File size: 5,519 Bytes
c5b5437
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
import os
import sys
import cv2
import copy
import numpy as np
import math
import time
import traceback
from ppocr.utils.logging import get_logger
from ppocr.utils.utility import get_image_file_list, check_and_read
import tools.infer.utility as utility
from ppocr.postprocess import build_post_process

logger = get_logger()


class TextClassifier(object):
    def __init__(self, args):
        self.cls_image_shape = [int(v) for v in args.cls_image_shape.split(",")]
        self.cls_batch_num = args.cls_batch_num
        self.cls_thresh = args.cls_thresh
        postprocess_params = {
            'name': 'ClsPostProcess',
            "label_list": args.label_list,
        }
        self.postprocess_op = build_post_process(postprocess_params)
        self.predictor, self.input_tensor, self.output_tensors, _ = \
            utility.create_predictor(args, 'cls', logger)
        self.use_onnx = args.use_onnx

    def resize_norm_img(self, img):
        imgC, imgH, imgW = self.cls_image_shape
        h = img.shape[0]
        w = img.shape[1]
        ratio = w / float(h)
        if math.ceil(imgH * ratio) > imgW:
            resized_w = imgW
        else:
            resized_w = int(math.ceil(imgH * ratio))
        resized_image = cv2.resize(img, (resized_w, imgH))
        resized_image = resized_image.astype('float32')
        if self.cls_image_shape[0] == 1:
            resized_image = resized_image / 255
            resized_image = resized_image[np.newaxis, :]
        else:
            resized_image = resized_image.transpose((2, 0, 1)) / 255
        resized_image -= 0.5
        resized_image /= 0.5
        padding_im = np.zeros((imgC, imgH, imgW), dtype=np.float32)
        padding_im[:, :, 0:resized_w] = resized_image
        return padding_im

    def __call__(self, img_list):
        img_list = copy.deepcopy(img_list)
        img_num = len(img_list)
        # Calculate the aspect ratio of all text bars
        width_list = []
        for img in img_list:
            width_list.append(img.shape[1] / float(img.shape[0]))
        # Sorting can speed up the cls process
        indices = np.argsort(np.array(width_list))

        cls_res = [['', 0.0]] * img_num
        batch_num = self.cls_batch_num
        elapse = 0
        for beg_img_no in range(0, img_num, batch_num):

            end_img_no = min(img_num, beg_img_no + batch_num)
            norm_img_batch = []
            max_wh_ratio = 0
            starttime = time.time()
            for ino in range(beg_img_no, end_img_no):
                h, w = img_list[indices[ino]].shape[0:2]
                wh_ratio = w * 1.0 / h
                max_wh_ratio = max(max_wh_ratio, wh_ratio)
            for ino in range(beg_img_no, end_img_no):
                norm_img = self.resize_norm_img(img_list[indices[ino]])
                norm_img = norm_img[np.newaxis, :]
                norm_img_batch.append(norm_img)
            norm_img_batch = np.concatenate(norm_img_batch)
            norm_img_batch = norm_img_batch.copy()

            if self.use_onnx:
                input_dict = {}
                input_dict[self.input_tensor.name] = norm_img_batch
                outputs = self.predictor.run(self.output_tensors, input_dict)
                prob_out = outputs[0]
            else:
                self.input_tensor.copy_from_cpu(norm_img_batch)
                self.predictor.run()
                prob_out = self.output_tensors[0].copy_to_cpu()
                self.predictor.try_shrink_memory()
            cls_result = self.postprocess_op(prob_out)
            elapse += time.time() - starttime
            for rno in range(len(cls_result)):
                label, score = cls_result[rno]
                cls_res[indices[beg_img_no + rno]] = [label, score]
                if '180' in label and score > self.cls_thresh:
                    img_list[indices[beg_img_no + rno]] = cv2.rotate(
                        img_list[indices[beg_img_no + rno]], 1)
        return img_list, cls_res, elapse
def run_text_classifier(image_dir, use_gpu, cls_model_dir, draw_img_save_dir):
    args = utility.parse_args()
    args.image_dir = image_dir
    args.use_gpu = use_gpu
    args.cls_model_dir = cls_model_dir
    args.draw_img_save_dir = draw_img_save_dir

    image_file_list = get_image_file_list(args.image_dir)
    text_classifier = TextClassifier(args)
    valid_image_file_list = []
    img_list = []
    for image_file in image_file_list:
        img, flag, _ = check_and_read(image_file)
        if not flag:
            img = cv2.imread(image_file)
        if img is None:
            logger.info("error in loading image:{}".format(image_file))
            continue
        valid_image_file_list.append(image_file)
        img_list.append(img)

    try:
        img_list, cls_res, predict_time = text_classifier(img_list)
    except Exception as e:
        logger.info(traceback.format_exc())
        logger.info(e)
        exit()

    output_file_path = os.path.join(draw_img_save_dir, "rotate.txt")
    with open(output_file_path, 'w') as output_file:
        for ino in range(len(img_list)):
            # logger.info("Predicts of {}:{}".format(valid_image_file_list[ino],
            #                                       cls_res[ino]))

            output_file.write(cls_res[ino][0] + '\n')


# if __name__ == "__main__":
#     run_text_classifier(
#         image_dir="output/cut",
#         use_gpu=False,
#         cls_model_dir="ch_ppocr_mobile_v2.0_cls_infer/",
#         draw_img_save_dir="output/"
#     )