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

EfficientNetV2 official impl w/ weights ported from TF. Cleanup/refactor of related EfficientNet classes and models.

Layer refactoring continues, ResNet downsample rewrite for proper dilation in 3x3 and avg_pool cases
* select_conv2d -> create_conv2d
* added create_attn to create attention module from string/bool/module
* factor padding helpers into own file, use in both conv2d_same and avg_pool2d_same
* add some more test eca resnet variants
* minor tweaks, naming, comments, consistency