pubmed-clip-vit-base-patch32

Zero-shot medical image classifier trained on biomedical image–text pairs..

Details

• Model name: pubmed-clip-vit-base-patch32

• Model source: https://huggingface.co/flaviagiammarino/pubmed-clip-vit-base-patch32

• Model author: Sedigheh Eslami et al.

• Model license: MIT

• Model size: 605.00 MB

• Exposes embeddings? no

• Tags: classification, torch, official, medical, zero-shot

Requirements

• Packages: torch, torchvision, transformers

• CPU support

  • yes

• GPU support

  • yes

Example usage

import fiftyone as fo
import fiftyone.zoo as foz

dataset = foz.load_zoo_dataset(
    "coco-2017",
    split="validation",
    dataset_name=fo.get_default_dataset_name(),
    max_samples=50,
    shuffle=True,
)

model = foz.load_zoo_model("pubmed-clip-vit-base-patch32")

dataset.apply_model(model, label_field="predictions")

session = fo.launch_app(dataset)