to any value you want during training, and to 1.0 during testing (effectively turning dropout off). This is a much more elegant solution than what was recommended in earlier versions of the book (i.e., writing your own wrapper class or having a separate model for training and testing). Thanks to Shen Cheng for bringing this to my attention."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 80,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"keep_prob = tf.placeholder_with_default(1.0, shape=())\n",
|
||||
"cells = [tf.contrib.rnn.BasicRNNCell(num_units=n_neurons)\n",
|
||||
" for layer in range(n_layers)]\n",
|
||||
"cells_drop = [tf.contrib.rnn.DropoutWrapper(cell, input_keep_prob=keep_prob)\n",
|
||||
|
|
@ -1457,10 +1375,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 80,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 81,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"learning_rate = 0.01\n",
|
||||
|
|
@ -1477,78 +1393,29 @@
|
|||
"saver = tf.train.Saver()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Unfortunately, this code is only usable for training, because the `DropoutWrapper` class has no `training` parameter, so it always applies dropout, even when the model is not being trained, so we must first train the model, then create a different model for testing, without the `DropoutWrapper`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 81,
|
||||
"execution_count": 82,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_iterations = 1000\n",
|
||||
"n_iterations = 1500\n",
|
||||
"batch_size = 50\n",
|
||||
"train_keep_prob = 0.5\n",
|
||||
"\n",
|
||||
"with tf.Session() as sess:\n",
|
||||
" init.run()\n",
|
||||
" for iteration in range(n_iterations):\n",
|
||||
" X_batch, y_batch = next_batch(batch_size, n_steps)\n",
|
||||
" _, mse = sess.run([training_op, loss], feed_dict={X: X_batch, y: y_batch})\n",
|
||||
" if iteration % 100 == 0:\n",
|
||||
" print(iteration, \"Training MSE:\", mse)\n",
|
||||
" _, mse = sess.run([training_op, loss],\n",
|
||||
" feed_dict={X: X_batch, y: y_batch,\n",
|
||||
" keep_prob: train_keep_prob})\n",
|
||||
" if iteration % 100 == 0: # not shown in the book\n",
|
||||
" print(iteration, \"Training MSE:\", mse) # not shown\n",
|
||||
" \n",
|
||||
" saver.save(sess, \"./my_dropout_time_series_model\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now that the model is trained, we need to create the model again, but without the `DropoutWrapper` for testing:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 82,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
"\n",
|
||||
"n_inputs = 1\n",
|
||||
"n_neurons = 100\n",
|
||||
"n_layers = 3\n",
|
||||
"n_steps = 20\n",
|
||||
"n_outputs = 1\n",
|
||||
"\n",
|
||||
"X = tf.placeholder(tf.float32, [None, n_steps, n_inputs])\n",
|
||||
"y = tf.placeholder(tf.float32, [None, n_steps, n_outputs])\n",
|
||||
"\n",
|
||||
"keep_prob = 0.5\n",
|
||||
"\n",
|
||||
"cells = [tf.contrib.rnn.BasicRNNCell(num_units=n_neurons)\n",
|
||||
" for layer in range(n_layers)]\n",
|
||||
"multi_layer_cell = tf.contrib.rnn.MultiRNNCell(cells)\n",
|
||||
"rnn_outputs, states = tf.nn.dynamic_rnn(multi_layer_cell, X, dtype=tf.float32)\n",
|
||||
"\n",
|
||||
"learning_rate = 0.01\n",
|
||||
"\n",
|
||||
"stacked_rnn_outputs = tf.reshape(rnn_outputs, [-1, n_neurons])\n",
|
||||
"stacked_outputs = tf.layers.dense(stacked_rnn_outputs, n_outputs)\n",
|
||||
"outputs = tf.reshape(stacked_outputs, [-1, n_steps, n_outputs])\n",
|
||||
"\n",
|
||||
"loss = tf.reduce_mean(tf.square(outputs - y))\n",
|
||||
"\n",
|
||||
"init = tf.global_variables_initializer()\n",
|
||||
"saver = tf.train.Saver()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 83,
|
||||
|
|
@ -1559,8 +1426,15 @@
|
|||
" saver.restore(sess, \"./my_dropout_time_series_model\")\n",
|
||||
"\n",
|
||||
" X_new = time_series(np.array(t_instance[:-1].reshape(-1, n_steps, n_inputs)))\n",
|
||||
" y_pred = sess.run(outputs, feed_dict={X: X_new})\n",
|
||||
"\n",
|
||||
" y_pred = sess.run(outputs, feed_dict={X: X_new})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 84,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"plt.title(\"Testing the model\", fontsize=14)\n",
|
||||
"plt.plot(t_instance[:-1], time_series(t_instance[:-1]), \"bo\", markersize=10, label=\"instance\")\n",
|
||||
"plt.plot(t_instance[1:], time_series(t_instance[1:]), \"w*\", markersize=10, label=\"target\")\n",
|
||||
|
|
@ -1578,59 +1452,6 @@
|
|||
"Oops, it seems that Dropout does not help at all in this particular case. :/"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Another option is to write a script with a command line argument to specify whether you want to train the mode or use it for making predictions:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 84,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
"\n",
|
||||
"import sys\n",
|
||||
"training = True # in a script, this would be (sys.argv[-1] == \"train\") instead\n",
|
||||
"\n",
|
||||
"X = tf.placeholder(tf.float32, [None, n_steps, n_inputs])\n",
|
||||
"y = tf.placeholder(tf.float32, [None, n_steps, n_outputs])\n",
|
||||
"\n",
|
||||
"cells = [tf.contrib.rnn.BasicRNNCell(num_units=n_neurons)\n",
|
||||
" for layer in range(n_layers)]\n",
|
||||
"if training:\n",
|
||||
" cells = [tf.contrib.rnn.DropoutWrapper(cell, input_keep_prob=keep_prob)\n",
|
||||
" for cell in cells]\n",
|
||||
"multi_layer_cell = tf.contrib.rnn.MultiRNNCell(cells)\n",
|
||||
"rnn_outputs, states = tf.nn.dynamic_rnn(multi_layer_cell, X, dtype=tf.float32)\n",
|
||||
"\n",
|
||||
"stacked_rnn_outputs = tf.reshape(rnn_outputs, [-1, n_neurons]) # not shown in the book\n",
|
||||
"stacked_outputs = tf.layers.dense(stacked_rnn_outputs, n_outputs) # not shown\n",
|
||||
"outputs = tf.reshape(stacked_outputs, [-1, n_steps, n_outputs]) # not shown\n",
|
||||
"loss = tf.reduce_mean(tf.square(outputs - y)) # not shown\n",
|
||||
"optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate) # not shown\n",
|
||||
"training_op = optimizer.minimize(loss) # not shown\n",
|
||||
"init = tf.global_variables_initializer() # not shown\n",
|
||||
"saver = tf.train.Saver() # not shown\n",
|
||||
"\n",
|
||||
"with tf.Session() as sess:\n",
|
||||
" if training:\n",
|
||||
" init.run()\n",
|
||||
" for iteration in range(n_iterations):\n",
|
||||
" X_batch, y_batch = next_batch(batch_size, n_steps) # not shown\n",
|
||||
" _, mse = sess.run([training_op, loss], feed_dict={X: X_batch, y: y_batch}) # not shown\n",
|
||||
" if iteration % 100 == 0: # not shown\n",
|
||||
" print(iteration, \"Training MSE:\", mse) # not shown\n",
|
||||
" save_path = saver.save(sess, \"/tmp/my_model.ckpt\")\n",
|
||||
" else:\n",
|
||||
" saver.restore(sess, \"/tmp/my_model.ckpt\")\n",
|
||||
" X_new = time_series(np.array(t_instance[:-1].reshape(-1, n_steps, n_inputs))) # not shown\n",
|
||||
" y_pred = sess.run(outputs, feed_dict={X: X_new}) # not shown"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
|
|
@ -2706,7 +2527,7 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.5.2"
|
||||
"version": "3.6.2"
|
||||
},
|
||||
"nav_menu": {},
|
||||
"toc": {
|
||||
|
|
|
|||
|
|
@ -131,6 +131,8 @@
|
|||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy.random as rnd\n",
|
||||
"\n",
|
||||
"rnd.seed(4)\n",
|
||||
"m = 200\n",
|
||||
"w1, w2 = 0.1, 0.3\n",
|
||||
|
|
|
|||
|
|
@ -31,9 +31,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# To support both python 2 and python 3\n",
|
||||
|
|
@ -95,9 +93,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import gym"
|
||||
|
|
@ -129,9 +125,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"obs = env.reset()"
|
||||
|
|
@ -163,9 +157,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"img = env.render(mode=\"rgb_array\")"
|
||||
|
|
@ -226,9 +218,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def plot_environment(env, figsize=(5,4)):\n",
|
||||
|
|
@ -273,9 +263,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"env.reset()\n",
|
||||
|
|
@ -311,9 +299,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"obs, reward, done, info = env.step(0)"
|
||||
|
|
@ -393,9 +379,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"frames = []\n",
|
||||
|
|
@ -424,9 +408,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 19,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def update_scene(num, frames, patch):\n",
|
||||
|
|
@ -461,9 +443,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"env.close()"
|
||||
|
|
@ -502,9 +482,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"obs = env.reset()"
|
||||
|
|
@ -547,9 +525,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 25,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from PIL import Image, ImageDraw\n",
|
||||
|
|
@ -633,9 +609,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 28,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"obs = env.reset()\n",
|
||||
|
|
@ -677,9 +651,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 31,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"obs = env.reset()\n",
|
||||
|
|
@ -722,9 +694,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 33,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"frames = []\n",
|
||||
|
|
@ -795,9 +765,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 35,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import tensorflow as tf\n",
|
||||
|
|
@ -846,9 +814,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 36,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_max_steps = 1000\n",
|
||||
|
|
@ -895,9 +861,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 38,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import tensorflow as tf\n",
|
||||
|
|
@ -965,9 +929,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 40,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def render_policy_net(model_path, action, X, n_max_steps = 1000):\n",
|
||||
|
|
@ -1024,9 +986,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 42,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import tensorflow as tf\n",
|
||||
|
|
@ -1069,9 +1029,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 43,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def discount_rewards(rewards, discount_rate):\n",
|
||||
|
|
@ -1157,9 +1115,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 47,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"env.close()"
|
||||
|
|
@ -1309,9 +1265,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 51,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_states = 3\n",
|
||||
|
|
@ -1336,9 +1290,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 52,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def optimal_policy(state):\n",
|
||||
|
|
@ -1439,23 +1391,28 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 57,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"mspacman_color = np.array([210, 164, 74]).mean()\n",
|
||||
"mspacman_color = 210 + 164 + 74\n",
|
||||
"\n",
|
||||
"def preprocess_observation(obs):\n",
|
||||
" img = obs[1:176:2, ::2] # crop and downsize\n",
|
||||
" img = img.mean(axis=2) # to greyscale\n",
|
||||
" img = img.sum(axis=2) # to greyscale\n",
|
||||
" img[img==mspacman_color] = 0 # Improve contrast\n",
|
||||
" img = (img - 128) / 128 - 1 # normalize from -1. to 1.\n",
|
||||
" img = (img // 3 - 128).astype(np.int8) # normalize from -128 to 127\n",
|
||||
" return img.reshape(88, 80, 1)\n",
|
||||
"\n",
|
||||
"img = preprocess_observation(obs)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Note: the `preprocess_observation()` function is slightly different from the one in the book: instead of representing pixels as 64-bit floats from -1.0 to 1.0, it represents them as signed bytes (from -128 to 127). The benefit is that the replay memory will take up roughly 8 times less RAM (about 6.5 GB instead of 52 GB). The reduced precision has no visible impact on training."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 58,
|
||||
|
|
@ -1498,9 +1455,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 59,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
|
|
@ -1520,7 +1475,7 @@
|
|||
"initializer = tf.contrib.layers.variance_scaling_initializer()\n",
|
||||
"\n",
|
||||
"def q_network(X_state, name):\n",
|
||||
" prev_layer = X_state\n",
|
||||
" prev_layer = X_state / 128.0 # scale pixel intensities to the [-1.0, 1.0] range.\n",
|
||||
" with tf.variable_scope(name) as scope:\n",
|
||||
" for n_maps, kernel_size, strides, padding, activation in zip(\n",
|
||||
" conv_n_maps, conv_kernel_sizes, conv_strides,\n",
|
||||
|
|
@ -1545,9 +1500,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 60,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_state = tf.placeholder(tf.float32, shape=[None, input_height, input_width,\n",
|
||||
|
|
@ -1572,9 +1525,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 62,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"learning_rate = 0.001\n",
|
||||
|
|
@ -1608,9 +1559,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 63,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from collections import deque\n",
|
||||
|
|
@ -1632,9 +1581,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 64,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"eps_min = 0.1\n",
|
||||
|
|
@ -1678,9 +1625,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 66,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loss_val = np.infty\n",
|
||||
|
|
@ -1970,7 +1915,7 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.5.2"
|
||||
"version": "3.6.3"
|
||||
},
|
||||
"nav_menu": {},
|
||||
"toc": {
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue