File size: 1,164 Bytes
98660fb fc3fbd2 98660fb 17063fb 98660fb 17063fb 98660fb |
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 |
from typing import Dict, List, Any
from transformers import CLIPModel, AutoProcessor, AutoTokenizer
import torch
from PIL import Image
import requests
class EndpointHandler:
def __init__(self, path=""):
self.model = CLIPModel.from_pretrained("patrickjohncyh/fashion-clip")
self.processor = AutoProcessor.from_pretrained("patrickjohncyh/fashion-clip")
self.tokenizer = AutoTokenizer.from_pretrained("openai/clip-vit-base-patch32")
def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
parameters = data.pop("parameters", {"mode": "text"})
inputs = data.pop("inputs", data)
with torch.no_grad():
if parameters["mode"] == "text":
inputs = self.tokenizer(inputs, padding=True, return_tensors="pt")
features = self.model.get_text_features(**inputs)
if parameters["mode"] == "image":
image = Image.open(requests.get(inputs, stream=True).raw)
inputs = self.processor(images=image, return_tensors="pt")
features = self.model.get_image_features(**inputs)
return features[0].tolist()
|