Downloads · 30 days
0
ikchain/vet-dermatology-feline
vet-dermatology-feline is a image classification model from ikchain. Use it when you need a label for an image. The card lists the license as apache-2.0.
EfficientNetV2-S for feline skin lesion classification (4 classes). Part of Howl Vision for the Gemma 4 Good Hackathon.
Downloads · 30 days
0
Access
Public
Updated Apr 5, 2026
Repo size
243 MB
Likes
0
Public
Click a slice to open those files.
.pt243 MB · 100%
From the Hugging Face model README
EfficientNetV2-S for feline skin lesion classification (4 classes). Part of Howl Vision for the Gemma 4 Good Hackathon.
| Metric | Value |
|---|---|
| Accuracy | 90.1% [84.4%, 93.9%] Wilson CI 95% |
| F1-macro | 0.902 |
| Cohen's Kappa | 0.868 |
Per-class: Flea_Allergy 0.904, Health 0.923, Ringworm 0.861, Scabies 0.919
timm/tf_efficientnetv2_s.in21k_ft_in1k, num_classes=4import timm, torch
model = timm.create_model("tf_efficientnetv2_s.in21k_ft_in1k", pretrained=False, num_classes=4)
ckpt = torch.load("vet_feline_dermatology.pt", map_location="cpu", weights_only=False)
model.load_state_dict(ckpt["model_state_dict"])
model.eval()