Hugging Face's logo

DaiShiResearch
/
mask2former-transnext-tiny-ade

Image Segmentation
PyTorch
English
vision
Model card Files Community
DaiShiResearch commited on
Commit
3d845be
•
1 Parent(s): 7e1f126

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -62,8 +62,8 @@ for ["TransNeXt: Robust Foveal Visual Perception for Vision Transformers"](https
62
 
63
  | Model | #Params | #FLOPs |IN-1K | IN-A |IN-R|Sketch|IN-V2| Download |Config|
64
  |:---:|:---:|:---:|:---:| :---:|:---:|:---:| :---:|:---:|:---:|
65
- | TransNeXt-Small |49.7M|32.1G| 86.0| 58.3|56.4|43.2|76.8| [model](https://huggingface.co/DaiShiResearch/transnext-small-384-1k-ft-1k/resolve/main/transnext_small_384_1k_ft_1k.pth?download=true)|[config](https://github.com/DaiShiResearch/TransNeXt/tree/main/classification/configs/finetune/transnext_small_384.py)|
66
- | TransNeXt-Base |89.7M|56.3G| 86.2| 61.6|57.7|44.7|77.0| [model](https://huggingface.co/DaiShiResearch/transnext-base-384-1k-ft-1k/resolve/main/transnext_base_384_1k_ft_1k.pth?download=true)|[config](https://github.com/DaiShiResearch/TransNeXt/tree/main/classification/configs/finetune/transnext_base_384.py)|
67
 
68
  **ImageNet-1K 256x256 pre-trained model fully utilizing aggregated attention at all stages:**
69
 
 
62
 
63
  | Model | #Params | #FLOPs |IN-1K | IN-A |IN-R|Sketch|IN-V2| Download |Config|
64
  |:---:|:---:|:---:|:---:| :---:|:---:|:---:| :---:|:---:|:---:|
65
+ | TransNeXt-Small |49.7M|32.1G| 86.0| 58.3|56.4|43.2|76.8| [model](https://huggingface.co/DaiShiResearch/transnext-small-384-1k-ft-1k/resolve/main/transnext_small_384_1k_ft_1k.pth?download=true)|[config](https://github.com/DaiShiResearch/TransNeXt/tree/main/classification/configs/finetune/transnext_small_384_ft.py)|
66
+ | TransNeXt-Base |89.7M|56.3G| 86.2| 61.6|57.7|44.7|77.0| [model](https://huggingface.co/DaiShiResearch/transnext-base-384-1k-ft-1k/resolve/main/transnext_base_384_1k_ft_1k.pth?download=true)|[config](https://github.com/DaiShiResearch/TransNeXt/tree/main/classification/configs/finetune/transnext_base_384_ft.py)|
67
 
68
  **ImageNet-1K 256x256 pre-trained model fully utilizing aggregated attention at all stages:**
69