Merge branch 'pytorch:main' into issue#1757

Author: HemanthSai7

Diff for: advanced_source/neural_style_tutorial.py

@@ -423,6 +423,9 @@ def run_style_transfer(cnn, normalization_mean, normalization_std,
     # We want to optimize the input and not the model parameters so we
     # update all the requires_grad fields accordingly
     input_img.requires_grad_(True)
+    # We also put the model in evaluation mode, so that specific layers 
+    # such as dropout or batch normalization layers behave correctly. 
+    model.eval()
     model.requires_grad_(False)
 
     optimizer = get_input_optimizer(input_img)

Diff for: advanced_source/super_resolution_with_onnxruntime.py

@@ -16,10 +16,7 @@
 and `ONNX Runtime <https://github.com/microsoft/onnxruntime>`__.
 You can get binary builds of ONNX and ONNX Runtime with
 ``pip install onnx onnxruntime``.
-Note that ONNX Runtime is compatible with Python versions 3.5 to 3.7.
-
-``NOTE``: This tutorial needs PyTorch master branch which can be installed by following
-the instructions `here <https://github.com/pytorch/pytorch#from-source>`__
+ONNX Runtime recommends using the latest stable runtime for PyTorch.
 
 """
 

Diff for: beginner_source/README.txt

@@ -23,4 +23,4 @@ Beginner Tutorials
 
 6. transformer_translation.py
 	Language Translation with Transformers
-	https://pytorch.org/tutorials/beginner/transformer_tutorial.html
+	https://pytorch.org/tutorials/beginner/translation_transformer.html

Diff for: beginner_source/deep_learning_60min_blitz.rst

@@ -20,11 +20,12 @@ Goal of this tutorial:
 - Understand PyTorch’s Tensor library and neural networks at a high level.
 - Train a small neural network to classify images
 
-To run the tutorials below, make sure you have the `torch`_ and `torchvision`_
-packages installed.
+To run the tutorials below, make sure you have the `torch`_, `torchvision`_,
+and `matplotlib`_ packages installed.
 
 .. _torch: https://github.com/pytorch/pytorch
 .. _torchvision: https://github.com/pytorch/vision
+.. _matplotlib: https://github.com/matplotlib/matplotlib
 
 .. toctree::
    :hidden:

Diff for: beginner_source/introyt/trainingyt.py

@@ -290,15 +290,19 @@ def train_one_epoch(epoch_index, tb_writer):
     model.train(True)
     avg_loss = train_one_epoch(epoch_number, writer)
 
-    # We don't need gradients on to do reporting
-    model.train(False)
-    
+
     running_vloss = 0.0
-    for i, vdata in enumerate(validation_loader):
-        vinputs, vlabels = vdata
-        voutputs = model(vinputs)
-        vloss = loss_fn(voutputs, vlabels)
-        running_vloss += vloss
+    # Set the model to evaluation mode, disabling dropout and using population 
+    # statistics for batch normalization.
+    model.eval()
+
+    # Disable gradient computation and reduce memory consumption.
+    with torch.no_grad():
+        for i, vdata in enumerate(validation_loader):
+            vinputs, vlabels = vdata
+            voutputs = model(vinputs)
+            vloss = loss_fn(voutputs, vlabels)
+            running_vloss += vloss
 
     avg_vloss = running_vloss / (i + 1)
     print('LOSS train {} valid {}'.format(avg_loss, avg_vloss))

Diff for: beginner_source/nn_tutorial.py

@@ -75,6 +75,11 @@
 import numpy as np
 
 pyplot.imshow(x_train[0].reshape((28, 28)), cmap="gray")
+# ``pyplot.show()`` only if not on Colab
+try:
+    import google.colab
+except ImportError:
+    pyplot.show()
 print(x_train.shape)
 
 ###############################################################################

Diff for: beginner_source/transformer_tutorial.py

@@ -37,7 +37,7 @@
 # ``nn.TransformerEncoder`` consists of multiple layers of
 # `nn.TransformerEncoderLayer <https://pytorch.org/docs/stable/generated/torch.nn.TransformerEncoderLayer.html>`__.
 # Along with the input sequence, a square attention mask is required because the
-# self-attention layers in ``nn.TransformerEncoder`` are only allowed to attend
+# self-attention layers in ``nn.TransformerDecoder`` are only allowed to attend
 # the earlier positions in the sequence. For the language modeling task, any
 # tokens on the future positions should be masked. To produce a probability
 # distribution over output words, the output of the ``nn.TransformerEncoder``

Diff for: intermediate_source/char_rnn_classification_tutorial.py

@@ -2,7 +2,7 @@
 """
 NLP From Scratch: Classifying Names with a Character-Level RNN
 **************************************************************
-**Author**: `Sean Robertson <https://github.com/spro/practical-pytorch>`_
+**Author**: `Sean Robertson <https://github.com/spro>`_
 
 We will be building and training a basic character-level RNN to classify
 words. This tutorial, along with the following two, show how to do

Diff for: intermediate_source/char_rnn_generation_tutorial.py

@@ -2,7 +2,7 @@
 """
 NLP From Scratch: Generating Names with a Character-Level RNN
 *************************************************************
-**Author**: `Sean Robertson <https://github.com/spro/practical-pytorch>`_
+**Author**: `Sean Robertson <https://github.com/spro>`_
 
 This is our second of three tutorials on "NLP From Scratch".
 In the `first tutorial </intermediate/char_rnn_classification_tutorial>`

Diff for: intermediate_source/dynamic_quantization_bert_tutorial.rst

@@ -68,7 +68,7 @@ built-in F1 score calculation helper function.
 .. code:: shell
 
    pip install sklearn
-   pip install transformers
+   pip install transformers==4.29.2
 
 
 Because we will be using the beta parts of the PyTorch, it is

Diff for: intermediate_source/seq2seq_translation_tutorial.py

@@ -2,7 +2,7 @@
 """
 NLP From Scratch: Translation with a Sequence to Sequence Network and Attention
 *******************************************************************************
-**Author**: `Sean Robertson <https://github.com/spro/practical-pytorch>`_
+**Author**: `Sean Robertson <https://github.com/spro>`_
 
 This is the third and final tutorial on doing "NLP From Scratch", where we
 write our own classes and functions to preprocess the data to do our NLP

Diff for: intermediate_source/torchvision_tutorial.rst

@@ -145,7 +145,7 @@ Let’s write a ``torch.utils.data.Dataset`` class for this dataset.
            num_objs = len(obj_ids)
            boxes = []
            for i in range(num_objs):
-               pos = np.where(masks[i])
+               pos = np.nonzero(masks[i])
                xmin = np.min(pos[1])
                xmax = np.max(pos[1])
                ymin = np.min(pos[0])