Hugging Face's logo

timm
/
eva02_large_patch14_clip_336.merged2b_ft_inat21

Image Classification
timm
PyTorch
Safetensors
Model card Files Community
1
rwightman HF staff commited on
Commit
5934f46
•
1 Parent(s): 22f7a3b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -5
README.md CHANGED
@@ -13,11 +13,15 @@ Covering 10,000 species, this dataset and these models are fun to explore via th
13
 
14
  No extra meta-data was used for training these models (as was the case for the competition), it was a straightfoward fine-tune to explore differences in model pretrain data.
15
 
16
- | Model | Top-1 | Top-5 | Paper |
17
- |-------|-------|-------|-------|
18
- | [eva02_large_patch14_clip_336.merged2b_ft_inat21](https://huggingface.co/timm/eva02_large_patch14_clip_336.merged2b_ft_inat21) | 92.05 | 98.01 | https://arxiv.org/abs/2303.11331 |
19
- | [vit_large_patch14_clip_336.datacompxl_ft_inat21](https://huggingface.co/timm/vit_large_patch14_clip_336.datacompxl_ft_inat21) | 90.85 | 97.68 | https://arxiv.org/abs/2304.14108 |
20
- | [vit_large_patch14_clip_336.laion2b_ft_in12k_in1k_inat21](https://huggingface.co/timm/vit_large_patch14_clip_336.laion2b_ft_in12k_in1k_inat21) | 90.29 | 97.44 | https://arxiv.org/abs/2212.07143 |
 
 
 
 
21
 
22
  ## Fine-tune hparams
23
 
 
13
 
14
  No extra meta-data was used for training these models (as was the case for the competition), it was a straightfoward fine-tune to explore differences in model pretrain data.
15
 
16
+ | Model | Top-1 | Top-5 | Img Size (Train) | Paper |
17
+ |-------|-------|-------|----------|-------|
18
+ | [eva02_large_patch14_clip_336.merged2b_ft_inat21](https://huggingface.co/timm/eva02_large_patch14_clip_336.merged2b_ft_inat21) | 92.05 | 98.01 | 336 | https://arxiv.org/abs/2303.11331 |
19
+ | [vit_large_patch14_clip_336.datacompxl_ft_augreg_inat21](https://huggingface.co/timm/vit_large_patch14_clip_336.datacompxl_ft_augreg_inat21) | 91.98 | 98.03 | 336 | https://arxiv.org/abs/2304.14108 |
20
+ | [vit_large_patch14_clip_336.laion2b_ft_augreg_inat21](https://huggingface.co/timm/vit_large_patch14_clip_336.laion2b_ft_augreg_inat21) | 91.48 | 97.89 | 336 | https://arxiv.org/abs/2212.07143 |
21
+ | [convnext_large_mlp.laion2b_ft_augreg_inat21](https://huggingface.co/timm/convnext_large_mlp.laion2b_ft_augreg_inat21) | 90.95 | 97.68 | 448 (384) | |
22
+ | [vit_large_patch14_clip_336.datacompxl_ft_inat21](https://huggingface.co/timm/vit_large_patch14_clip_336.datacompxl_ft_inat21) | 90.85 | 97.68 | 336 | https://arxiv.org/abs/2304.14108 |
23
+ | [convnext_large_mlp.laion2b_ft_augreg_inat21](https://huggingface.co/timm/convnext_large_mlp.laion2b_ft_augreg_inat21) | 90.62 | 97.61 | 384 | |
24
+ | [vit_large_patch14_clip_336.laion2b_ft_in12k_in1k_inat21](https://huggingface.co/timm/vit_large_patch14_clip_336.laion2b_ft_in12k_in1k_inat21) | 90.29 | 97.44 | 336 | https://arxiv.org/abs/2212.07143 |
25
 
26
  ## Fine-tune hparams
27