Merge branch 'master' into remove_generative_section

Author: Seth Weidman

beginner_source/transfer_learning_tutorial.py

@@ -252,6 +252,8 @@ def visualize_model(model, num_images=6):
 
 model_ft = models.resnet18(pretrained=True)
 num_ftrs = model_ft.fc.in_features
+# Here the size of each output sample is set to 2.
+# Alternatively, it can be generalized to nn.Linear(num_ftrs, len(class_names)).
 model_ft.fc = nn.Linear(num_ftrs, 2)
 
 model_ft = model_ft.to(device)

index.rst

@@ -307,7 +307,7 @@ PyTorch in Other Languages
    intermediate/char_rnn_generation_tutorial
    intermediate/seq2seq_translation_tutorial
    beginner/text_sentiment_ngrams_tutorial
-   beginner/translation_torchtext_tutorial
+   beginner/torchtext_translation_tutorial
    beginner/transformer_tutorial
 
 .. toctree::

intermediate_source/dist_tuto.rst

@@ -1,4 +1,4 @@
-Writing Distributed Applications with PyTorch
+3. Writing Distributed Applications with PyTorch
 =============================================
 **Author**: `Séb Arnold <https://seba1511.com>`_
 

intermediate_source/model_parallel_tutorial.py

@@ -28,7 +28,7 @@
 applications.
 
 Basic Usage
-================================
+-----------
 """
 
 ######################################################################
@@ -75,7 +75,7 @@ def forward(self, x):
 
 ######################################################################
 # Apply Model Parallel to Existing Modules
-# =======================
+# ----------------------------------------
 #
 # It is also possible to run an existing single-GPU module on multiple GPUs
 # with just a few lines of changes. The code below shows how to decompose
@@ -235,7 +235,7 @@ def plot(means, stds, labels, fig_name):
 
 ######################################################################
 # Speed Up by Pipelining Inputs
-# =======================
+# -----------------------------
 #
 # In the following experiments, we further divide each 120-image batch into
 # 20-image splits. As PyTorch launches CUDA operations asynchronizely, the
@@ -350,3 +350,4 @@ def forward(self, x):
 # for your environment, a proper approach is to first generate the curve to
 # figure out the best split size, and then use that split size to pipeline
 # inputs.
+#