Add Gather-Excite, Global Context, BAT, Non-Local attn modules and refactored all attn modules and factory for improved consistency. EfficientNet / MobileNetV3 backbones able to use a wider variety of attention modules.

Add non-local and BAT attention. Merge attn and self-attn factories into one. Add attention references to README. Add mlp 'mode' to ECA.

Able to use other attn layer in EfficientNet now. Create test ECA + GC B0 configs. Make ECA more configurable.

Bring EfficientNet SE layer in line with others, pull se_ratio outside of blocks. Allows swapping w/ other attn layers.

Throw in some FBNetV3 code I had lying around, some refactoring of SE reduction channel calcs for all EffNet archs.

Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.

Fix #661, move hardswish out of default args for LeViT. Enable native torch support for hardswish, hardsigmoid, mish if present.

LeVit, Visformer, RedNet/Involution models and layers

README: fix simple typos

Expand scope of testing for non-std vision transformer / mlp models. Some related cleanup and create fn cleanup for all vision transformer and mlp models. More CoaT weights.

Merge branch 'master' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-master