handler.py

# +
from typing import  Dict, Any
from PIL import Image
import torch
import requests
from io import BytesIO
from transformers import BlipForConditionalGeneration, BlipProcessor
# -

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

class EndpointHandler():
    def __init__(self, path=""):
        # load the optimized model
        
        self.processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base") 
        self.model = BlipForConditionalGeneration.from_pretrained(
            "Salesforce/blip-image-captioning-base"
        ).to(device)
        self.model.eval()
        self.model = self.model.to(device)
        


    def __call__(self, data: Any) -> Dict[str, Any]:
        """
        Args:
            data (:obj:):
                includes the input data and the parameters for the inference.
        Return:
            A :obj:`dict`:. The object returned should be a dict of one list like {"captions": ["A hugging face at the office"]} containing :
                - "caption": A string corresponding to the generated caption.
        """
        inputs = data.pop("inputs", data)
        parameters = data.pop("parameters", {})
 
        raw_images = [Image.open(BytesIO(requests.get(_img).content)) for _img in inputs]
                                     
        processed_image = self.processor(images=raw_images, return_tensors="pt") 
        processed_image["pixel_values"] = processed_image["pixel_values"].to(device)
        processed_image = {**processed_image, **parameters}
        
        with torch.no_grad():
            out = self.model.generate(
                **processed_image
            )
        captions = self.processor.batch_decode(out, skip_special_tokens=True)
        # postprocess the prediction
        return {"captions": captions}