GitLab

This reverts commit 36849429.

This reverts commit 7a54c6be.

This reverts commit dd53c974.

This reverts commit c94ea5ff.

This reverts commit 30a5aa0f.

This reverts commit 3ce6c828.

This reverts commit f69298d4.

* load densenet tensors onto cpu

* fix docs for size param in random + center crop

* revert incorrect commit

Some links were not displaying properly

* added FashionMNIST dataset

* documentation

* fixed formatting

* fixed formatting

* DOC fixed typo in make_grid argument name

* DOC document "padding" make_grid argument

isinstance(padding, tuple) is added to the padding assertion to be able to pass a sequence.

* enable ~ expression in datasets

* fixed root in __init__ to self.root

Wrong order of dimensions In transforms.CenterCrop and transforms.RandomCrop:
Documentation says it should be (w, h), but it actually is (h, w).
Fixing docs to match the code

* Add documentation for transforms

* document and remove unused imports in mnist.py

* document lsun, mscoco datasets

* rest of the datasets documented

* Clean up the documentation in other functions

* Add links for datasets

* Add more documentation

* pep8 fix

Fixes #152

See https://github.com/python-pillow/Pillow/issues/835

changed a small mistake.

It can be enabled by calling torchvision.set_image_backend('accimage')

First dimension is batch size, channel is the second