File size: 1,160 Bytes
ca6c577 6191c38 f4e54f2 ca6c577 |
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 |
from typing import Dict, List, Any
import numpy as np
from transformers import CLIPProcessor, CLIPModel
from PIL import Image
from io import BytesIO
import base64
class EndpointHandler():
def __init__(self, path=""):
# Preload all the elements you are going to need at inference.
self.model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
self.processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
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)
words = inputs["words"]
imageData = inputs["image"]
image = Image.open(BytesIO(base64.b64decode(imageData)))
inputs = self.processor(text=words, images=image, return_tensors="pt", padding=True)
outputs = self.model(**inputs)
embeddings = outputs.image_embeds.detach().numpy().flatten().tolist()
return {"embeddings": embeddings} |