Merge branch 'main' into main

Author: NM512

beginner_source/Intro_to_TorchScript_tutorial.py

@@ -33,6 +33,7 @@
 
 import torch  # This is all you need to use both PyTorch and TorchScript!
 print(torch.__version__)
+torch.manual_seed(191009)  # set the seed for reproducibility
 
 
 ######################################################################
@@ -308,7 +309,7 @@ def forward(self, x, h):
 
 # New inputs
 x, h = torch.rand(3, 4), torch.rand(3, 4)
-traced_cell(x, h)
+print(scripted_cell(x, h))
 
 
 ######################################################################

intermediate_source/seq2seq_translation_tutorial.py

@@ -45,7 +45,7 @@
    :alt:
 
 To improve upon this model we'll use an `attention
-mechanism <https://arxiv.org/abs/1409.0473>`__, which lets the decoder
+mechanism <https://arxiv.org/abs/1508.04025>`__, which lets the decoder
 learn to focus over a specific range of the input sequence.
 
 **Recommended Reading:**
@@ -66,8 +66,8 @@
    Statistical Machine Translation <https://arxiv.org/abs/1406.1078>`__
 -  `Sequence to Sequence Learning with Neural
    Networks <https://arxiv.org/abs/1409.3215>`__
--  `Neural Machine Translation by Jointly Learning to Align and
-   Translate <https://arxiv.org/abs/1409.0473>`__
+-  `Effective Approaches to Attention-based Neural Machine
+   Translation <https://arxiv.org/abs/1508.04025>`__
 -  `A Neural Conversational Model <https://arxiv.org/abs/1506.05869>`__
 
 You will also find the previous tutorials on

intermediate_source/torch_compile_tutorial.py

@@ -105,7 +105,7 @@ def forward(self, x):
 #
 # Let's now demonstrate that using ``torch.compile`` can speed
 # up real models. We will compare standard eager mode and 
-# ``torch.compile`` by evaluating and training ResNet-18 on random data.
+# ``torch.compile`` by evaluating and training a ``torchvision`` model on random data.
 #
 # Before we start, we need to define some utility functions.