Skip to content

Commit 497be83

Browse files
committed
Update README and version
1 parent 0d33127 commit 497be83

File tree

2 files changed

+20
-2
lines changed

2 files changed

+20
-2
lines changed

README.md

Lines changed: 19 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,6 +24,24 @@ And a big thanks to all GitHub sponsors who helped with some of my costs before
2424
* ❗Updates after Oct 10, 2022 are available in 0.8.x pre-releases (`pip install --pre timm`) or cloning main❗
2525
* Stable releases are 0.6.x and available by normal pip install or clone from [0.6.x](https://github.com/rwightman/pytorch-image-models/tree/0.6.x) branch.
2626

27+
### Feb 7, 2023
28+
* New inference benchmark numbers added in [results](results/) folder.
29+
* Add convnext LAION CLIP trained weights and initial set of in1k fine-tunes
30+
* `convnext_base.clip_laion2b_augreg_ft_in1k` - 86.2% @ 256x256
31+
* `convnext_base.clip_laiona_augreg_ft_in1k_384` - 86.5% @ 384x384
32+
* `convnext_large_mlp.clip_laion2b_augreg_ft_in1k` - 87.3% @ 256x256
33+
* `convnext_large_mlp.` - 87.9% @ 384x384
34+
* Add DaViT models. Supports `features_only=True`. Adapted from https://github.com/dingmyu/davit by [Fredo](https://github.com/fffffgggg54).
35+
* Use a common NormMlpClassifierHead across MaxViT, ConvNeXt, DaViT
36+
* Add EfficientFormer-V2 model, update EfficientFormer, and refactor LeViT (closely related architectures). Weights on HF hub.
37+
* New EfficientFormer-V2 arch, significant refactor from original at (https://github.com/snap-research/EfficientFormer). Supports `features_only=True`.
38+
* Minor updates to EfficientFormer.
39+
* Refactor LeViT models to stages, add `features_only=True` support to new `conv` variants, weight remap required.
40+
* Move ImageNet meta-data (synsets, indices) from `/results` to `timm/data/_info`.
41+
* Add ImageNetInfo / DatasetInfo classes to provide labelling for various ImageNet classifier layouts in `timm`
42+
* Update `inference.py` to use, try: `python inference.py /folder/to/images --model convnext_small.in12k --label-type detail --topk 5`
43+
* Ready for 0.8.10 pypi pre-release (final testing).
44+
2745
### Jan 20, 2023
2846
* Add two convnext 12k -> 1k fine-tunes at 384x384
2947
* `convnext_tiny.in12k_ft_in1k_384` - 85.1 @ 384
@@ -571,7 +589,7 @@ Several (less common) features that I often utilize in my projects are included.
571589

572590
## Results
573591

574-
Model validation results can be found in the [documentation](https://rwightman.github.io/pytorch-image-models/results/) and in the [results tables](results/README.md)
592+
Model validation results can be found in the [results tables](results/README.md)
575593

576594
## Getting Started (Documentation)
577595

timm/version.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
__version__ = '0.8.9dev0'
1+
__version__ = '0.8.10dev0'

0 commit comments

Comments
 (0)