mirrors
/
pytorch-image-models
mirror of https://github.com/huggingface/pytorch-image-models.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Add tiny/small in12k pretrained and fine-tuned ConvNeXt models

pull/1633/head v0.8.6dev0
Ross Wightman 2023-01-11 14:50:39 -08:00
parent 01aea8c1bf
commit a2c14c2064
2 changed files with 18 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -24,6 +24,12 @@ And a big thanks to all GitHub sponsors who helped with some of my costs before
* ❗Updates after Oct 10, 2022 are available in 0.8.x pre-releases (`pip install --pre timm`) or cloning main❗ * ❗Updates after Oct 10, 2022 are available in 0.8.x pre-releases (`pip install --pre timm`) or cloning main❗
* 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. * 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.
### Jan 11, 2023
* Update ConvNeXt ImageNet-12k pretrain series w/ two new fine-tuned weights (and pre FT `.in12k` tags)
* `convnext_nano.in12k_ft_in1k` - 82.3 @ 224, 82.9 @ 288 (previously released)
* `convnext_tiny.in12k_ft_in1k` - 84.2 @ 224, 84.5 @ 288
* `convnext_small.in12k_ft_in1k` - 85.2 @ 224, 85.3 @ 288
### Jan 6, 2023 ### Jan 6, 2023
* Finally got around to adding `--model-kwargs` and `--opt-kwargs` to scripts to pass through rare args directly to model classes from cmd line * Finally got around to adding `--model-kwargs` and `--opt-kwargs` to scripts to pass through rare args directly to model classes from cmd line
* `train.py /imagenet --model resnet50 --amp --model-kwargs output_stride=16 act_layer=silu` * `train.py /imagenet --model resnet50 --amp --model-kwargs output_stride=16 act_layer=silu`

12
timm/models/convnext.py
View File

@ -478,10 +478,22 @@ default_cfgs = generate_default_cfgs({
url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-rsb-weights/convnext_tiny_hnf_a2h-ab7e9df2.pth', url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-rsb-weights/convnext_tiny_hnf_a2h-ab7e9df2.pth',
hf_hub_id='timm/', hf_hub_id='timm/',
crop_pct=0.95, test_input_size=(3, 288, 288), test_crop_pct=1.0), crop_pct=0.95, test_input_size=(3, 288, 288), test_crop_pct=1.0),
'convnext_tiny.in12k_ft_in1k': _cfg(
hf_hub_id='timm/',
crop_pct=0.95, test_input_size=(3, 288, 288), test_crop_pct=1.0),
'convnext_small.in12k_ft_in1k': _cfg(
hf_hub_id='timm/',
crop_pct=0.95, test_input_size=(3, 288, 288), test_crop_pct=1.0),
'convnext_nano.in12k': _cfg( 'convnext_nano.in12k': _cfg(
hf_hub_id='timm/', hf_hub_id='timm/',
crop_pct=0.95, num_classes=11821), crop_pct=0.95, num_classes=11821),
'convnext_tiny.in12k': _cfg(
hf_hub_id='timm/',
crop_pct=0.95, num_classes=11821),
'convnext_small.in12k': _cfg(
hf_hub_id='timm/',
crop_pct=0.95, num_classes=11821),
'convnext_tiny.fb_in1k': _cfg( 'convnext_tiny.fb_in1k': _cfg(
url="https://dl.fbaipublicfiles.com/convnext/convnext_tiny_1k_224_ema.pth", url="https://dl.fbaipublicfiles.com/convnext/convnext_tiny_1k_224_ema.pth",