118 lines
3.8 KiB
Python
118 lines
3.8 KiB
Python
# -*- coding:utf-8 -*-
|
|
from __future__ import absolute_import
|
|
from __future__ import division
|
|
from __future__ import print_function
|
|
|
|
import os
|
|
import sys
|
|
sys.path.insert(0, ".")
|
|
|
|
from paddlehub.common.logger import logger
|
|
from paddlehub.module.module import moduleinfo, runnable, serving
|
|
import cv2
|
|
import numpy as np
|
|
import paddlehub as hub
|
|
|
|
from tools.infer.utility import base64_to_cv2
|
|
from tools.infer.predict_det import TextDetector
|
|
|
|
|
|
@moduleinfo(
|
|
name="ocr_det",
|
|
version="1.0.0",
|
|
summary="ocr detection service",
|
|
author="paddle-dev",
|
|
author_email="paddle-dev@baidu.com",
|
|
type="cv/text_recognition")
|
|
class OCRDet(hub.Module):
|
|
def _initialize(self, use_gpu=False, enable_mkldnn=False):
|
|
"""
|
|
initialize with the necessary elements
|
|
"""
|
|
from ocr_det.params import read_params
|
|
cfg = read_params()
|
|
|
|
cfg.use_gpu = use_gpu
|
|
if use_gpu:
|
|
try:
|
|
_places = os.environ["CUDA_VISIBLE_DEVICES"]
|
|
int(_places[0])
|
|
print("use gpu: ", use_gpu)
|
|
print("CUDA_VISIBLE_DEVICES: ", _places)
|
|
cfg.gpu_mem = 8000
|
|
except:
|
|
raise RuntimeError(
|
|
"Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
|
|
)
|
|
cfg.ir_optim = True
|
|
cfg.enable_mkldnn = enable_mkldnn
|
|
|
|
self.text_detector = TextDetector(cfg)
|
|
|
|
def read_images(self, paths=[]):
|
|
images = []
|
|
for img_path in paths:
|
|
assert os.path.isfile(
|
|
img_path), "The {} isn't a valid file.".format(img_path)
|
|
img = cv2.imread(img_path)
|
|
if img is None:
|
|
logger.info("error in loading image:{}".format(img_path))
|
|
continue
|
|
images.append(img)
|
|
return images
|
|
|
|
def predict(self, images=[], paths=[]):
|
|
"""
|
|
Get the text box in the predicted images.
|
|
Args:
|
|
images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths
|
|
paths (list[str]): The paths of images. If paths not images
|
|
Returns:
|
|
res (list): The result of text detection box and save path of images.
|
|
"""
|
|
|
|
if images != [] and isinstance(images, list) and paths == []:
|
|
predicted_data = images
|
|
elif images == [] and isinstance(paths, list) and paths != []:
|
|
predicted_data = self.read_images(paths)
|
|
else:
|
|
raise TypeError("The input data is inconsistent with expectations.")
|
|
|
|
assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
|
|
|
|
all_results = []
|
|
for img in predicted_data:
|
|
if img is None:
|
|
logger.info("error in loading image")
|
|
all_results.append([])
|
|
continue
|
|
dt_boxes, elapse = self.text_detector(img)
|
|
logger.info("Predict time : {}".format(elapse))
|
|
|
|
rec_res_final = []
|
|
for dno in range(len(dt_boxes)):
|
|
rec_res_final.append({
|
|
'text_region': dt_boxes[dno].astype(np.int).tolist()
|
|
})
|
|
all_results.append(rec_res_final)
|
|
return all_results
|
|
|
|
@serving
|
|
def serving_method(self, images, **kwargs):
|
|
"""
|
|
Run as a service.
|
|
"""
|
|
images_decode = [base64_to_cv2(image) for image in images]
|
|
results = self.predict(images_decode, **kwargs)
|
|
return results
|
|
|
|
|
|
if __name__ == '__main__':
|
|
ocr = OCRDet()
|
|
image_path = [
|
|
'./doc/imgs/11.jpg',
|
|
'./doc/imgs/12.jpg',
|
|
]
|
|
res = ocr.predict(paths=image_path)
|
|
print(res)
|