more formatting, editing, etc

beginner_source/quickstart/autograd_tutorial.py

@@ -234,10 +234,11 @@
 
 ##################################################################
 # More help with the Pytorch Quickstart
-# ----------------------
-#| `Tensors <quickstart/tensor_tutorial.html>`_
+# -----------------
+#
+#| `Tensors <tensor_tutorial.html>`_
 #| `DataSets and DataLoaders <data_quickstart_tutorial.html>`_
 #| `Transformations <transforms_tutorial.html>`_
 #| `Build Model <build_model_tutorial.html>`_
 #| `Optimization Loop <optimization_tutorial.html>`_
-#| `AutoGrad <autograd_tutorial.html>`_
+#| `AutoGrad <autograd_tutorial.html>`_

beginner_source/quickstart/build_model_tutorial.py

@@ -1,19 +1,29 @@
 """
 Build Model Tutorial
 =======================================
+"""
 
-The data has been loaded and transformed we can now build the model. We will leverage `torch.nn <https://pytorch.org/docs/stable/nn.html>`_ predefined layers that Pytorch has that can both simplify our code, and  make it faster.
-
-In the below example, for our FashionMNIT image dataset, we are using a `Sequential` container from class `torch.nn.Sequential <https://pytorch.org/docs/stable/generated/torch.nn.Sequential.html>`_ that allows us to define the model layers inline. The neural network modules layers will be added to it in the order they are passed in.
-
-Another way this model could be bulid is with a class using `nn.Module <https://pytorch.org/docs/stable/generated/torch.nn.Module.html)>`_
+###############################################
+# The data has been loaded and transformed we can now build the model. 
+# We will leverage `torch.nn <https://pytorch.org/docs/stable/nn.html>`_ 
+# predefined layers that Pytorch has that can both simplify our code, and  make it faster.
+# 
+# In the below example, for our FashionMNIT image dataset, we are using a `Sequential` 
+# container from class `torch.nn.# Sequential <https://pytorch.org/docs/stable/generated/torch.nn.Sequential.html>`_ 
+# that allows us to define the model # layers inline. 
+# The neural network modules layers will be added to it in the order they are passed in.
+# 
+# Another way this model could be bulid is with a class 
+# using `nn.Module <https://pytorch.org/docs/stable/generated/torch.nn.Module.html)>`_
+#
+# We will break down the model below.
+#
 
-We will break down the model below.
-"""
 ########################################## 
 # Inline nn.Sequential Example:
 # ----------------------------
 #
+
 import os
 import torch
 import torch.nn as nn
@@ -139,10 +149,11 @@ def forward(self, x):
 
 ##################################################################
 # More help with the Pytorch Quickstart
-# -------------------------
+# -----------------
+#
 #| `Tensors <tensor_tutorial.html>`_
 #| `DataSets and DataLoaders <data_quickstart_tutorial.html>`_
 #| `Transformations <transforms_tutorial.html>`_
 #| `Build Model <build_model_tutorial.html>`_
 #| `Optimization Loop <optimization_tutorial.html>`_
-#| `AutoGrad <autograd_tutorial.html>`_
+#| `AutoGrad <autograd_tutorial.html>`_

beginner_source/quickstart/data_quickstart_tutorial.py

@@ -12,7 +12,7 @@
 
 ###############################################################
 # .. figure:: /_static/img/quickstart/typesofdata.png
-#    :alt:
+#    :alt: typesofdata
 # 
 
 ############################################################
@@ -59,7 +59,7 @@
 
 #################################################################
 # .. figure:: /_static/img/quickstart/fashion_mnist.png
-#    :alt:
+#    :alt: fashion_mnist
 #
 
 #################################################################

beginner_source/quickstart/optimization_tutorial.py

@@ -104,11 +104,12 @@
 
 
 ##################################################################
-# More help with the PyTorch Quickstart
+# More help with the Pytorch Quickstart
 # -----------------
-#| `Tensors <quickstart/tensor_tutorial.html>`_
+#
+#| `Tensors <tensor_tutorial.html>`_
 #| `DataSets and DataLoaders <data_quickstart_tutorial.html>`_
 #| `Transformations <transforms_tutorial.html>`_
 #| `Build Model <build_model_tutorial.html>`_
 #| `Optimization Loop <optimization_tutorial.html>`_
-#| `AutoGrad <autograd_tutorial.html>`_
+#| `AutoGrad <autograd_tutorial.html>`_

beginner_source/quickstart/tensor_tutorial.py

@@ -250,11 +250,12 @@
 
 
 ##################################################################
-# More help with the PyTorch Quickstart
-# ----------------------------------------
-# | `Tensors <tensor_tutorial.html>`_
-# | `DataSets and DataLoaders <data_quickstart_tutorial.html>`_
-# | `Transformations <transforms_tutorial.html>`_
-# | `Build Model <build_model_tutorial.html>`_
-# | `Optimization Loop <optimization_tutorial.html>`_
-# | `AutoGrad <autograd_quickstart_tutorial.html>`_
+# More help with the Pytorch Quickstart
+# -----------------
+#
+#| `Tensors <tensor_tutorial.html>`_
+#| `DataSets and DataLoaders <data_quickstart_tutorial.html>`_
+#| `Transformations <transforms_tutorial.html>`_
+#| `Build Model <build_model_tutorial.html>`_
+#| `Optimization Loop <optimization_tutorial.html>`_
+#| `AutoGrad <autograd_tutorial.html>`_

beginner_source/quickstart/transforms_tutorial.py

@@ -58,7 +58,7 @@
 # The `transforms.compose` allows us to string together different steps of transformations in a sequential order. This allows us to add an array of transforms for both the features and labels when preparing our data for training.
 #
 # *ToTensor()* 
-#For the feature transforms we have an array of transforms to process our image data for training. The first transform in the array is `transforms.ToTensor()` this is from class [torchvision.transforms.ToTensor](https://pytorch.org/docs/stable/torchvision/transforms.html#torchvision.transforms.ToTensor). We need to take our images and turn them into a tensor. (To learn more about Tensors check out [this]() resource.) The ToTensor() transformation is doing more than converting our image into a tensor. Its also normalizing our data for us by scaling the images to be between 0 and 1.
+# For the feature transforms we have an array of transforms to process our image data for training. The first transform in the array is `transforms.ToTensor()` this is from class [torchvision.transforms.ToTensor](https://pytorch.org/docs/stable/torchvision/transforms.html#torchvision.transforms.ToTensor). We need to take our images and turn them into a tensor. (To learn more about Tensors check out [this]() resource.) The ToTensor() transformation is doing more than converting our image into a tensor. Its also normalizing our data for us by scaling the images to be between 0 and 1.
 #
 #
 # ..note: ToTensor only normalized image data that is in PIL mode of (L, LA, P, I, F, RGB, YCbCr, RGBA, CMYK, 1) or if the numpy.ndarray has dtype = np.uint8. In the other cases, tensors are returned without scaling.
@@ -71,7 +71,7 @@
 # Target_Transform: Labels
 # -------------------------------
 #
-#Example:
+# Example:
 #
 
 target_transform= transforms.Lambda(lambda y: torch.zeros(10, dtype=torchfloat).scatter_(dim=0, index=torchtensor(y), value=1))

beginner_source/quickstart_tutorial.py

@@ -16,7 +16,7 @@
 # To see more examples and details of how to work with Tensors, Datasets, DataLoaders and Transforms in Pytoch with this example checkout these resources:
 #  - `DataSet and DataLoader <quickstart/data_quickstart_tutorial.html>`_
 #  - `Tensors <quickstart/tensor_tutorial.html>`_
-#  - `Transformations <quickstart/transforms_tutorial.html>`_
+#  - `Transforms <quickstart/transforms_tutorial.html>`_
 
 import torch
 import torch.nn as nn
@@ -147,7 +147,7 @@ def test(dataloader, model):
 # Saving Models
 # -------------
 # 
-# PyTorch has different ways you can save your model. One was is to serialize the internal model state to a file. Another would be to use the built-in `ONNX <https://github.com/onnx/tutorials>`_ support.
+# PyTorch has different ways you can save your model. One way is to serialize the internal model state to a file. Another would be to use the built-in `ONNX <https://github.com/onnx/tutorials>`_ support.
 
 # Saving PyTorch Model Dictionary
 torch.save(model.state_dict(), 'model.pth')