pytorch-image-models

mirror of https://github.com/huggingface/pytorch-image-models.git synced 2025-06-03 15:01:08 +08:00

History

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

2022-03-21 14:50:28 -07:00

data

Significant model refactor and additions:

2022-02-28 13:56:23 -08:00

loss

Update binary cross ent impl to use thresholding as an option (convert soft targets from mixup/cutmix to 0, 1)

2021-09-23 15:45:39 -07:00

models

Update SwinTransformerV2Cr post-merge, update with grad checkpointing / grad matcher

2022-03-21 14:50:28 -07:00

optim

Fix bug introduced in non layer_decay weight_decay application. Remove debug print, fix arg desc.