Upload folder using huggingface_hub

README.md

@@ -36,12 +36,24 @@ image = Image.open("hand_xray.png").convert("RGB")
 inputs = processor(images=image, return_tensors="pt")
 
 with torch.no_grad():
-    outputs = model(**inputs)
+    tokens = model(**inputs).last_hidden_state
 
-cls_embedding = outputs.last_hidden_state[:, 0]  # [1, 768]
-print(cls_embedding.shape)
+# DINOv3 token order: [CLS, register tokens, patch tokens]
+num_register_tokens = getattr(model.config, "num_register_tokens", 0)
+cls_embedding = tokens[:, 0, :]                         # [B, 768]
+patch_embeddings = tokens[:, 1 + num_register_tokens:, :]  # [B, 196, 768] for 224x224
+
+# Optional: mean-pool CLS + patch tokens (excluding register tokens)
+features = torch.cat([cls_embedding.unsqueeze(1), patch_embeddings], dim=1)
+pooled_embedding = features.mean(dim=1)                  # [B, 768]
+
+print("CLS:", cls_embedding.shape)
+print("Patches:", patch_embeddings.shape)
+print("Pooled:", pooled_embedding.shape)
 ```
 
+Use `cls_embedding` for global image features, `patch_embeddings` for spatial features, or `pooled_embedding` for a single pooled representation. Register tokens are excluded from patch features.
+
 **Intended use:** Research on hand radiographs. Not validated for direct clinical diagnosis or treatment decisions. The model weights are distributed subject to the [DINOv3 License](https://github.com/facebookresearch/dinov3/blob/main/LICENSE.md); see the accompanying license file.
 
 ## Citation