Updated to latest version of TensorFlow
Aurélien Geron
parent
55adea1ff4
commit
1886d796e1
|
|
@ -77,9 +77,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
|
|
@ -90,7 +88,7 @@
|
|||
"X = iris.data[:, (2, 3)] # petal length, petal width\n",
|
||||
"y = (iris.target == 0).astype(np.int)\n",
|
||||
"\n",
|
||||
"per_clf = Perceptron(random_state=42)\n",
|
||||
"per_clf = Perceptron(max_iter=100, random_state=42)\n",
|
||||
"per_clf.fit(X, y)\n",
|
||||
"\n",
|
||||
"y_pred = per_clf.predict([[2, 0.5]])"
|
||||
|
|
@ -132,7 +130,7 @@
|
|||
"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.contourf(x0, x1, zz, cmap=custom_cmap)\n",
|
||||
"plt.xlabel(\"Petal length\", fontsize=14)\n",
|
||||
"plt.ylabel(\"Petal width\", fontsize=14)\n",
|
||||
"plt.legend(loc=\"lower right\", fontsize=14)\n",
|
||||
|
|
@ -152,9 +150,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def logit(z):\n",
|
||||
|
|
@ -206,9 +202,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def heaviside(z):\n",
|
||||
|
|
@ -262,7 +256,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## using tf.learn"
|
||||
"## Using the Estimator API (formerly `tf.contrib.learn`)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -271,23 +265,29 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from tensorflow.examples.tutorials.mnist import input_data\n",
|
||||
"\n",
|
||||
"mnist = input_data.read_data_sets(\"/tmp/data/\")"
|
||||
"import tensorflow as tf"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Warning**: `tf.examples.tutorials.mnist` is deprecated. We will use `tf.keras.datasets.mnist` instead. Moreover, the `tf.contrib.learn` API was promoted to `tf.estimators` and `tf.feature_columns`, and it has changed considerably. In particular, there is no `infer_real_valued_columns_from_input()` function or `SKCompat` class."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"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\")"
|
||||
"(X_train, y_train), (X_test, y_test) = tf.keras.datasets.mnist.load_data()\n",
|
||||
"X_train = X_train.astype(np.float32).reshape(-1, 28*28) / 255.0\n",
|
||||
"X_test = X_test.astype(np.float32).reshape(-1, 28*28) / 255.0\n",
|
||||
"y_train = y_train.astype(np.int32)\n",
|
||||
"y_test = y_test.astype(np.int32)\n",
|
||||
"X_valid, X_train = X_train[:5000], X_train[5000:]\n",
|
||||
"y_valid, y_train = y_train[:5000], y_train[5000:]"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -296,15 +296,13 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import tensorflow as tf\n",
|
||||
"feature_cols = [tf.feature_column.numeric_column(\"X\", shape=[28 * 28])]\n",
|
||||
"dnn_clf = tf.estimator.DNNClassifier(hidden_units=[300,100], n_classes=10,\n",
|
||||
" feature_columns=feature_cols)\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",
|
||||
"dnn_clf = tf.contrib.learn.DNNClassifier(hidden_units=[300,100], n_classes=10,\n",
|
||||
" feature_columns=feature_cols, config=config)\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)"
|
||||
"input_fn = tf.estimator.inputs.numpy_input_fn(\n",
|
||||
" x={\"X\": X_train}, y=y_train, num_epochs=40, batch_size=50, shuffle=True)\n",
|
||||
"dnn_clf.train(input_fn=input_fn)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -313,10 +311,9 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.metrics import accuracy_score\n",
|
||||
"\n",
|
||||
"y_pred = dnn_clf.predict(X_test)\n",
|
||||
"accuracy_score(y_test, y_pred['classes'])"
|
||||
"test_input_fn = tf.estimator.inputs.numpy_input_fn(\n",
|
||||
" x={\"X\": X_test}, y=y_test, shuffle=False)\n",
|
||||
"eval_results = dnn_clf.evaluate(input_fn=test_input_fn)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -325,10 +322,18 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.metrics import log_loss\n",
|
||||
"\n",
|
||||
"y_pred_proba = y_pred['probabilities']\n",
|
||||
"log_loss(y_test, y_pred_proba)"
|
||||
"eval_results"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"y_pred_iter = dnn_clf.predict(input_fn=test_input_fn)\n",
|
||||
"y_pred = list(y_pred_iter)\n",
|
||||
"y_pred[0]"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -342,7 +347,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -356,19 +361,19 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"execution_count": 16,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
"\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.int32, shape=(None), name=\"y\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"execution_count": 17,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -388,7 +393,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"execution_count": 18,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -402,7 +407,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"execution_count": 19,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -414,7 +419,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 19,
|
||||
"execution_count": 20,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -427,7 +432,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 20,
|
||||
"execution_count": 21,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -438,7 +443,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"execution_count": 22,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -448,7 +453,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
"execution_count": 23,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -458,55 +463,69 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"execution_count": 24,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def shuffle_batch(X, y, batch_size):\n",
|
||||
" rnd_idx = np.random.permutation(len(X))\n",
|
||||
" n_batches = len(X) // batch_size\n",
|
||||
" for batch_idx in np.array_split(rnd_idx, n_batches):\n",
|
||||
" X_batch, y_batch = X[batch_idx], y[batch_idx]\n",
|
||||
" yield X_batch, y_batch"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 25,
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.Session() as sess:\n",
|
||||
" init.run()\n",
|
||||
" for epoch in range(n_epochs):\n",
|
||||
" for iteration in range(mnist.train.num_examples // batch_size):\n",
|
||||
" X_batch, y_batch = mnist.train.next_batch(batch_size)\n",
|
||||
" for X_batch, y_batch in shuffle_batch(X_train, y_train, 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_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",
|
||||
" acc_batch = accuracy.eval(feed_dict={X: X_batch, y: y_batch})\n",
|
||||
" acc_val = accuracy.eval(feed_dict={X: X_valid, y: y_valid})\n",
|
||||
" print(epoch, \"Batch accuracy:\", acc_batch, \"Val accuracy:\", acc_val)\n",
|
||||
"\n",
|
||||
" save_path = saver.save(sess, \"./my_model_final.ckpt\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 24,
|
||||
"execution_count": 26,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.Session() as sess:\n",
|
||||
" saver.restore(sess, \"./my_model_final.ckpt\") # or better, use save_path\n",
|
||||
" X_new_scaled = mnist.test.images[:20]\n",
|
||||
" X_new_scaled = X_test[:20]\n",
|
||||
" Z = logits.eval(feed_dict={X: X_new_scaled})\n",
|
||||
" y_pred = np.argmax(Z, axis=1)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 25,
|
||||
"execution_count": 27,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"Predicted classes:\", y_pred)\n",
|
||||
"print(\"Actual classes: \", mnist.test.labels[:20])"
|
||||
"print(\"Actual classes: \", y_test[:20])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 26,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 28,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Works on Chrome, not guaranteed on other browsers\n",
|
||||
"\n",
|
||||
"from IPython.display import clear_output, Image, display, HTML\n",
|
||||
"\n",
|
||||
"def strip_consts(graph_def, max_const_size=32):\n",
|
||||
|
|
@ -547,7 +566,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 27,
|
||||
"execution_count": 29,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -565,7 +584,7 @@
|
|||
"cell_type": "markdown",
|
||||
"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",
|
||||
"Note: previous releases of the book used `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",
|
||||
"* the default `activation` is now `None` rather than `tf.nn.relu`.\n",
|
||||
"* a few more differences are presented in chapter 11."
|
||||
|
|
@ -573,7 +592,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 28,
|
||||
"execution_count": 30,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -585,21 +604,19 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 31,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
"\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.int32, shape=(None), name=\"y\") "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 30,
|
||||
"execution_count": 32,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -608,15 +625,14 @@
|
|||
" activation=tf.nn.relu)\n",
|
||||
" hidden2 = tf.layers.dense(hidden1, n_hidden2, name=\"hidden2\",\n",
|
||||
" activation=tf.nn.relu)\n",
|
||||
" logits = tf.layers.dense(hidden2, n_outputs, name=\"outputs\")"
|
||||
" logits = tf.layers.dense(hidden2, n_outputs, name=\"outputs\")\n",
|
||||
" y_proba = tf.nn.softmax(logits)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 31,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 33,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.name_scope(\"loss\"):\n",
|
||||
|
|
@ -626,10 +642,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 32,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 34,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"learning_rate = 0.01\n",
|
||||
|
|
@ -641,10 +655,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 33,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 35,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.name_scope(\"eval\"):\n",
|
||||
|
|
@ -654,10 +666,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 34,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 36,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"init = tf.global_variables_initializer()\n",
|
||||
|
|
@ -666,7 +676,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 35,
|
||||
"execution_count": 38,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -676,19 +686,18 @@
|
|||
"with tf.Session() as sess:\n",
|
||||
" init.run()\n",
|
||||
" for epoch in range(n_epochs):\n",
|
||||
" for iteration in range(mnist.train.num_examples // batch_size):\n",
|
||||
" X_batch, y_batch = mnist.train.next_batch(batch_size)\n",
|
||||
" for X_batch, y_batch in shuffle_batch(X_train, y_train, 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",
|
||||
" acc_batch = accuracy.eval(feed_dict={X: X_batch, y: y_batch})\n",
|
||||
" acc_valid = accuracy.eval(feed_dict={X: X_valid, y: y_valid})\n",
|
||||
" print(epoch, \"Batch accuracy:\", acc_batch, \"Validation accuracy:\", acc_valid)\n",
|
||||
"\n",
|
||||
" save_path = saver.save(sess, \"./my_model_final.ckpt\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 36,
|
||||
"execution_count": 39,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -743,7 +752,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 37,
|
||||
"execution_count": 40,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -755,21 +764,19 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 38,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 41,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reset_graph()\n",
|
||||
"\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.int32, shape=(None), name=\"y\") "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 39,
|
||||
"execution_count": 42,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -783,10 +790,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 40,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 43,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.name_scope(\"loss\"):\n",
|
||||
|
|
@ -797,10 +802,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 41,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 44,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"learning_rate = 0.01\n",
|
||||
|
|
@ -812,10 +815,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 42,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 45,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with tf.name_scope(\"eval\"):\n",
|
||||
|
|
@ -826,10 +827,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 43,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 46,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"init = tf.global_variables_initializer()\n",
|
||||
|
|
@ -845,10 +844,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 44,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 47,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from datetime import datetime\n",
|
||||
|
|
@ -864,10 +861,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 45,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 48,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"logdir = log_dir(\"mnist_dnn\")"
|
||||
|
|
@ -882,10 +877,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 46,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 49,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"file_writer = tf.summary.FileWriter(logdir, tf.get_default_graph())"
|
||||
|
|
@ -895,33 +888,21 @@
|
|||
"cell_type": "markdown",
|
||||
"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`:"
|
||||
"Hey! Why don't we implement early stopping? For this, we are going to need to use the validation set."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 47,
|
||||
"execution_count": 50,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_valid = mnist.validation.images\n",
|
||||
"y_valid = mnist.validation.labels"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 48,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"m, n = X_train.shape"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 49,
|
||||
"execution_count": 52,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -949,8 +930,7 @@
|
|||
" sess.run(init)\n",
|
||||
"\n",
|
||||
" for epoch in range(start_epoch, n_epochs):\n",
|
||||
" for iteration in range(mnist.train.num_examples // batch_size):\n",
|
||||
" X_batch, y_batch = mnist.train.next_batch(batch_size)\n",
|
||||
" for X_batch, y_batch in shuffle_batch(X_train, y_train, batch_size):\n",
|
||||
" sess.run(training_op, feed_dict={X: X_batch, y: y_batch})\n",
|
||||
" accuracy_val, loss_val, accuracy_summary_str, loss_summary_str = sess.run([accuracy, loss, accuracy_summary, loss_summary], feed_dict={X: X_valid, y: y_valid})\n",
|
||||
" file_writer.add_summary(accuracy_summary_str, epoch)\n",
|
||||
|
|
@ -974,7 +954,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 50,
|
||||
"execution_count": 53,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -983,7 +963,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 51,
|
||||
"execution_count": 54,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -994,7 +974,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 52,
|
||||
"execution_count": 55,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -1004,9 +984,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
|
|
@ -1027,7 +1005,7 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.2"
|
||||
"version": "3.5.2"
|
||||
},
|
||||
"nav_menu": {
|
||||
"height": "264px",
|
||||
|
|
|
|||
Loading…
Reference in New Issue