module.py 4.83 KB
Newer Older
WenmuZhou's avatar
WenmuZhou committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

dyning's avatar
dyning committed
15
16
17
18
19
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import os
WenmuZhou's avatar
WenmuZhou committed
20
21
import sys
sys.path.insert(0, ".")
littletomatodonkey's avatar
littletomatodonkey committed
22
import copy
WenmuZhou's avatar
WenmuZhou committed
23
import paddlehub
dyning's avatar
dyning committed
24
25
26
27
28
29
30
from paddlehub.common.logger import logger
from paddlehub.module.module import moduleinfo, runnable, serving
import cv2
import paddlehub as hub

from tools.infer.utility import base64_to_cv2
from tools.infer.predict_rec import TextRecognizer
littletomatodonkey's avatar
littletomatodonkey committed
31
from tools.infer.utility import parse_args
LDOUBLEV's avatar
LDOUBLEV committed
32
from deploy.hubserving.ocr_rec.params import read_params
dyning's avatar
dyning committed
33
34
35
36
37
38
39
40
41
42


@moduleinfo(
    name="ocr_rec",
    version="1.0.0",
    summary="ocr recognition service",
    author="paddle-dev",
    author_email="paddle-dev@baidu.com",
    type="cv/text_recognition")
class OCRRec(hub.Module):
43
    def _initialize(self, use_gpu=False, enable_mkldnn=False):
dyning's avatar
dyning committed
44
45
46
        """
        initialize with the necessary elements
        """
littletomatodonkey's avatar
littletomatodonkey committed
47
        cfg = self.merge_configs()
dyning's avatar
dyning committed
48
49

        cfg.use_gpu = use_gpu
dyning's avatar
dyning committed
50
51
52
53
54
55
        if use_gpu:
            try:
                _places = os.environ["CUDA_VISIBLE_DEVICES"]
                int(_places[0])
                print("use gpu: ", use_gpu)
                print("CUDA_VISIBLE_DEVICES: ", _places)
dyning's avatar
dyning committed
56
                cfg.gpu_mem = 8000
dyning's avatar
dyning committed
57
58
59
60
            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."
                )
dyning's avatar
dyning committed
61
        cfg.ir_optim = True
62
        cfg.enable_mkldnn = enable_mkldnn
dyning's avatar
dyning committed
63

dyning's avatar
dyning committed
64
        self.text_recognizer = TextRecognizer(cfg)
dyning's avatar
dyning committed
65

littletomatodonkey's avatar
littletomatodonkey committed
66
67
68
69
70
71
72
73
74
75
76
77
78
79
    def merge_configs(self, ):
        # deafult cfg
        backup_argv = copy.deepcopy(sys.argv)
        sys.argv = sys.argv[:1]
        cfg = parse_args()

        update_cfg_map = vars(read_params())

        for key in update_cfg_map:
            cfg.__setattr__(key, update_cfg_map[key])

        sys.argv = copy.deepcopy(backup_argv)
        return cfg

dyning's avatar
dyning committed
80
81
82
83
84
85
86
87
88
89
90
91
    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

WenmuZhou's avatar
WenmuZhou committed
92
    def predict(self, images=[], paths=[]):
dyning's avatar
dyning committed
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
        """
        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."
WenmuZhou's avatar
WenmuZhou committed
110

dyning's avatar
dyning committed
111
112
113
114
115
        img_list = []
        for img in predicted_data:
            if img is None:
                continue
            img_list.append(img)
WenmuZhou's avatar
WenmuZhou committed
116

dyning's avatar
dyning committed
117
        rec_res_final = []
dyning's avatar
dyning committed
118
        try:
dyning's avatar
dyning committed
119
            rec_res, predict_time = self.text_recognizer(img_list)
dyning's avatar
dyning committed
120
121
            for dno in range(len(rec_res)):
                text, score = rec_res[dno]
WenmuZhou's avatar
WenmuZhou committed
122
123
124
125
                rec_res_final.append({
                    'text': text,
                    'confidence': float(score),
                })
dyning's avatar
dyning committed
126
127
        except Exception as e:
            print(e)
dyning's avatar
dyning committed
128
129
130
131
            return [[]]

        return [rec_res_final]

dyning's avatar
dyning committed
132
133
134
135
136
137
    @serving
    def serving_method(self, images, **kwargs):
        """
        Run as a service.
        """
        images_decode = [base64_to_cv2(image) for image in images]
dyning's avatar
dyning committed
138
        results = self.predict(images_decode, **kwargs)
dyning's avatar
dyning committed
139
140
        return results

WenmuZhou's avatar
WenmuZhou committed
141

dyning's avatar
dyning committed
142
143
if __name__ == '__main__':
    ocr = OCRRec()
WenmuZhou's avatar
WenmuZhou committed
144
    ocr._initialize()
dyning's avatar
dyning committed
145
146
147
148
149
    image_path = [
        './doc/imgs_words/ch/word_1.jpg',
        './doc/imgs_words/ch/word_2.jpg',
        './doc/imgs_words/ch/word_3.jpg',
    ]
dyning's avatar
dyning committed
150
    res = ocr.predict(paths=image_path)
WenmuZhou's avatar
WenmuZhou committed
151
    print(res)