You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+12Lines changed: 12 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -23,6 +23,17 @@ I'm fortunate to be able to dedicate significant time and money of my own suppor
23
23
24
24
## What's New
25
25
26
+
### May 13, 2022
27
+
* Official Swin-V2 models and weights added from (https://github.com/microsoft/Swin-Transformer). Cleaned up to support torchscript.
28
+
* 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.
29
+
* More Vision Transformer relative position / residual post-norm experiments w/ 512 dim
30
+
*`vit_relpos_small_patch16_224` - 81.5 @ 224, 82.5 @ 320 -- rel pos, layer scale, no class token, avg pool
31
+
*`vit_relpos_medium_patch16_rpn_224` - 82.3 @ 224, 83.1 @ 320 -- rel pos + res-post-norm, no class token, avg pool
32
+
*`vit_relpos_medium_patch16_224` - 82.5 @ 224, 83.3 @ 320 -- rel pos, layer scale, no class token, avg pool
33
+
*`vit_relpos_base_patch16_gapcls_224` - 82.8 @ 224, 83.9 @ 320 -- rel pos, layer scale, class token, avg pool (by mistake)
34
+
* 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)
35
+
* Add ViT relative position support for switching btw existing impl and some additions in official Swin-V2 impl for future trials
36
+
* Sequencer2D impl (https://arxiv.org/abs/2205.01972), added via PR from author (https://github.com/okojoalg)
26
37
27
38
### May 2, 2022
28
39
* 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
0 commit comments