Merge branch 'master' into link

Author: holly1238

.circleci/scripts/build_for_windows.sh

@@ -49,6 +49,7 @@ if [[ "${CIRCLE_JOB}" == *worker_* ]]; then
   python $DIR/remove_runnable_code.py advanced_source/static_quantization_tutorial.py advanced_source/static_quantization_tutorial.py || true
   python $DIR/remove_runnable_code.py beginner_source/hyperparameter_tuning_tutorial.py beginner_source/hyperparameter_tuning_tutorial.py || true
   python $DIR/remove_runnable_code.py beginner_source/audio_preprocessing_tutorial.py  beginner_source/audio_preprocessing_tutorial.py || true
+  python $DIR/remove_runnable_code.py beginner_source/dcgan_faces_tutorial.py  beginner_source/dcgan_faces_tutorial.py || true
   python $DIR/remove_runnable_code.py intermediate_source/tensorboard_profiler_tutorial.py intermediate_source/tensorboard_profiler_tutorial.py || true
   # Temp remove for mnist download issue. (Re-enabled for 1.8.1)
   # python $DIR/remove_runnable_code.py beginner_source/fgsm_tutorial.py  beginner_source/fgsm_tutorial.py || true

beginner_source/basics/autogradqs_tutorial.py

@@ -47,7 +47,7 @@
 #
 # In this network, ``w`` and ``b`` are **parameters**, which we need to
 # optimize. Thus, we need to be able to compute the gradients of loss
-# function with respect to those variables. In orded to do that, we set
+# function with respect to those variables. In order to do that, we set
 # the ``requires_grad`` property of those tensors.
 
 #######################################################################

beginner_source/chatbot_tutorial.py

@@ -471,7 +471,7 @@ def trimRareWords(voc, pairs, MIN_COUNT):
 # with mini-batches.
 #
 # Using mini-batches also means that we must be mindful of the variation
-# of sentence length in our batches. To accomodate sentences of different
+# of sentence length in our batches. To accommodate sentences of different
 # sizes in the same batch, we will make our batched input tensor of shape
 # *(max_length, batch_size)*, where sentences shorter than the
 # *max_length* are zero padded after an *EOS_token*.
@@ -615,7 +615,7 @@ def batch2TrainData(voc, pair_batch):
 # in normal sequential order, and one that is fed the input sequence in
 # reverse order. The outputs of each network are summed at each time step.
 # Using a bidirectional GRU will give us the advantage of encoding both
-# past and future context.
+# past and future contexts.
 #
 # Bidirectional RNN:
 #
@@ -700,7 +700,7 @@ def forward(self, input_seq, input_lengths, hidden=None):
 # states to generate the next word in the sequence. It continues
 # generating words until it outputs an *EOS_token*, representing the end
 # of the sentence. A common problem with a vanilla seq2seq decoder is that
-# if we rely soley on the context vector to encode the entire input
+# if we rely solely on the context vector to encode the entire input
 # sequence’s meaning, it is likely that we will have information loss.
 # This is especially the case when dealing with long input sequences,
 # greatly limiting the capability of our decoder.
@@ -950,7 +950,7 @@ def maskNLLLoss(inp, target, mask):
 #   sequence (or batch of sequences). We use the ``GRU`` layer like this in
 #   the ``encoder``. The reality is that under the hood, there is an
 #   iterative process looping over each time step calculating hidden states.
-#   Alternatively, you ran run these modules one time-step at a time. In
+#   Alternatively, you can run these modules one time-step at a time. In
 #   this case, we manually loop over the sequences during the training
 #   process like we must do for the ``decoder`` model. As long as you
 #   maintain the correct conceptual model of these modules, implementing
@@ -1115,7 +1115,7 @@ def trainIters(model_name, voc, pairs, encoder, decoder, encoder_optimizer, deco
 # softmax value. This decoding method is optimal on a single time-step
 # level.
 #
-# To facilite the greedy decoding operation, we define a
+# To facilitate the greedy decoding operation, we define a
 # ``GreedySearchDecoder`` class. When run, an object of this class takes
 # an input sequence (``input_seq``) of shape *(input_seq length, 1)*, a
 # scalar input length (``input_length``) tensor, and a ``max_length`` to

beginner_source/nlp/pytorch_tutorial.py

@@ -9,7 +9,7 @@
 All of deep learning is computations on tensors, which are
 generalizations of a matrix that can be indexed in more than 2
 dimensions. We will see exactly what this means in-depth later. First,
-lets look what we can do with tensors.
+let's look what we can do with tensors.
 """
 # Author: Robert Guthrie
 
@@ -162,7 +162,7 @@
 # other operation, etc.)
 #
 # If ``requires_grad=True``, the Tensor object keeps track of how it was
-# created. Lets see it in action.
+# created. Let's see it in action.
 #
 
 # Tensor factory methods have a ``requires_grad`` flag
@@ -187,7 +187,7 @@
 # But how does that help us compute a gradient?
 #
 
-# Lets sum up all the entries in z
+# Let's sum up all the entries in z
 s = z.sum()
 print(s)
 print(s.grad_fn)
@@ -222,7 +222,7 @@
 
 
 ######################################################################
-# Lets have Pytorch compute the gradient, and see that we were right:
+# Let's have Pytorch compute the gradient, and see that we were right:
 # (note if you run this block multiple times, the gradient will increment.
 # That is because Pytorch *accumulates* the gradient into the .grad
 # property, since for many models this is very convenient.)

beginner_source/transformer_tutorial.py

@@ -45,15 +45,16 @@
 #
 
 import math
+
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
+from torch.nn import TransformerEncoder, TransformerEncoderLayer
 
 class TransformerModel(nn.Module):
 
     def __init__(self, ntoken, ninp, nhead, nhid, nlayers, dropout=0.5):
         super(TransformerModel, self).__init__()
-        from torch.nn import TransformerEncoder, TransformerEncoderLayer
         self.model_type = 'Transformer'
         self.pos_encoder = PositionalEncoding(ninp, dropout)
         encoder_layers = TransformerEncoderLayer(ninp, nhead, nhid, dropout)
@@ -251,12 +252,13 @@ def get_batch(source, i):
 # function to scale all the gradient together to prevent exploding.
 #
 
+import time
+
 criterion = nn.CrossEntropyLoss()
 lr = 5.0 # learning rate
 optimizer = torch.optim.SGD(model.parameters(), lr=lr)
 scheduler = torch.optim.lr_scheduler.StepLR(optimizer, 1.0, gamma=0.95)
 
-import time
 def train():
     model.train() # Turn on the train mode
     total_loss = 0.

index.rst

@@ -497,7 +497,7 @@ Additional Resources
    :header: PyTorch Cheat Sheet
    :description: Quick overview to essential PyTorch elements.
    :button_link: beginner/ptcheat.html
-   :button_text: Download
+   :button_text: Open
 
 .. customcalloutitem::
    :header: Tutorials on GitHub
@@ -509,7 +509,7 @@ Additional Resources
    :header: Run Tutorials on Google Colab
    :description: Learn how to copy tutorial data into Google Drive so that you can run tutorials on Google Colab.
    :button_link: beginner/colab.html
-   :button_text: Download
+   :button_text: Open
 
 .. End of callout section
 

intermediate_source/torchvision_tutorial.rst

@@ -64,7 +64,7 @@ training and evaluation, and will use the evaluation scripts from
 One note on the ``labels``. The model considers class ``0`` as background. If your dataset does not contain the background class, you should not have ``0`` in your ``labels``. For example, assuming you have just two classes, *cat* and *dog*, you can define ``1`` (not ``0``) to represent *cats* and ``2`` to represent *dogs*. So, for instance, if one of the images has both classes, your ``labels`` tensor should look like ``[1,2]``.
 
 Additionally, if you want to use aspect ratio grouping during training
-(so that each batch only contains images with similar aspect ratio),
+(so that each batch only contains images with similar aspect ratios),
 then it is recommended to also implement a ``get_height_and_width``
 method, which returns the height and the width of the image. If this
 method is not provided, we query all elements of the dataset via