metadata
license: apache-2.0
a hand classifier detect the image is showing left hand or right hand
it is trained with hagrid dataset on vit model, google/vit-base-patch16-224-in21k.
Limitation: it couldn't predict both hand and no hand images.
inputs = image_processor(image, return_tensors="pt")
with torch.no_grad():
logits = model(**inputs).logits
predicted_label = logits.argmax(-1).item()
print(f'predicted_label: {model.config.id2label[predicted_label]}')