Merge branch 'master' into master

Author: holly1238

README.md

@@ -28,10 +28,10 @@ In case you prefer to write your tutorial in jupyter, you can use [this script](
 - Then you can build using `make docs`. This will download the data, execute the tutorials and build the documentation to `docs/` directory. This will take about 60-120 min for systems with GPUs. If you do not have a GPU installed on your system, then see next step.
 - You can skip the computationally intensive graph generation by running `make html-noplot` to build basic html documentation to `_build/html`. This way, you can quickly preview your tutorial.
 
-> If you get **ModuleNotFoundError: No module named 'pytorch_sphinx_theme' make: *** [html-noplot] Error 2**, from /tutorials/src/pytorch-sphinx-theme run `python setup.py install`. 
+> If you get **ModuleNotFoundError: No module named 'pytorch_sphinx_theme' make: *** [html-noplot] Error 2** from /tutorials/src/pytorch-sphinx-theme or /venv/src/pytorch-sphinx-theme (while using virtualenv), run `python setup.py install`. 
 
 
 ## About contributing to PyTorch Documentation and Tutorials
 * You can find information about contributing to PyTorch documentation in the 
 PyTorch Repo [README.md](https://github.com/pytorch/pytorch/blob/master/README.md) file. 
-* Additional information can be found in [PyTorch CONTRIBUTING.md](https://github.com/pytorch/pytorch/blob/master/CONTRIBUTING.md).
+* Additional information can be found in [PyTorch CONTRIBUTING.md](https://github.com/pytorch/pytorch/blob/master/CONTRIBUTING.md).

beginner_source/basics/autogradqs_tutorial.py

@@ -58,7 +58,7 @@
 # A function that we apply to tensors to construct computational graph is
 # in fact an object of class ``Function``. This object knows how to
 # compute the function in the *forward* direction, and also how to compute
-# it's derivative during the *backward propagation* step. A reference to
+# its derivative during the *backward propagation* step. A reference to
 # the backward propagation function is stored in ``grad_fn`` property of a
 # tensor. You can find more information of ``Function`` `in the
 # documentation <https://pytorch.org/docs/stable/autograd.html#function>`__.

beginner_source/basics/buildmodel_tutorial.py

@@ -67,7 +67,7 @@ def forward(self, x):
 
 ##############################################
 # We create an instance of ``NeuralNetwork``, and move it to the ``device``, and print 
-# it's structure.
+# its structure.
 
 model = NeuralNetwork().to(device)
 print(model)
@@ -119,7 +119,7 @@ def forward(self, x):
 # nn.Linear 
 # ^^^^^^^^^^^^^^^^^^^^^^
 # The `linear layer <https://pytorch.org/docs/stable/generated/torch.nn.Linear.html>`_
-# is a module that applies a linear transformation on the input using it's stored weights and biases.
+# is a module that applies a linear transformation on the input using its stored weights and biases.
 #
 layer1 = nn.Linear(in_features=28*28, out_features=20)
 hidden1 = layer1(flat_image)

beginner_source/basics/data_tutorial.py

@@ -225,7 +225,7 @@ def __getitem__(self, idx):
 # --------------------------
 #
 # We have loaded that dataset into the ``Dataloader`` and can iterate through the dataset as needed.
-# Each iteration below returns a batch of ``train_features`` and ``train_labels``(containing ``batch_size=64`` features and labels respectively).
+# Each iteration below returns a batch of ``train_features`` and ``train_labels`` (containing ``batch_size=64`` features and labels respectively).
 # Because we specified ``shuffle=True``, after we iterate over all batches the data is shuffled (for finer-grained control over 
 # the data loading order, take a look at `Samplers <https://pytorch.org/docs/stable/data.html#data-loading-order-and-sampler>`_).
 

beginner_source/blitz/README.txt

@@ -13,12 +13,11 @@ Deep Learning with PyTorch: A 60 Minute Blitz
 	Neural Networks
 	https://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#
 
-4. autograd_tutorial.py
-	Automatic Differentiation 
-	https://pytorch.org/tutorials/beginner/blitz/autograd_tutorial.html
-
-5. cifar10_tutorial.py
+4. cifar10_tutorial.py
 	Training a Classifier
 	https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html
 
+5. data_parallel_tutorial.py 
+	Optional: Data Parallelism
+	https://pytorch.org/tutorials/beginner/blitz/data_parallel_tutorial.html
 

beginner_source/blitz/cifar10_tutorial.py

@@ -246,10 +246,13 @@ def forward(self, x):
 
 correct = 0
 total = 0
+# since we're not training, we don't need to calculate the gradients for our outputs
 with torch.no_grad():
     for data in testloader:
         images, labels = data
+        # calculate outputs by running images through the network 
         outputs = net(images)
+        # the class with the highest energy is what we choose as prediction
         _, predicted = torch.max(outputs.data, 1)
         total += labels.size(0)
         correct += (predicted == labels).sum().item()
@@ -265,23 +268,28 @@ def forward(self, x):
 # Hmmm, what are the classes that performed well, and the classes that did
 # not perform well:
 
-class_correct = list(0. for i in range(10))
-class_total = list(0. for i in range(10))
+# prepare to count predictions for each class
+correct_pred = {classname: 0 for classname in classes}
+total_pred = {classname: 0 for classname in classes}
+
+# again no gradients needed
 with torch.no_grad():
     for data in testloader:
-        images, labels = data
-        outputs = net(images)
-        _, predicted = torch.max(outputs, 1)
-        c = (predicted == labels).squeeze()
-        for i in range(4):
-            label = labels[i]
-            class_correct[label] += c[i].item()
-            class_total[label] += 1
-
-
-for i in range(10):
-    print('Accuracy of %5s : %2d %%' % (
-        classes[i], 100 * class_correct[i] / class_total[i]))
+        images, labels = data    
+        outputs = net(images)    
+        _, predictions = torch.max(outputs, 1)
+        # collect the correct predictions for each class
+        for label, prediction in zip(labels, predictions):
+            if label == prediction:
+                correct_pred[classes[label]] += 1
+            total_pred[classes[label]] += 1
+
+  
+# print accuracy for each class
+for classname, correct_count in correct_pred.items():
+    accuracy = 100 * float(correct_count) / total_pred[classname]
+    print("Accuracy for class {:5s} is: {:.1f} %".format(classname, 
+                                                   accuracy))
 
 ########################################################################
 # Okay, so what next?

beginner_source/blitz/neural_networks_tutorial.py

@@ -176,8 +176,9 @@ def num_flat_features(self, x):
 #           -> loss
 #
 # So, when we call ``loss.backward()``, the whole graph is differentiated
-# w.r.t. the loss, and all Tensors in the graph that have ``requires_grad=True``
-# will have their ``.grad`` Tensor accumulated with the gradient.
+# w.r.t. the neural net parameters, and all Tensors in the graph that have
+# ``requires_grad=True`` will have their ``.grad`` Tensor accumulated with the
+# gradient.
 #
 # For illustration, let us follow a few steps backward:
 

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/dcgan_faces_tutorial.py

@@ -71,7 +71,7 @@
 # :math:`D` and :math:`G` play a minimax game in which :math:`D` tries to
 # maximize the probability it correctly classifies reals and fakes
 # (:math:`logD(x)`), and :math:`G` tries to minimize the probability that
-# :math:`D` will predict its outputs are fake (:math:`log(1-D(G(x)))`).
+# :math:`D` will predict its outputs are fake (:math:`log(1-D(G(z)))`).
 # From the paper, the GAN loss function is
 # 
 # .. math:: \underset{G}{\text{min}} \underset{D}{\text{max}}V(D,G) = \mathbb{E}_{x\sim p_{data}(x)}\big[logD(x)\big] + \mathbb{E}_{z\sim p_{z}(z)}\big[log(1-D(G(z)))\big]

beginner_source/nn_tutorial.py

@@ -85,7 +85,6 @@
     torch.tensor, (x_train, y_train, x_valid, y_valid)
 )
 n, c = x_train.shape
-x_train, x_train.shape, y_train.min(), y_train.max()
 print(x_train, y_train)
 print(x_train.shape)
 print(y_train.min(), y_train.max())