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: load with fgir_zoo create_model
Browse files
README.md
CHANGED
|
@@ -73,7 +73,7 @@ from PIL import Image
|
|
| 73 |
from torchvision import transforms
|
| 74 |
from fgir_zoo import backbones
|
| 75 |
|
| 76 |
-
model = backbones.
|
| 77 |
cfg = model.config
|
| 78 |
tf = transforms.Compose([
|
| 79 |
transforms.Resize((cfg.test_resize_size, cfg.test_resize_size),
|
|
|
|
| 73 |
from torchvision import transforms
|
| 74 |
from fgir_zoo import backbones
|
| 75 |
|
| 76 |
+
model = backbones.create_model('cal_224/cub_vit_b16_cal') # or model_name='vit_b16', dataset='cub', strategy='cal'
|
| 77 |
cfg = model.config
|
| 78 |
tf = transforms.Compose([
|
| 79 |
transforms.Resize((cfg.test_resize_size, cfg.test_resize_size),
|