File size: 1,267 Bytes
1347a75 ba84673 b2d86ed 1347a75 ba84673 b2d86ed |
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 |
from transformers import Blip2Processor, Blip2Model
from typing import Dict, List, Any
from PIL import Image
from transformers import pipeline
import requests
import torch
class EndpointHandler():
def __init__(self, path=""):
"""
path:
"""
self.device = "cuda" if torch.cuda.is_available() else "cpu"
self.processor = Blip2Processor.from_pretrained(path)
self.model = Blip2Model.from_pretrained(path, torch_dtype=torch.float16)
self.model.to(self.device)
def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
"""
data args:
inputs (:obj: `str` | `PIL.Image` | `np.array`)
kwargs
Return:
A :obj:`list` | `dict`: will be serialized and returned
"""
inputs = data.pop("inputs", data)
image_url = inputs['image_url']
image = Image.open(requests.get(image_url, stream=True).raw)
processed_image = self.processor(images=image, return_tensors="pt").to(self.device, torch.float16)
generated_ids = self.model.generate(**processed_image)
generated_text = self.processor.batch_decode(generated_ids, skip_special_tokens=True)[0].strip()
return image_url, generated_text
|