Merge branch 'main' into data-loading-guide

Author: divyanshk

beginner_source/basics/data_tutorial.py

@@ -48,22 +48,22 @@
 import torch
 from torch.utils.data import Dataset
 from torchvision import datasets
-from torchvision.transforms import ToTensor
+from torchvision.transforms import v2
 import matplotlib.pyplot as plt
 
 
 training_data = datasets.FashionMNIST(
     root="data",
     train=True,
     download=True,
-    transform=ToTensor()
+    transform=v2.Compose([v2.ToImage(), v2.ToDtype(torch.float32, scale=True)])
 )
 
 test_data = datasets.FashionMNIST(
     root="data",
     train=False,
     download=True,
-    transform=ToTensor()
+    transform=v2.Compose([v2.ToImage(), v2.ToDtype(torch.float32, scale=True)])
 )
 
 

beginner_source/basics/optimization_tutorial.py

@@ -28,20 +28,20 @@
 from torch import nn
 from torch.utils.data import DataLoader
 from torchvision import datasets
-from torchvision.transforms import ToTensor
+from torchvision.transforms import v2
 
 training_data = datasets.FashionMNIST(
     root="data",
     train=True,
     download=True,
-    transform=ToTensor()
+    transform=v2.Compose([v2.ToImage(), v2.ToDtype(torch.float32, scale=True)])
 )
 
 test_data = datasets.FashionMNIST(
     root="data",
     train=False,
     download=True,
-    transform=ToTensor()
+    transform=v2.Compose([v2.ToImage(), v2.ToDtype(torch.float32, scale=True)])
 )
 
 train_dataloader = DataLoader(training_data, batch_size=64)

beginner_source/basics/transforms_tutorial.py

@@ -23,42 +23,47 @@
 
 The FashionMNIST features are in PIL Image format, and the labels are integers.
 For training, we need the features as normalized tensors, and the labels as one-hot encoded tensors.
-To make these transformations, we use ``ToTensor`` and ``Lambda``.
+To make these transformations, we use the ``torchvision.transforms.v2`` API along with ``torch.nn.functional.one_hot``.
 """
 
 import torch
+import torch.nn.functional as F
 from torchvision import datasets
-from torchvision.transforms import ToTensor, Lambda
+from torchvision.transforms import v2
 
 ds = datasets.FashionMNIST(
     root="data",
     train=True,
     download=True,
-    transform=ToTensor(),
-    target_transform=Lambda(lambda y: torch.zeros(10, dtype=torch.float).scatter_(0, torch.tensor(y), value=1))
+    transform=v2.Compose([v2.ToImage(), v2.ToDtype(torch.float32, scale=True)]),
+    target_transform=v2.Lambda(
+        lambda y: F.one_hot(torch.tensor(y), num_classes=10).float()
+    ),
 )
 
 #################################################
-# ToTensor()
+# ToImage() and ToDtype()
 # -------------------------------
 #
-# `ToTensor <https://pytorch.org/vision/stable/transforms.html#torchvision.transforms.ToTensor>`_
-# converts a PIL image or NumPy ``ndarray`` into a ``FloatTensor``. and scales
-# the image's pixel intensity values in the range [0., 1.]
+# The ``torchvision.transforms.v2`` API replaces the legacy ``ToTensor`` transform with a two-step pipeline.
+# `v2.ToImage <https://pytorch.org/vision/stable/generated/torchvision.transforms.v2.ToImage.html>`_
+# converts a PIL image or NumPy ``ndarray`` into a ``torchvision.tv_tensors.Image`` tensor, and
+# `v2.ToDtype <https://pytorch.org/vision/stable/generated/torchvision.transforms.v2.ToDtype.html>`_
+# with ``scale=True`` casts it to ``float32`` and scales the pixel intensity values to the range [0., 1.].
 #
 
 ##############################################
 # Lambda Transforms
 # -------------------------------
 #
-# Lambda transforms apply any user-defined lambda function. Here, we define a function
-# to turn the integer into a one-hot encoded tensor.
-# It first creates a zero tensor of size 10 (the number of labels in our dataset) and calls
-# `scatter_ <https://pytorch.org/docs/stable/generated/torch.Tensor.scatter_.html>`_ which assigns a
-# ``value=1`` on the index as given by the label ``y``.
+# Lambda transforms apply any user-defined lambda function. Here, we use
+# `torch.nn.functional.one_hot <https://pytorch.org/docs/stable/generated/torch.nn.functional.one_hot.html>`_
+# to turn the integer label into a one-hot encoded tensor of size 10 (the number of labels in our dataset),
+# then cast it to ``float`` to match the expected dtype.
 
-target_transform = Lambda(lambda y: torch.zeros(
-    10, dtype=torch.float).scatter_(dim=0, index=torch.tensor(y), value=1))
+target_transform = v2.Lambda(
+    lambda y: F.one_hot(torch.tensor(y), num_classes=10).float()
+)
 
 ######################################################################
 # --------------
@@ -67,4 +72,5 @@
 #################################################################
 # Further Reading
 # ~~~~~~~~~~~~~~~~~
-# - `torchvision.transforms API <https://pytorch.org/vision/stable/transforms.html>`_
+# - `Getting started with transforms v2 <https://pytorch.org/vision/stable/auto_examples/transforms/plot_transforms_getting_started.html>`_
+# - `torchvision.transforms.v2 API <https://pytorch.org/vision/stable/transforms.html#v2-api-reference-recommended>`_