File size: 1,841 Bytes
2040850 a454558 e7bc726 a454558 e7bc726 1616f3a 65b2717 1616f3a a454558 e7bc726 a454558 e7bc726 a454558 e7bc726 a454558 e7bc726 |
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 |
import os
os.system('pip install paddlepaddle==2.4.2')
# os.system('pip install paddlepaddle==0.0.0 -f https://www.paddlepaddle.org.cn/whl/linux/cpu-mkl/develop.html')
os.system('pip install paddleocr')
from paddleocr import PaddleOCR, draw_ocr
from PIL import Image
from typing import Dict, List, Any
import base64
from io import BytesIO
import numpy as np
class EndpointHandler():
def __init__(self, path=""):
self.pipeline = PaddleOCR(lang="en",ocr_version="PP-OCRv4",
show_log = False,use_gpu=False,
det_model_dir=path,
cls_model_dir=path,
rec_model_dir=path
)
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", None)
receipt_image = Image.open(BytesIO(base64.b64decode(inputs)))
receipt_image_array = np.array(receipt_image.convert('RGB'))
result = self.pipeline.ocr(receipt_image_array,cls=True)
txts = [line[1][0] for line in result[0]]
# pass inputs with all kwargs in data
extract = "".join(txts)
# postprocess the prediction
return extract |