Instructions to use amanyagami/viyog-weights with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use amanyagami/viyog-weights with timm:
import timm model = timm.create_model("hf_hub:amanyagami/viyog-weights", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Viyog โ finetuned backbones
Finetuned classification checkpoints used in Viyog (separating adversarial from out-of-distribution inputs). 20 architectures (ResNet/DenseNet/ConvNeXt/Swin/ViT
- edge backbones) across CIFAR-100, CIFAR-10, GTSRB.
Layout โ state_dict .pth files:
- root: the 4 original CIFAR-100 backbones (convnextv2_base, swin_tiny, vit_b, tf_efficientnetv2_l)
cifar100/,cifar10/,gtsrb/: per-dataset checkpoints for every architecture
Package: pip install viyog ยท code: https://github.com/amanyagami/viyog ยท
demo: https://huggingface.co/spaces/amanyagami/viyog
- Downloads last month
- -