Downloads · 30 days
6
12% of all-time downloads
siglip-ecva-best
happy8825/siglip-ecva-best
siglip-ecva-best is a machine learning model from happy8825. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
50
Public
Parameters
92.9M
372 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors372 MB · 100%
At a glance
- Model type
- siglip
- Access
- Public
- Created
- Dec 16, 2025
- Updated
- Dec 24, 2025
- SHA
- f3302f40
Model card
From the Hugging Face model README
SigLIP Classification Model - best
Pushed: 2025-12-16T15:39:49.421242Z
Metrics
- Best (accuracy): 0.6731601731601732
Train Sampling
- mode: balanced
- before: normal=56738 abnormal=30844 total=87582
- after: normal=30844 abnormal=30844 total=61688
Inference
from transformers import AutoImageProcessor, AutoModelForImageClassification
from PIL import Image
import torch
processor = AutoImageProcessor.from_pretrained('happy8825/siglip-ecva-best')
model = AutoModelForImageClassification.from_pretrained('happy8825/siglip-ecva-best')
img = Image.open('your_image.png').convert('RGB')
inputs = processor(images=img, return_tensors='pt')
with torch.no_grad():
logits = model(**inputs).logits
pred = logits.argmax(-1).item()
print(model.config.id2label[pred])
- Type
- siglip
- Created
- Dec 16, 2025
- Updated
- Dec 24, 2025