import requests
from PIL import Image
import matplotlib.pyplot as plt

from transformers import CLIPProcessor, CLIPModel

model = CLIPModel.from_pretrained("flaviagiammarino/pubmed-clip-vit-base-patch32")
processor = CLIPProcessor.from_pretrained("flaviagiammarino/pubmed-clip-vit-base-patch32")

url = "https://encrypted-tbn3.gstatic.com/images?q=tbn:ANd9GcSjP8UWzpGqXKwlC1zPRhcJOXThfI4pXgg2Zhd1B-cstpnEDalY"
image = Image.open(requests.get(url, stream=True).raw)
text = ["Chest X-Ray", "Brain MRI"]

inputs = processor(text=text, images=image, return_tensors="pt", padding=True)
probs = model(**inputs).logits_per_image.softmax(dim=1).detach().numpy().flatten()

plt.subplots()
plt.imshow(image)
plt.title("".join([x[0] + ": " + x[1] + " " for x in zip(text, [format(prob, ".4%") for prob in probs])]))
plt.axis("off")
plt.show()