Merge branch 'master' into master

Author: brianjo

.jenkins/build.sh

@@ -40,7 +40,7 @@ if [[ "${JOB_BASE_NAME}" == *worker_* ]]; then
   # Step 1: Remove runnable code from tutorials that are not supposed to be run
   python $DIR/remove_runnable_code.py beginner_source/aws_distributed_training_tutorial.py beginner_source/aws_distributed_training_tutorial.py || true
   # TODO: Fix bugs in these tutorials to make them runnable again
-  python $DIR/remove_runnable_code.py beginner_source/audio_classifier_tutorial.py beginner_source/audio_classifier_tutorial.py || true
+  # python $DIR/remove_runnable_code.py beginner_source/audio_classifier_tutorial.py beginner_source/audio_classifier_tutorial.py || true
 
   # Step 2: Keep certain tutorials based on file count, and remove runnable code in all other tutorials
   # IMPORTANT NOTE: We assume that each tutorial has a UNIQUE filename.

advanced_source/dynamic_quantization_tutorial.py

@@ -178,7 +178,7 @@ def tokenize(self, path):
 
             word = corpus.dictionary.idx2word[word_idx]
 
-            outf.write(str(word) + ('\n' if i % 20 == 19 else ' '))
+            outf.write(str(word.encode('utf-8')) + ('\n' if i % 20 == 19 else ' '))
 
             if i % 100 == 0:
                 print('| Generated {}/{} words'.format(i, 1000))

beginner_source/blitz/neural_networks_tutorial.py

@@ -90,9 +90,9 @@ def num_flat_features(self, x):
 print(params[0].size())  # conv1's .weight
 
 ########################################################################
-# Let try a random 32x32 input.
+# Let's try a random 32x32 input.
 # Note: expected input size of this net (LeNet) is 32x32. To use this net on
-# MNIST dataset, please resize the images from the dataset to 32x32.
+# the MNIST dataset, please resize the images from the dataset to 32x32.
 
 input = torch.randn(1, 1, 32, 32)
 out = net(input)
@@ -227,7 +227,7 @@ def num_flat_features(self, x):
 #
 #      ``weight = weight - learning_rate * gradient``
 #
-# We can implement this using simple python code:
+# We can implement this using simple Python code:
 #
 # .. code:: python
 #
@@ -258,4 +258,4 @@ def num_flat_features(self, x):
 #
 #       Observe how gradient buffers had to be manually set to zero using
 #       ``optimizer.zero_grad()``. This is because gradients are accumulated
-#       as explained in `Backprop`_ section.
+#       as explained in the `Backprop`_ section.