|
--- |
|
tags: |
|
- image-classification |
|
- timm |
|
library_name: timm |
|
license: cc-by-nc-4.0 |
|
--- |
|
# Model card for vit_large_patch14_clip_336.laion2b_ft_augreg_inat21 |
|
Part of a series of `timm` fine-tune experiments on iNaturalist 2021 competition data (https://github.com/visipedia/inat_comp/tree/master/2021) for higher capacity models. |
|
|
|
Covering 10,000 species, this dataset and these models are fun to explore via the classification widget with pictures from your backyard, but quite a bit smaller than models you can find on iNaturalist website (https://www.inaturalist.org/blog/75633-a-new-computer-vision-model-v2-1-including-1-770-new-taxa). |
|
|
|
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. |
|
|
|
| Model | Top-1 | Top-5 | Img Size (Train) | Paper | |
|
|-------|-------|-------|----------|-------| |
|
| [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 | |
|
| [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 | |
|
| [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 | |
|
| [convnext_large_mlp.laion2b_ft_augreg_inat21](https://huggingface.co/timm/convnext_large_mlp.laion2b_ft_augreg_inat21) | 90.95 | 97.68 | 448 (384) | | |
|
| [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 | |
|
| [convnext_large_mlp.laion2b_ft_augreg_inat21](https://huggingface.co/timm/convnext_large_mlp.laion2b_ft_augreg_inat21) | 90.62 | 97.61 | 384 | | |
|
| [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 | |
|
|
|
|
|
## Run Validation |
|
``` |
|
python validate.py /tfds/ --dataset tfds/i_naturalist2021 --model hf-hub:timm/vit_large_patch14_clip_336.laion2b_ft_augreg_inat21 --split val --amp |
|
``` |
|
|
|
## Citation |
|
|
|
```bibtex |
|
@inproceedings{cherti2023reproducible, |
|
title={Reproducible scaling laws for contrastive language-image learning}, |
|
author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia}, |
|
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, |
|
pages={2818--2829}, |
|
year={2023} |
|
} |
|
``` |
|
|
