plip

病理语言和图像预训练 (PLIP)

病理学语言和图像预训练（PLIP）是病理学人工智能的第一个视觉和语言基础模型。 PLIP是一种大规模预训练模型，可用于从病理图像和文本描述中提取视觉和语言特征。该模型是原始 CLIP 模型的微调版本。

资源

• 官方演示
• HuggingFace 上的 PLIP
• 纸

内部API使用

    from plip . plip import PLIP
    import numpy as np
    
    plip = PLIP ( 'vinid/plip' )
    
    # we create image embeddings and text embeddings
    image_embeddings = plip . encode_images ( images , batch_size = 32 )
    text_embeddings = plip . encode_text ( texts , batch_size = 32 )
    
    # we normalize the embeddings to unit norm (so that we can use dot product instead of cosine similarity to do comparisons)
    image_embeddings = image_embeddings / np . linalg . norm ( image_embeddings , ord = 2 , axis = - 1 , keepdims = True )
    text_embeddings = text_embeddings / np . linalg . norm ( text_embeddings , ord = 2 , axis = - 1 , keepdims = True )

HuggingFace API 使用

    from PIL import Image
    from transformers import CLIPProcessor , CLIPModel
    
    model = CLIPModel . from_pretrained ( "vinid/plip" )
    processor = CLIPProcessor . from_pretrained ( "vinid/plip" )
    
    image = Image . open ( "images/image1.jpg" )
    
    inputs = processor ( text = [ "a photo of label 1" , "a photo of label 2" ],
                       images = image , return_tensors = "pt" , padding = True )
    
    outputs = model ( ** inputs )
    logits_per_image = outputs . logits_per_image  # this is the image-text similarity score
    probs = logits_per_image . softmax ( dim = 1 )  
    print ( probs )
    image . resize (( 224 , 224 ))

引文

如果您在研究中使用 PLIP，请引用以下论文：

    @article { huang2023visual ,
    title = { A visual--language foundation model for pathology image analysis using medical Twitter } ,
    author = { Huang, Zhi and Bianchi, Federico and Yuksekgonul, Mert and Montine, Thomas J and Zou, James } ,
    journal = { Nature Medicine } ,
    pages = { 1--10 } ,
    year = { 2023 } ,
    publisher = { Nature Publishing Group US New York }
}

致谢

内部 API 是从 FashionCLIP复制的。