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

Fix bug: tf.add_n([loss] + reg_losses) rather than loss + reg_losses

main
Aurélien Geron 2017-03-04 12:36:25 +01:00
parent fe552bbbed
commit 7997d4d38c
2 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
11_deep_learning.ipynb
View File

@ -504,7 +504,7 @@
" xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y, logits=logits)\n",
" reg_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)\n",
" base_loss = tf.reduce_mean(xentropy, name=\"base_loss\")\n",
" loss = tf.add(base_loss, reg_losses, name=\"loss\")\n",
" loss = tf.add_n([base_loss] + reg_losses, name=\"loss\")\n",
"\n",
"with tf.name_scope(\"train\"):\n",
" optimizer = tf.train.MomentumOptimizer(learning_rate, momentum)\n",
@ -749,6 +749,7 @@
" for iteration in range(len(mnist.test.labels)//batch_size):\n",
" X_batch, y_batch = mnist.train.next_batch(batch_size)\n",
" sess.run(training_op, feed_dict={is_training: True, X: X_batch, y: y_batch})\n",
" sess.run(clip_all_weights)\n",
" acc_train = accuracy.eval(feed_dict={is_training: False, X: X_batch, y: y_batch})\n",
" acc_test = accuracy.eval(feed_dict={is_training: False, X: mnist.test.images, y: mnist.test.labels})\n",
" print(epoch, \"Train accuracy:\", acc_train, \"Test accuracy:\", acc_test)\n",

4
15_autoencoders.ipynb
View File

@ -393,7 +393,7 @@
"mse = tf.reduce_mean(tf.square(outputs - X))\n",
"\n",
"reg_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)\n",
"loss = mse + reg_losses\n",
"loss = tf.add_n([mse] + reg_losses)\n",
"\n",
"optimizer = tf.train.AdamOptimizer(learning_rate)\n",
"training_op = optimizer.minimize(loss)\n",
@ -545,7 +545,7 @@
" mse = tf.reduce_mean(tf.square(outputs - X))\n",
"\n",
" reg_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)\n",
" loss = mse + reg_losses\n",
" loss = tf.add_n([mse] + reg_losses)\n",
"\n",
" optimizer = tf.train.AdamOptimizer(learning_rate)\n",
" training_op = optimizer.minimize(loss)\n",