schuetoliver
/
handson-ml
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Use np.random.set_seed(42) and tf.set_random_seed(42) to make notebook's output constant

main
Aurélien Geron 2017-06-08 15:44:00 +02:00
parent 91acc2e1fd
commit 48718eff9d
1 changed files with 69 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

110
16_reinforcement_learning.ipynb
View File

@ -55,12 +55,14 @@
"\n",
"# Common imports\n",
"import numpy as np\n",
"import numpy.random as rnd\n",
"import os\n",
"import sys\n",
"\n",
"# to make this notebook's output stable across runs\n",
"rnd.seed(42)\n",
"def reset_graph(seed=42):\n",
" tf.reset_default_graph()\n",
" tf.set_random_seed(seed)\n",
" np.random.seed(seed)\n",
"\n",
"# To plot pretty figures and animations\n",
"%matplotlib nbagg\n",
@ -83,6 +85,13 @@
" plt.savefig(path, format='png', dpi=300)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Note: there may be minor differences between the output of this notebook and the examples shown in the book. You can safely ignore these differences. They are mainly due to the fact that most of the environments provided by OpenAI gym have some randomness."
]
},
{
"cell_type": "markdown",
"metadata": {
@ -840,6 +849,19 @@
"save_fig(\"cart_pole_plot\")"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
"img.shape"
]
},
{
"cell_type": "markdown",
"metadata": {
@ -852,7 +874,7 @@
},
{
"cell_type": "code",
"execution_count": 30,
"execution_count": 31,
"metadata": {
"collapsed": false,
"deletable": true,
@ -869,7 +891,7 @@
},
{
"cell_type": "code",
"execution_count": 31,
"execution_count": 32,
"metadata": {
"collapsed": false,
"deletable": true,
@ -912,7 +934,7 @@
},
{
"cell_type": "code",
"execution_count": 32,
"execution_count": 33,
"metadata": {
"collapsed": false,
"deletable": true,
@ -944,7 +966,7 @@
},
{
"cell_type": "code",
"execution_count": 33,
"execution_count": 34,
"metadata": {
"collapsed": false,
"deletable": true,
@ -988,7 +1010,10 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"Note: instead of using the `fully_connected()` function from the `tensorflow.contrib.layers` module (as in the book), we now use the `dense()` function from the `tf.layers` module, which did not exist when this chapter was written. This is preferable because anything in contrib may change or be deleted without notice, while `tf.layers` is part of the official API. As you will see, the code is mostly the same.\n",
"\n",
@ -1000,7 +1025,7 @@
},
{
"cell_type": "code",
"execution_count": 34,
"execution_count": 35,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1062,7 +1087,7 @@
},
{
"cell_type": "code",
"execution_count": 35,
"execution_count": 36,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1099,7 +1124,7 @@
},
{
"cell_type": "code",
"execution_count": 36,
"execution_count": 37,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1123,7 +1148,7 @@
},
{
"cell_type": "code",
"execution_count": 37,
"execution_count": 38,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1133,7 +1158,7 @@
"source": [
"import tensorflow as tf\n",
"\n",
"tf.reset_default_graph()\n",
"reset_graph()\n",
"\n",
"n_inputs = 4\n",
"n_hidden = 4\n",
@ -1172,7 +1197,7 @@
},
{
"cell_type": "code",
"execution_count": 38,
"execution_count": 39,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1202,7 +1227,7 @@
},
{
"cell_type": "code",
"execution_count": 39,
"execution_count": 40,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1229,7 +1254,7 @@
},
{
"cell_type": "code",
"execution_count": 40,
"execution_count": 41,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1276,7 +1301,7 @@
},
{
"cell_type": "code",
"execution_count": 41,
"execution_count": 42,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1286,7 +1311,7 @@
"source": [
"import tensorflow as tf\n",
"\n",
"tf.reset_default_graph()\n",
"reset_graph()\n",
"\n",
"n_inputs = 4\n",
"n_hidden = 4\n",
@ -1323,7 +1348,7 @@
},
{
"cell_type": "code",
"execution_count": 42,
"execution_count": 43,
"metadata": {
"collapsed": true,
"deletable": true,
@ -1349,7 +1374,7 @@
},
{
"cell_type": "code",
"execution_count": 43,
"execution_count": 44,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1362,7 +1387,7 @@
},
{
"cell_type": "code",
"execution_count": 44,
"execution_count": 45,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1375,7 +1400,7 @@
},
{
"cell_type": "code",
"execution_count": 45,
"execution_count": 46,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1425,7 +1450,7 @@
},
{
"cell_type": "code",
"execution_count": 46,
"execution_count": 47,
"metadata": {
"collapsed": true,
"deletable": true,
@ -1438,7 +1463,7 @@
},
{
"cell_type": "code",
"execution_count": 47,
"execution_count": 48,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1463,7 +1488,7 @@
},
{
"cell_type": "code",
"execution_count": 48,
"execution_count": 49,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1508,7 +1533,7 @@
},
{
"cell_type": "code",
"execution_count": 49,
"execution_count": 50,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1603,7 +1628,7 @@
},
{
"cell_type": "code",
"execution_count": 50,
"execution_count": 51,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1632,7 +1657,7 @@
},
{
"cell_type": "code",
"execution_count": 51,
"execution_count": 52,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1646,7 +1671,7 @@
},
{
"cell_type": "code",
"execution_count": 52,
"execution_count": 53,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1659,7 +1684,7 @@
},
{
"cell_type": "code",
"execution_count": 53,
"execution_count": 54,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1686,7 +1711,7 @@
},
{
"cell_type": "code",
"execution_count": 54,
"execution_count": 55,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1700,7 +1725,7 @@
},
{
"cell_type": "code",
"execution_count": 55,
"execution_count": 56,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1713,7 +1738,7 @@
},
{
"cell_type": "code",
"execution_count": 56,
"execution_count": 57,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1746,7 +1771,7 @@
},
{
"cell_type": "code",
"execution_count": 57,
"execution_count": 58,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1768,7 +1793,7 @@
},
{
"cell_type": "code",
"execution_count": 58,
"execution_count": 59,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1801,7 +1826,10 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"Note: instead of using `tf.contrib.layers.convolution2d()` or `tf.contrib.layers.conv2d()` (as in the book), we now use the `tf.layers.conv2d()`, which did not exist when this chapter was written. This is preferable because anything in contrib may change or be deleted without notice, while `tf.layers` is part of the official API. As you will see, the code is mostly the same, except that the parameter names have changed slightly:\n",
"* the `num_outputs` parameter was renamed to `filters`,\n",
@ -1814,7 +1842,7 @@
},
{
"cell_type": "code",
"execution_count": 59,
"execution_count": 60,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1822,7 +1850,7 @@
},
"outputs": [],
"source": [
"tf.reset_default_graph()\n",
"reset_graph()\n",
"\n",
"input_height = 88\n",
"input_width = 80\n",
@ -1877,7 +1905,7 @@
},
{
"cell_type": "code",
"execution_count": 60,
"execution_count": 61,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1890,7 +1918,7 @@
},
{
"cell_type": "code",
"execution_count": 61,
"execution_count": 62,
"metadata": {
"collapsed": false,
"deletable": true,
@ -1916,7 +1944,7 @@
},
{
"cell_type": "code",
"execution_count": 62,
"execution_count": 63,
"metadata": {
"collapsed": true,
"deletable": true,
@ -1939,7 +1967,7 @@
},
{
"cell_type": "code",
"execution_count": 63,
"execution_count": 64,
"metadata": {
"collapsed": false,
"deletable": true,