[DOC] Adds Documentation for AutoAugmentation (#3529)

* add _all for autoaugment

* adds docs

* add docs, test locally

* refactored as per code review

docs/source/transforms.rst

@@ -57,6 +57,7 @@ Compositions of transforms
 
 .. autoclass:: Compose
 
+
 Transforms on PIL Image and torch.\*Tensor
 ------------------------------------------
 
@@ -156,6 +157,22 @@ Generic Transforms
     :members:
 
 
+AutoAugment Transforms
+----------------------
+
+`AutoAugment <https://arxiv.org/pdf/1805.09501.pdf>`_ is a common Data Augmentation technique that can improve the accuracy of Image Classification models.
+Though the data augmentation policies are directly linked to their trained dataset, empirical studies show that
+ImageNet policies provide significant improvements when applied to other datasets.
+In TorchVision we implemented 3 policies learned on the following datasets: ImageNet, CIFAR10 and SVHN.
+The new transform can be used standalone or mixed-and-matched with existing transforms:
+
+.. autoclass:: AutoAugmentPolicy
+    :members:
+
+.. autoclass:: AutoAugment
+    :members:
+
+
 Functional Transforms
 ---------------------
 

torchvision/transforms/autoaugment.py

@@ -7,9 +7,12 @@ from typing import List, Tuple, Optional
 
 from . import functional as F, InterpolationMode
 
+__all__ = ["AutoAugmentPolicy", "AutoAugment"]
+
 
 class AutoAugmentPolicy(Enum):
     """AutoAugment policies learned on different datasets.
+    Available policies are IMAGENET, CIFAR10 and SVHN.
     """
     IMAGENET = "imagenet"
     CIFAR10 = "cifar10"