jamessyx/PathGen-CLIP · Hugging Face

Usage of PathGen-CLIP

pip install open_clip_torch

import torch
from PIL import Image
import open_clip

model, _, preprocess = open_clip.create_model_and_transforms('ViT-B-16', pretrained='path/pathgen-clip.pt')
model.eval()  # model in train mode by default, impacts some models with BatchNorm or stochastic depth active
tokenizer = open_clip.get_tokenizer('ViT-B-32')

image = preprocess(Image.open("example.png")).unsqueeze(0)
text = tokenizer(["An H&E image of tumor patch", "An H&E image of normal patch"])

with torch.no_grad(), torch.cuda.amp.autocast():
    image_features = model.encode_image(image)
    text_features = model.encode_text(text)
    image_features /= image_features.norm(dim=-1, keepdim=True)
    text_features /= text_features.norm(dim=-1, keepdim=True)

    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)

print("Label probs:", text_probs)

Cite

@misc{sun2024pathgen16m16millionpathology,
      title={PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration}, 
      author={Yuxuan Sun and Yunlong Zhang and Yixuan Si and Chenglu Zhu and Zhongyi Shui and Kai Zhang and Jingxiong Li and Xingheng Lyu and Tao Lin and Lin Yang},
      year={2024},
      eprint={2407.00203},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2407.00203}, 
}