@ -23,6 +23,17 @@ I'm fortunate to be able to dedicate significant time and money of my own suppor
## What's New
## What's New
### May 13, 2022
* Official Swin-V2 models and weights added from (https://github.com/microsoft/Swin-Transformer). Cleaned up to support torchscript.
* Some refactoring for existing `timm` Swin-V2-CR impl, will likely do a bit more to bring parts closer to official and decide whether to merge some aspects.
* More Vision Transformer relative position / residual post-norm experiments w/ 512 dim
* `vit_relpos_small_patch16_224` - 81.5 @ 224, 82.5 @ 320 -- rel pos, layer scale, no class token, avg pool
* `vit_relpos_medium_patch16_rpn_224` - 82.3 @ 224, 83.1 @ 320 -- rel pos + res-post-norm, no class token, avg pool
* `vit_relpos_medium_patch16_224` - 82.5 @ 224, 83.3 @ 320 -- rel pos, layer scale, no class token, avg pool
* `vit_relpos_base_patch16_gapcls_224` - 82.8 @ 224, 83.9 @ 320 -- rel pos, layer scale, class token, avg pool (by mistake)
* Bring 512 dim, 8-head 'medium' ViT model variant back to life (after using in a pre DeiT 'small' model for first ViT impl back in 2020)
* Add ViT relative position support for switching btw existing impl and some additions in official Swin-V2 impl for future trials
* Sequencer2D impl (https://arxiv.org/abs/2205.01972), added via PR from author (https://github.com/okojoalg)
### May 2, 2022
### May 2, 2022
* Vision Transformer experiments adding Relative Position (Swin-V2 log-coord) (`vision_transformer_relpos.py`) and Residual Post-Norm branches (from Swin-V2) (`vision_transformer*.py`)
* Vision Transformer experiments adding Relative Position (Swin-V2 log-coord) (`vision_transformer_relpos.py`) and Residual Post-Norm branches (from Swin-V2) (`vision_transformer*.py`)
@ -390,6 +401,7 @@ A full version of the list below with source links can be found in the [document