Hugging Face's logo

DaiShiResearch
/
transnext-tiny-224-1k

Image Classification
PyTorch
English
vision
Model card Files Community
DaiShiResearch commited on
Commit
927a91e
•
1 Parent(s): 0274088

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -61,8 +61,8 @@ for ["TransNeXt: Robust Foveal Visual Perception for Vision Transformers"](https
61
 
62
  | Model | #Params | #FLOPs |IN-1K | IN-A |IN-R|Sketch|IN-V2| Download |Config|
63
  |:---:|:---:|:---:|:---:| :---:|:---:|:---:| :---:|:---:|:---:|
64
- | 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)|
65
- | 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)|
66
 
67
  **ImageNet-1K 256x256 pre-trained model fully utilizing aggregated attention at all stages:**
68
 
 
61
 
62
  | Model | #Params | #FLOPs |IN-1K | IN-A |IN-R|Sketch|IN-V2| Download |Config|
63
  |:---:|:---:|:---:|:---:| :---:|:---:|:---:| :---:|:---:|:---:|
64
+ | 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)|
65
+ | 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)|
66
 
67
  **ImageNet-1K 256x256 pre-trained model fully utilizing aggregated attention at all stages:**
68