File size: 1,853 Bytes
db9328f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60be62e
 
db9328f
 
f49e3ec
 
60be62e
 
 
 
 
 
 
 
f49e3ec
db9328f
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
from typing import Dict, List, Any

from transformers import Blip2Processor, Blip2ForConditionalGeneration

from PIL import Image
from io import BytesIO
import torch
import os

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

class EndpointHandler:
    def __init__(self, path=""):
        # load the optimized model

        self.processor = Blip2Processor.from_pretrained("Salesforce/blip2-opt-2.7b") 
        self.model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-2.7b", device_map="auto")
        self.model.eval()
        self.model = self.model.to("cuda")


    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 = inputs

        inputs = self.processor(inputs, return_tensors="pt").to("cuda")
                                     
        processed_image = self.processor(images=raw_images, return_tensors="pt").to(device)

        out = self.model.generate(**processed_image)
        # 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.decode(out[0], skip_special_tokens=True)

        # postprocess the prediction
        return {"captions": captions}