Compatibility with recent versions of standard BatchNorm, update comm…

…ents, code clean-up

Summary:
This updates ABN, InPlaceABN and InPlaceABNSync to have feature parity with recent versions of Pytorch's BatchNormNd layers:
* Add a `track_running_stats` parameter to enable / disable computation of running statistics independently from the layer's `training` state
* Add a `num_batches_tracked` buffer, and allow passing `momentum=None` to support cumulative moving average for tracking running stats instead of exponential moving average
* As a side-effect, now support loading parameters from standard BatchNorm without work-arounds. Still, if the loaded parameters contain negative `weight` elements the output will differ compared to standard BatchNorm

Additional changes:
* **Fix** backward pass in `eval` mode: it was not properly accounting for the activation function
* Refactor library code to follow more sensible formatting standards
* Add type annotations
* Improve docstrings
* Update installation instructions, pointing to the PyPI package

Reviewed By: pkontschieder, acolovic

Differential Revision: D23475677

fbshipit-source-id: 98b9d881e209b16232dd9719cf235add44aa5291

Changes for Pytorch 1.5.0

Compatibility with Pytorch 1.4, fix AT_CHECK warnings

Better fix to the tensor overwriting issue using less temp memory

Avoid overwriting y and dy in the backward pass

Update README to reference latest release

Fixed wrong references to pytorch 1.1, added note about Linux and CUDA

Fix compilation for systems that have CUDA sdk but no CUDA devices

Add proper support for CPU-only Pytorch

Support loading state dicts from post-Pytorch 1.0 standard BN models