File size: 1,716 Bytes
9a5e8b9 44ee688 9a5e8b9 f1ad91f 9a5e8b9 f1ad91f e8db095 f1ad91f e8db095 9a5e8b9 f1ad91f 9a5e8b9 f1ad91f 9a5e8b9 |
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 49 50 51 |
from typing import Dict, List, Any
from optimum.onnxruntime import ORTModelForSequenceClassification
from transformers import AutoTokenizer
from optimum.pipelines import pipeline
import torch
if torch.backends.cudnn.is_available():
print("cudnn:", torch.backends.cudnn.version())
class EndpointHandler():
def __init__(self, path=""):
on_cuda = torch.cuda.is_available()
# load the optimized model
provider = "CPUExecutionProvider"
if on_cuda:
provider = "CUDAExecutionProvider"
model = ORTModelForSequenceClassification.from_pretrained(
path,
export=False,
provider=provider,
)
tokenizer = AutoTokenizer.from_pretrained(path)
device = -1
if on_cuda:
device = 0
# create inference pipeline
self.pipeline = pipeline("text-classification", model=model, tokenizer=tokenizer, device=device)
def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
"""
Args:
data (:obj:):
includes the input data and the parameters for the inference.
Return:
A :obj:`list`:. The object returned should be a list of one list like [[{"label": 0.9939950108528137}]] containing :
- "label": A string representing what the label/class is. There can be multiple labels.
- "score": A score between 0 and 1 describing how confident the model is for this label/class.
"""
inputs = data.pop("inputs", data)
parameters = data.pop("parameters", dict())
prediction = self.pipeline(inputs, **parameters)
return prediction |