Unit tests for Vision

This issue fleshes out the full details and scope of the unit tests needed for torchvision.

There are very limited unit tests under test/ which dont cover the transform outputs themselves, but are limited to dimension and shape checks.

First, let's start with quantitative tests on known results.

We need to have a set of 10 test images, and then do each transformation of vision.transforms on these 10 images, and compare them pixel-wise with known results. We then compare the known results with the computed result from the transforms, and if they are within some threshold, we pass the test.

Some of the transforms such as Horizontal / Vertical flip can also have exact numerical unit-tests.

The test images:

• 2 monochrome images
• 2 3-channel images
• 2 4-channel PNG images with an Alpha component

Can find some on Wikipedia that are freely licensed.

The tests need to cover all transforms under: https://github.com/pytorch/vision#transforms

For similar testing, you can have a look at:

https://github.com/torch/image/blob/master/test/test.lua#L258-L646

Start by reading the existing tests under test/ and the transforms listed in the torchvision README. Review the referenced torch/image tests for comparison patterns, then define the freely licensed test-image set and expected results. Done means every vision.transforms transform has quantitative coverage, including exact checks where applicable.