You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Ross Wightman fe457c1996 Update SwinTransformerV2Cr post-merge, update with grad checkpointing / grad matcher ... * 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		2 years ago
..
data	Significant model refactor and additions:	2 years ago
loss	Update binary cross ent impl to use thresholding as an option (convert soft targets from mixup/cutmix to 0, 1)	3 years ago
models	Update SwinTransformerV2Cr post-merge, update with grad checkpointing / grad matcher	2 years ago
optim	Fix bug introduced in non layer_decay weight_decay application. Remove debug print, fix arg desc.	2 years ago
scheduler	Merge remote-tracking branch 'origin/master' into norm_norm_norm	2 years ago
utils	Add --fuser arg to train/validate/benchmark scripts to select jit fuser type	2 years ago
__init__.py	Transitioning default_cfg -> pretrained_cfg. Improving handling of pretrained_cfg source (HF-Hub, files, timm config, etc). Checkpoint handling tweaks.	2 years ago
version.py	Version to 0.6.0, possible interface incompatibilities vs 0.5.x	2 years ago