File size: 1,733 Bytes
42762fe 696a8e1 42762fe |
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 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", {})
processed_image = self.processor(images=inputs, 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}
|