RAD-DINO 模型卡片

>>> import requests
>>> from PIL import Image
>>> def download_sample_image() -> Image.Image:
...     """Download chest X-ray with CC license."""
...     base_url = "https://upload.wikimedia.org/wikipedia/commons"
...     image_url = f"{base_url}/2/20/Chest_X-ray_in_influenza_and_Haemophilus_influenzae.jpg"
...     headers = {"User-Agent": "RAD-DINO"}
...     response = requests.get(image_url, headers=headers, stream=True)
...     return Image.open(response.raw)
...

>>> import torch
>>> from transformers import AutoModel
>>> from transformers import AutoImageProcessor
>>>
>>> # Download the model
>>> repo = "microsoft/rad-dino"
>>> rad_dino = AutoModel.from_pretrained(repo)
>>>
>>> # The processor takes a PIL image, performs resizing, center-cropping, and
>>> # intensity normalization using stats from MIMIC-CXR, and returns a
>>> # dictionary with a PyTorch tensor ready for the encoder
>>> processor = AutoImageProcessor.from_pretrained(repo)

>>> # Download and preprocess a chest X-ray
>>> image = download_sample_image()
>>> image.size  # (width, height)
(2765, 2505)
>>> inputs = processor(images=image, return_tensors="pt")
>>>
>>> # Encode the image!
>>> with torch.inference_mode():
>>>     outputs = rad_dino(**inputs)
>>>
>>> # Look at the CLS embeddings
>>> cls_embeddings = outputs.pooler_output
>>> cls_embeddings.shape  # (batch_size, num_channels)
torch.Size([1, 768])

>>> def reshape_patch_embeddings(flat_tokens: torch.Tensor) -> torch.Tensor:
...     """Reshape flat list of patch tokens into a nice grid."""
...     from einops import rearrange
...     image_size = processor.crop_size["height"]
...     patch_size = model.config.patch_size
...     embeddings_size = image_size // patch_size
...     patches_grid = rearrange(flat_tokens, "b (h w) c -> b c h w", h=embeddings_size)
...     return patches_grid
...
>>> flat_patch_embeddings = outputs.last_hidden_state[:, 1:]  # first token is CLS
>>> reshaped_patch_embeddings = reshape_patch_embeddings(flat_patch_embeddings)
>>> reshaped_patch_embeddings.shape  # (batch_size, num_channels, height, width)
torch.Size([1, 768, 37, 37])

>>> import safetensors
>>> def safetensors_to_state_dict(checkpoint_path: str) -> dict[str, torch.Tensor]:
...     state_dict = {}
...     with safe_open(checkpoint_path, framework="pt") as ckpt_file:
...         for key in ckpt_file.keys():
...             state_dict[key] = ckpt_file.get_tensor(key)
...     return state_dict
...

git clone https://github.com/facebookresearch/dinov2.git
cd dinov2

>>> import torch
>>> rad_dino_gh = torch.hub.load(".", "dinov2_vitb14")
>>> backbone_state_dict = safetensors_to_state_dict("backbone_compatible.safetensors")
>>> rad_dino_gh.load_state_dict(backbone_state_dict, strict=True)
<All keys matched successfully>

>>> from dinov2.layers import DINOHead
>>> rad_dino_head_gh = DINOHead(
...    in_dim=768,
...    out_dim=65536,
...    hidden_dim=2048,
...    bottleneck_dim=256,
...    nlayers=3,
... )
>>> head_state_dict = safetensors_to_state_dict("dino_head.safetensors")
>>> rad_dino_head_gh.load_state_dict(head_state_dict, strict=True)
<All keys matched successfully>

@article{perez-garcia_exploring_2025,
	title = {Exploring scalable medical image encoders beyond text supervision},
	issn = {2522-5839},
	url = {https://doi.org/10.1038/s42256-024-00965-w},
	doi = {10.1038/s42256-024-00965-w},
	journal = {Nature Machine Intelligence},
	author = {P{\'e}rez-Garc{\'i}a, Fernando and Sharma, Harshita and Bond-Taylor, Sam and Bouzid, Kenza and Salvatelli, Valentina and Ilse, Maximilian and Bannur, Shruthi and Castro, Daniel C. and Schwaighofer, Anton and Lungren, Matthew P. and Wetscherek, Maria Teodora and Codella, Noel and Hyland, Stephanie L. and Alvarez-Valle, Javier and Oktay, Ozan},
	month = jan,
	year = {2025},
}