Instructions to use ERISLab/FGIR-Backbones with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use ERISLab/FGIR-Backbones with timm:
import timm model = timm.create_model("hf_hub:ERISLab/FGIR-Backbones", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Card: link the ERISLab collection
Browse files
README.md
CHANGED
|
@@ -20,6 +20,8 @@ set of runs, and compares accuracy against training and inference cost. Training
|
|
| 20 |
[arkel23/fgir-zoo](https://github.com/arkel23/fgir-zoo).
|
| 21 |
|
| 22 |
825 checkpoints, one per (dataset, backbone, strategy, image size), each from one training seed.
|
|
|
|
|
|
|
| 23 |
|
| 24 |
## Strategies
|
| 25 |
|
|
|
|
| 20 |
[arkel23/fgir-zoo](https://github.com/arkel23/fgir-zoo).
|
| 21 |
|
| 22 |
825 checkpoints, one per (dataset, backbone, strategy, image size), each from one training seed.
|
| 23 |
+
The collection [FGIR-Backbones (FGVC13 @ CVPR 2026)](https://huggingface.co/collections/ERISLab/fgir-backbones-fgvc13-cvpr-2026-6ab234cc19fcfd2de1f796a4) groups this repo with the
|
| 24 |
+
paper.
|
| 25 |
|
| 26 |
## Strategies
|
| 27 |
|