* All models updated with revised foward_features / forward_head interface
* Vision transformer and MLP based models consistently output sequence from forward_features (pooling or token selection considered part of 'head')
* WIP param grouping interface to allow consistent grouping of parameters for layer-wise decay across all model types
* Add gradient checkpointing support to a significant % of models, especially popular architectures
* Formatting and interface consistency improvements across models
* layer-wise LR decay impl part of optimizer factory w/ scale support in scheduler
* Poolformer and Volo architectures added
* ConvBnAct layer renamed -> ConvNormAct and ConvNormActAa for anti-aliased
* Significant update to EfficientNet and MobileNetV3 arch to support NormAct layers and grouped conv (as alternative to depthwise)
* Update RegNet to add Z variant
* Add Pre variant of XceptionAligned that works with NormAct layers
* EvoNorm matches bits_and_tpu branch for merge
* Add eca_nfnet_l2 weights, 84.7 @ 384x384
* All 'non-std' (ie transformer / mlp) models have classifier / default_cfg test added
* Fix#694 reset_classifer / num_features / forward_features / num_classes=0 consistency for transformer / mlp models
* Add direct loading of npz to vision transformer (pure transformer so far, hybrid to come)
* Rename vit_deit* to deit_*
* Remove some deprecated vit hybrid model defs
* Clean up classifier flatten for conv classifiers and unusual cases (mobilenetv3/ghostnet)
* Remove explicit model fns for levit conv, just pass in arg
* Add ResNet-RS models
* Only include resnet-rs changes
* remove whitespace diff
* EOF newline
* Update time
* increase time
* Add first conv
* Try running only resnetv2_101x1_bitm on Linux runner
* Add to exclude filter
* Run test_model_forward_features for all
* Add to exclude ftrs
* back to defaults
* only run test_forward_features
* run all tests
* Run all tests
* Add bigger resnetrs to model filters to fix Github CLI
* Remove resnetv2_101x1_bitm from exclude feat features
* Remove hardcoded values
* Make sure reduction ratio in resnetrs is 0.25
* There is no bias in replaced maxpool so remove it
* improve consistency of model creation helper fns
* add comments to some of the model helpers
* support passing external default_cfgs so they can be sourced from hub
* stage creation + make_layer moved to separate fn with more sensible dilation/output_stride calc
* drop path rate decay easy to impl with refactored block creation loops
* fix dilation + blur pool combo
Fredo Guan