Merge changes from github.

Change: 138143557

2 files changed, 10 insertions, 5 deletions

diff --git a/tensorflow/models/image/cifar10/cifar10.py b/tensorflow/models/image/cifar10/cifar10.py
index fb3a42cbb1..7df2149d40 100644
--- a/tensorflow/models/image/cifar10/cifar10.py
+++ b/tensorflow/models/image/cifar10/cifar10.py
@@ -256,7 +256,10 @@ def inference(images):
     local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name=scope.name)
     _activation_summary(local4)
 
-  # softmax, i.e. softmax(WX + b)
+  # linear layer(WX + b),
+  # We don't apply softmax here because 
+  # tf.nn.sparse_softmax_cross_entropy_with_logits accepts the unscaled logits 
+  # and performs the softmax internally for efficiency.
   with tf.variable_scope('softmax_linear') as scope:
     weights = _variable_with_weight_decay('weights', [192, NUM_CLASSES],
                                           stddev=1/192.0, wd=0.0)
diff --git a/tensorflow/models/image/mnist/convolutional.py b/tensorflow/models/image/mnist/convolutional.py
index 3ef1411c15..b458280379 100644
--- a/tensorflow/models/image/mnist/convolutional.py
+++ b/tensorflow/models/image/mnist/convolutional.py
@@ -296,11 +296,13 @@ def main(_):
       # node in the graph it should be fed to.
       feed_dict = {train_data_node: batch_data,
                    train_labels_node: batch_labels}
-      # Run the graph and fetch some of the nodes.
-      _, l, lr, predictions = sess.run(
-          [optimizer, loss, learning_rate, train_prediction],
-          feed_dict=feed_dict)
+      # Run the optimizer to update weights.
+      sess.run(optimizer, feed_dict=feed_dict)
+      # print some extra information once reach the evaluation frequency
       if step % EVAL_FREQUENCY == 0:
+        # fetch some extra nodes' data
+        l, lr, predictions = sess.run([loss, learning_rate, train_prediction],
+                                      feed_dict=feed_dict)
         elapsed_time = time.time() - start_time
         start_time = time.time()
         print('Step %d (epoch %.2f), %.1f ms' %