File size: 1,910 Bytes
5318d99 c1fd285 5318d99 1da5b95 5318d99 9cb5c0d 5318d99 c1fd285 5318d99 1da5b95 5318d99 c1fd285 1b73145 |
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 |
from typing import Dict, List, Any
from PIL import Image
import base64
import torch
import os
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", {})
if isinstance(inputs, Image.Image):
raw_images = [inputs]
else:
inputs = isinstance(inputs, str) and [inputs] or inputs
raw_images = [Image.open(BytesIO(base64.b64decode(_img))) for _img in inputs]
processed_images = self.processor(images=raw_images, return_tensors="pt")
processed_images["pixel_values"] = processed_images["pixel_values"].to(device)
processed_images = {**processed_images, **parameters}
with torch.no_grad():
out = self.model.generate(**processed_images)
captions = self.processor.batch_decode(out, skip_special_tokens=True)
return {"captions": captions} |