## Motivation
We are going to use a new blob account to store the checkpoints.
## Modification
Modify the azure blob storage URLs for BEiT checkpoints.
* remove dtype kwarg from .to() calls in EvoNorm as it messed up script + trace combo
* BatchNormAct2d always uses custom forward (cut & paste from original) instead of super().forward. Fixes#1176
* BlurPool groups==channels, no need to use input.dim[1]
* weight compat break, activate norm3 for final block of final stage (equivalent to pre-head norm, but while still in BLC shape)
* remove fold/unfold for TPU compat, add commented out roll code for TPU
* add option for end of stage norm in all stages
* allow weight_init to be selected between pytorch default inits and xavier / moco style vit variant
* 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
* reformat and change some naming so closer to existing timm vision transformers
* remove typing that wasn't adding clarity (or causing torchscript issues)
* support non-square windows
* auto window size adjust from image size
* post-norm + main-branch no
Ross Wightman
Ross Wightman
okojoalg
jjsjann123
Li Dong
SeeFun
Christoph Reich