Skip to content

Commit 5a196dd

Browse files
committed
Update README.md with latest, bump version to 0.4.8
1 parent ce6585f commit 5a196dd

File tree

2 files changed

+10
-1
lines changed

2 files changed

+10
-1
lines changed

README.md

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -23,6 +23,15 @@ I'm fortunate to be able to dedicate significant time and money of my own suppor
2323

2424
## What's New
2525

26+
### April 12, 2021
27+
* Add ECA-NFNet-L1 (slimmed down F1 w/ SiLU, 41M params) trained with this code. 84% top-1 @ 320x320. Trained at 256x256.
28+
* Add EfficientNet-V2S model (unverified model definition) weights. 83.3 top-1 @ 288x288. Only trained single res 224. Working on progressive training.
29+
* Add ByoaNet model definition (Bring-your-own-attention) w/ SelfAttention block and corresponding SA/SA-like modules and model defs
30+
* Lambda Networks - https://arxiv.org/abs/2102.08602
31+
* Bottleneck Transformers - https://arxiv.org/abs/2101.11605
32+
* Halo Nets - https://arxiv.org/abs/2103.12731
33+
* Adabelief optimizer contributed by Juntang Zhuang
34+
2635
### April 1, 2021
2736
* Add snazzy `benchmark.py` script for bulk `timm` model benchmarking of train and/or inference
2837
* Add Pooling-based Vision Transformer (PiT) models (from https://github.com/naver-ai/pit)

timm/version.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
__version__ = '0.4.7'
1+
__version__ = '0.4.8'

0 commit comments

Comments
 (0)