Instructions to use ERISLab/FGIR-KD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use ERISLab/FGIR-KD with timm:
import timm model = timm.create_model("hf-hub:ERISLab/FGIR-KD", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Card: load with fgir_zoo.tgda
Browse files
README.md
CHANGED
|
@@ -84,9 +84,9 @@ class count, accuracy, SHA-256 and size.
|
|
| 84 |
import torch
|
| 85 |
from PIL import Image
|
| 86 |
from torchvision import transforms
|
| 87 |
-
from fgir_zoo import
|
| 88 |
|
| 89 |
-
model =
|
| 90 |
cfg = model.config
|
| 91 |
tf = transforms.Compose([
|
| 92 |
transforms.Resize((cfg.test_resize_size, cfg.test_resize_size),
|
|
|
|
| 84 |
import torch
|
| 85 |
from PIL import Image
|
| 86 |
from torchvision import transforms
|
| 87 |
+
from fgir_zoo import tgda
|
| 88 |
|
| 89 |
+
model = tgda.create_model('students/serial_203/cub_resnet18_vgg19_bn_cal_203')
|
| 90 |
cfg = model.config
|
| 91 |
tf = transforms.Compose([
|
| 92 |
transforms.Resize((cfg.test_resize_size, cfg.test_resize_size),
|