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

Use tf.set_random_seed(42) and more to make notebook's output constant

main
Aurélien Geron 2017-06-06 23:12:21 +02:00
parent 422cd78ea6
commit 6ec768b165
1 changed files with 76 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

102
10_introduction_to_artificial_neural_networks.ipynb
View File

@ -55,11 +55,13 @@
"\n", "\n",
"# Common imports\n", "# Common imports\n",
"import numpy as np\n", "import numpy as np\n",
"import numpy.random as rnd\n",
"import os\n", "import os\n",
"\n", "\n",
"# to make this notebook's output stable across runs\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", "\n",
"# To plot pretty figures\n", "# To plot pretty figures\n",
"%matplotlib inline\n", "%matplotlib inline\n",
@ -356,9 +358,11 @@
"source": [ "source": [
"import tensorflow as tf\n", "import tensorflow as tf\n",
"\n", "\n",
"config = tf.contrib.learn.RunConfig(tf_random_seed=42) # not shown in the config\n",
"\n",
"feature_cols = tf.contrib.learn.infer_real_valued_columns_from_input(X_train)\n", "feature_cols = 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", "dnn_clf = tf.contrib.learn.DNNClassifier(hidden_units=[300,100], n_classes=10,\n",
" feature_columns=feature_cols)\n", " feature_columns=feature_cols, config=config)\n",
"dnn_clf = tf.contrib.learn.SKCompat(dnn_clf) # if TensorFlow >= 1.1\n", "dnn_clf = tf.contrib.learn.SKCompat(dnn_clf) # if TensorFlow >= 1.1\n",
"dnn_clf.fit(X_train, y_train, batch_size=50, steps=40000)" "dnn_clf.fit(X_train, y_train, batch_size=50, steps=40000)"
] ]
@ -434,7 +438,7 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"tf.reset_default_graph()\n", "reset_graph()\n",
"\n", "\n",
"X = tf.placeholder(tf.float32, shape=(None, n_inputs), name=\"X\")\n", "X = tf.placeholder(tf.float32, shape=(None, n_inputs), name=\"X\")\n",
"y = tf.placeholder(tf.int64, shape=(None), name=\"y\")" "y = tf.placeholder(tf.int64, shape=(None), name=\"y\")"
@ -723,7 +727,7 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"tf.reset_default_graph()\n", "reset_graph()\n",
"\n", "\n",
"X = tf.placeholder(tf.float32, shape=(None, n_inputs), name=\"X\")\n", "X = tf.placeholder(tf.float32, shape=(None, n_inputs), name=\"X\")\n",
"y = tf.placeholder(tf.int64, shape=(None), name=\"y\") " "y = tf.placeholder(tf.int64, shape=(None), name=\"y\") "
@ -751,7 +755,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 31, "execution_count": 31,
"metadata": { "metadata": {
"collapsed": true "collapsed": true,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -764,7 +770,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 32, "execution_count": 32,
"metadata": { "metadata": {
"collapsed": true "collapsed": true,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -779,7 +787,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 33, "execution_count": 33,
"metadata": { "metadata": {
"collapsed": true "collapsed": true,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -792,7 +802,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 34, "execution_count": 34,
"metadata": { "metadata": {
"collapsed": true "collapsed": true,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -873,21 +885,30 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {
"deletable": true,
"editable": true
},
"source": [ "source": [
"## 9." "## 9."
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {
"deletable": true,
"editable": true
},
"source": [ "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)._" "_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", "cell_type": "markdown",
"metadata": {}, "metadata": {
"deletable": true,
"editable": true
},
"source": [ "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." "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."
] ]
@ -918,7 +939,7 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"tf.reset_default_graph()\n", "reset_graph()\n",
"\n", "\n",
"X = tf.placeholder(tf.float32, shape=(None, n_inputs), name=\"X\")\n", "X = tf.placeholder(tf.float32, shape=(None, n_inputs), name=\"X\")\n",
"y = tf.placeholder(tf.int64, shape=(None), name=\"y\") " "y = tf.placeholder(tf.int64, shape=(None), name=\"y\") "
@ -1007,7 +1028,10 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {
"deletable": true,
"editable": true
},
"source": [ "source": [
"Now we need to define the directory to write the TensorBoard logs to:" "Now we need to define the directory to write the TensorBoard logs to:"
] ]
@ -1016,7 +1040,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 44, "execution_count": 44,
"metadata": { "metadata": {
"collapsed": true "collapsed": true,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1035,7 +1061,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 45, "execution_count": 45,
"metadata": { "metadata": {
"collapsed": true "collapsed": true,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1044,7 +1072,10 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {
"deletable": true,
"editable": true
},
"source": [ "source": [
"Now we can create the `FileWriter` that we will use to write the TensorBoard logs:" "Now we can create the `FileWriter` that we will use to write the TensorBoard logs:"
] ]
@ -1053,7 +1084,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 46, "execution_count": 46,
"metadata": { "metadata": {
"collapsed": true "collapsed": true,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1062,7 +1095,10 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {
"deletable": true,
"editable": true
},
"source": [ "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`:" "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`:"
] ]
@ -1071,7 +1107,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 47, "execution_count": 47,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1083,7 +1121,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 48, "execution_count": 48,
"metadata": { "metadata": {
"collapsed": true "collapsed": true,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1094,7 +1134,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 49, "execution_count": 49,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1149,7 +1191,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 50, "execution_count": 50,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1160,7 +1204,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 51, "execution_count": 51,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1173,7 +1219,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 52, "execution_count": 52,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1184,7 +1232,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": { "metadata": {
"collapsed": true "collapsed": true,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [] "source": []