Convert :: to code-block directive (#2737)

* Convert `::` to code-block directive

Author: svekars

advanced_source/neural_style_tutorial.py

@@ -87,7 +87,7 @@
 # to 255 tensor images. 
 #
 #
-# .. Note::
+# .. note::
 #     Here are links to download the images required to run the tutorial:
 #     `picasso.jpg <https://pytorch.org/tutorials/_static/img/neural-style/picasso.jpg>`__ and
 #     `dancing.jpg <https://pytorch.org/tutorials/_static/img/neural-style/dancing.jpg>`__.
@@ -183,7 +183,7 @@ def forward(self, input):
         return input
 
 ######################################################################
-# .. Note::
+# .. note::
 #    **Important detail**: although this module is named ``ContentLoss``, it
 #    is not a true PyTorch Loss function. If you want to define your content
 #    loss as a PyTorch Loss function, you have to create a PyTorch autograd function 
@@ -372,7 +372,7 @@ def get_style_model_and_losses(cnn, normalization_mean, normalization_std,
 input_img = content_img.clone()
 # if you want to use white noise by using the following code:
 #
-# ::
+# .. code-block:: python
 #
 #    input_img = torch.randn(content_img.data.size())
 

beginner_source/blitz/neural_networks_tutorial.py

@@ -161,7 +161,7 @@ def forward(self, x):
 # ``.grad_fn`` attribute, you will see a graph of computations that looks
 # like this:
 #
-# ::
+# .. code-block:: sh
 #
 #     input -> conv2d -> relu -> maxpool2d -> conv2d -> relu -> maxpool2d
 #           -> flatten -> linear -> relu -> linear -> relu -> linear
@@ -253,7 +253,7 @@ def forward(self, x):
 
 
 ###############################################################
-# .. Note::
+# .. note::
 #
 #       Observe how gradient buffers had to be manually set to zero using
 #       ``optimizer.zero_grad()``. This is because gradients are accumulated

beginner_source/data_loading_tutorial.py

@@ -50,9 +50,9 @@
 #     estimation <https://blog.dlib.net/2014/08/real-time-face-pose-estimation.html>`__
 #     on a few images from imagenet tagged as 'face'.
 #
-# Dataset comes with a csv file with annotations which looks like this:
+# Dataset comes with a ``.csv`` file with annotations which looks like this:
 #
-# ::
+# .. code-block:: sh
 #
 #     image_name,part_0_x,part_0_y,part_1_x,part_1_y,part_2_x, ... ,part_67_x,part_67_y
 #     0805personali01.jpg,27,83,27,98, ... 84,134
@@ -196,7 +196,7 @@ def __getitem__(self, idx):
 # called. For this, we just need to implement ``__call__`` method and
 # if required, ``__init__`` method. We can then use a transform like this:
 #
-# ::
+# .. code-block:: python
 #
 #     tsfm = Transform(params)
 #     transformed_sample = tsfm(sample)
@@ -421,7 +421,9 @@ def show_landmarks_batch(sample_batched):
 # and dataloader. ``torchvision`` package provides some common datasets and
 # transforms. You might not even have to write custom classes. One of the
 # more generic datasets available in torchvision is ``ImageFolder``.
-# It assumes that images are organized in the following way: ::
+# It assumes that images are organized in the following way:
+#
+# .. code-block:: sh
 #
 #     root/ants/xxx.png
 #     root/ants/xxy.jpeg
@@ -435,7 +437,9 @@ def show_landmarks_batch(sample_batched):
 #
 # where 'ants', 'bees' etc. are class labels. Similarly generic transforms
 # which operate on ``PIL.Image`` like  ``RandomHorizontalFlip``, ``Scale``,
-# are also available. You can use these to write a dataloader like this: ::
+# are also available. You can use these to write a dataloader like this:
+#
+# .. code-block:: pytorch
 #
 #    import torch
 #    from torchvision import transforms, datasets

beginner_source/dcgan_faces_tutorial.py

@@ -226,7 +226,7 @@
 # the ``celeba`` directory you just created. The resulting directory
 # structure should be:
 # 
-# ::
+# .. code-block:: sh
 # 
 #    /path/to/celeba
 #        -> img_align_celeba  

beginner_source/hyperparameter_tuning_tutorial.py

@@ -462,7 +462,7 @@ def main(num_samples=10, max_num_epochs=10, gpus_per_trial=2):
 ######################################################################
 # If you run the code, an example output could look like this:
 #
-# ::
+# .. code-block:: sh
 #
 #     Number of trials: 10/10 (10 TERMINATED)
 #     +-----+--------------+------+------+-------------+--------+---------+------------+

beginner_source/introyt/autogradyt_tutorial.py

@@ -213,7 +213,7 @@
 #########################################################################
 # Recall the computation steps we took to get here:
 # 
-# ::
+# .. code-block:: python
 # 
 #    a = torch.linspace(0., 2. * math.pi, steps=25, requires_grad=True)
 #    b = torch.sin(a)
@@ -456,10 +456,10 @@ def add_tensors2(x, y):
 # .. note::
 #     The following code cell throws a runtime error. This is expected.
 # 
-# ::
+#    .. code-block:: python
 #
-#    a = torch.linspace(0., 2. * math.pi, steps=25, requires_grad=True)
-#    torch.sin_(a)
+#       a = torch.linspace(0., 2. * math.pi, steps=25, requires_grad=True)
+#       torch.sin_(a)
 #
 
 #########################################################################

beginner_source/introyt/captumyt.py

@@ -109,11 +109,15 @@
 To install Captum in an Anaconda or pip virtual environment, use the
 appropriate command for your environment below:
 
-With ``conda``::
+With ``conda``:
+
+.. code-block:: sh
 
     conda install pytorch torchvision captum flask-compress matplotlib=3.3.4 -c pytorch
 
-With ``pip``::
+With ``pip``:
+
+.. code-block:: sh
 
     pip install torch torchvision captum matplotlib==3.3.4 Flask-Compress
 

beginner_source/introyt/introyt1_tutorial.py

@@ -580,7 +580,7 @@ def forward(self, x):
 # 
 # **When you run the cell above,** you should see something like this:
 # 
-# ::
+# .. code-block:: sh
 # 
 #    [1,  2000] loss: 2.235
 #    [1,  4000] loss: 1.940

beginner_source/introyt/tensorboardyt_tutorial.py

@@ -24,12 +24,16 @@
 To run this tutorial, you’ll need to install PyTorch, TorchVision,
 Matplotlib, and TensorBoard.
 
-With ``conda``::
+With ``conda``:
+
+.. code-block:: sh
 
     conda install pytorch torchvision -c pytorch
     conda install matplotlib tensorboard
 
-With ``pip``::
+With ``pip``:
+
+.. code-block:: sh
 
     pip install torch torchvision matplotlib tensorboard
 

beginner_source/introyt/tensors_deeper_tutorial.py

@@ -292,14 +292,14 @@
 # binary operation on tensors if dissimilar shape?
 # 
 # .. note::
-#      The following cell throws a run-time error. This is intentional.
+#    The following cell throws a run-time error. This is intentional.
 #
-# ::
+#    .. code-block:: sh
 #
-#    a = torch.rand(2, 3)
-#    b = torch.rand(3, 2)
+#       a = torch.rand(2, 3)
+#       b = torch.rand(3, 2)
 #
-#    print(a * b)
+#       print(a * b)
 #
 
 
@@ -390,17 +390,17 @@
 # Here are some examples of attempts at broadcasting that will fail:
 # 
 # .. note::
-#       The following cell throws a run-time error. This is intentional.
+#    The following cell throws a run-time error. This is intentional.
 #
-# ::
+#    .. code-block:: python
 #
-#    a =     torch.ones(4, 3, 2)
+#       a =     torch.ones(4, 3, 2)
 #
-#    b = a * torch.rand(4, 3)    # dimensions must match last-to-first
+#       b = a * torch.rand(4, 3)    # dimensions must match last-to-first
 #
-#    c = a * torch.rand(   2, 3) # both 3rd & 2nd dims different
+#       c = a * torch.rand(   2, 3) # both 3rd & 2nd dims different
 #
-#    d = a * torch.rand((0, ))   # can't broadcast with an empty tensor
+#       d = a * torch.rand((0, ))   # can't broadcast with an empty tensor
 #
 
 
@@ -729,7 +729,7 @@
 # following code will throw a runtime error, regardless of whether you
 # have a GPU device available:
 # 
-# ::
+# .. code-block:: python
 # 
 #    x = torch.rand(2, 2)
 #    y = torch.rand(2, 2, device='gpu')
@@ -820,9 +820,9 @@
 # Another place you might use ``unsqueeze()`` is to ease broadcasting.
 # Recall the example above where we had the following code:
 # 
-# ::
+# .. code-block:: python
 # 
-#    a =     torch.ones(4, 3, 2)
+#    a = torch.ones(4, 3, 2)
 # 
 #    c = a * torch.rand(   3, 1) # 3rd dim = 1, 2nd dim identical to a
 #    print(c)

beginner_source/nn_tutorial.py

@@ -328,7 +328,7 @@ def forward(self, xb):
 # Previously for our training loop we had to update the values for each parameter
 # by name, and manually zero out the grads for each parameter separately, like this:
 #
-# ::
+# .. code-block:: python
 #
 #    with torch.no_grad():
 #        weights -= weights.grad * lr
@@ -342,7 +342,7 @@ def forward(self, xb):
 # and less prone to the error of forgetting some of our parameters, particularly
 # if we had a more complicated model:
 #
-# ::
+# .. code-block:: python
 #
 #    with torch.no_grad():
 #        for p in model.parameters(): p -= p.grad * lr
@@ -418,15 +418,15 @@ def forward(self, xb):
 #
 # This will let us replace our previous manually coded optimization step:
 #
-# ::
+# .. code-block:: python
 #
 #    with torch.no_grad():
 #        for p in model.parameters(): p -= p.grad * lr
 #        model.zero_grad()
 #
 # and instead use just:
 #
-# ::
+# .. code-block:: python
 #
 #    opt.step()
 #    opt.zero_grad()
@@ -490,15 +490,15 @@ def get_model():
 ###############################################################################
 # Previously, we had to iterate through minibatches of ``x`` and ``y`` values separately:
 #
-# ::
+# .. code-block:: python
 #
 #    xb = x_train[start_i:end_i]
 #    yb = y_train[start_i:end_i]
 #
 #
 # Now, we can do these two steps together:
 #
-# ::
+# .. code-block:: python
 #
 #    xb,yb = train_ds[i*bs : i*bs+bs]
 #
@@ -534,15 +534,15 @@ def get_model():
 ###############################################################################
 # Previously, our loop iterated over batches ``(xb, yb)`` like this:
 #
-# ::
+# .. code-block:: python
 #
 #    for i in range((n-1)//bs + 1):
 #        xb,yb = train_ds[i*bs : i*bs+bs]
 #        pred = model(xb)
 #
 # Now, our loop is much cleaner, as ``(xb, yb)`` are loaded automatically from the data loader:
 #
-# ::
+# .. code-block:: python
 #
 #    for xb,yb in train_dl:
 #        pred = model(xb)

beginner_source/profiler.py

@@ -82,7 +82,7 @@ def forward(self, input, mask):
 # ``profiler.profile`` context manager. The ``with_stack=True`` parameter appends the
 # file and line number of the operation in the trace.
 #
-# .. WARNING::
+# .. warning::
 #     ``with_stack=True`` incurs an additional overhead, and is better suited for investigating code.
 #     Remember to remove it if you are benchmarking performance.
 #
@@ -115,7 +115,7 @@ def forward(self, input, mask):
 # `docs <https://pytorch.org/docs/stable/autograd.html#profiler>`__ for
 # valid sorting keys).
 #
-# .. Note::
+# .. note::
 #   When running profiler in a notebook, you might see entries like ``<ipython-input-18-193a910735e8>(13): forward``
 #   instead of filenames in the stacktrace. These correspond to ``<notebook-cell>(line number): calling-function``.
 

beginner_source/saving_loading_models.py

@@ -115,7 +115,7 @@
 #
 # **Output:**
 #
-# ::
+# .. code-block:: sh
 #
 #    Model's state_dict:
 #    conv1.weight     torch.Size([6, 3, 5, 5])
@@ -175,15 +175,15 @@
 # normalization layers to evaluation mode before running inference.
 # Failing to do this will yield inconsistent inference results.
 #
-# .. Note ::
+# .. note::
 #
 #    Notice that the ``load_state_dict()`` function takes a dictionary
 #    object, NOT a path to a saved object. This means that you must
 #    deserialize the saved *state_dict* before you pass it to the
 #    ``load_state_dict()`` function. For example, you CANNOT load using
 #    ``model.load_state_dict(PATH)``.
 #
-# .. Note ::
+# .. note::
 #    
 #    If you only plan to keep the best performing model (according to the 
 #    acquired validation loss), don't forget that ``best_model_state = model.state_dict()``

beginner_source/text_sentiment_ngrams_tutorial.py

@@ -37,7 +37,7 @@
 train_iter = iter(AG_NEWS(split="train"))
 
 ######################################################################
-# ::
+# .. code-block:: sh
 #
 #     next(train_iter)
 #     >>> (3, "Fears for T N pension after talks Unions representing workers at Turner
@@ -88,7 +88,7 @@ def yield_tokens(data_iter):
 ######################################################################
 # The vocabulary block converts a list of tokens into integers.
 #
-# ::
+# .. code-block:: sh
 #
 #     vocab(['here', 'is', 'an', 'example'])
 #     >>> [475, 21, 30, 5297]
@@ -102,7 +102,7 @@ def yield_tokens(data_iter):
 ######################################################################
 # The text pipeline converts a text string into a list of integers based on the lookup table defined in the vocabulary. The label pipeline converts the label into integers. For example,
 #
-# ::
+# .. code-block:: sh
 #
 #     text_pipeline('here is the an example')
 #     >>> [475, 21, 2, 30, 5297]
@@ -188,7 +188,7 @@ def forward(self, text, offsets):
 #
 # The ``AG_NEWS`` dataset has four labels and therefore the number of classes is four.
 #
-# ::
+# .. code-block:: sh
 #
 #    1 : World
 #    2 : Sports