predict_e2e.py 5.7 KB
Newer Older
J
Jethong 已提交
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
# Copyright (c) 2020 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.
import os
import sys

__dir__ = os.path.dirname(os.path.abspath(__file__))
sys.path.append(__dir__)
sys.path.append(os.path.abspath(os.path.join(__dir__, '../..')))

os.environ["FLAGS_allocator_strategy"] = 'auto_growth'

import cv2
import numpy as np
import time
import sys

import tools.infer.utility as utility
from ppocr.utils.logging import get_logger
from ppocr.utils.utility import get_image_file_list, check_and_read_gif
from ppocr.data import create_operators, transform
from ppocr.postprocess import build_post_process

logger = get_logger()


J
Jethong 已提交
37
class TextE2E(object):
J
Jethong 已提交
38 39 40 41
    def __init__(self, args):
        self.args = args
        self.e2e_algorithm = args.e2e_algorithm
        pre_process_list = [{
J
Jethong 已提交
42
            'E2EResizeForTest': {}
J
Jethong 已提交
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
        }, {
            'NormalizeImage': {
                'std': [0.229, 0.224, 0.225],
                'mean': [0.485, 0.456, 0.406],
                'scale': '1./255.',
                'order': 'hwc'
            }
        }, {
            'ToCHWImage': None
        }, {
            'KeepKeys': {
                'keep_keys': ['image', 'shape']
            }
        }]
        postprocess_params = {}
        if self.e2e_algorithm == "PGNet":
            pre_process_list[0] = {
                'E2EResizeForTest': {
                    'max_side_len': args.e2e_limit_side_len,
                    'valid_set': 'totaltext'
                }
            }
            postprocess_params['name'] = 'PGPostProcess'
            postprocess_params["score_thresh"] = args.e2e_pgnet_score_thresh
            postprocess_params["character_dict_path"] = args.e2e_char_dict_path
            postprocess_params["valid_set"] = args.e2e_pgnet_valid_set
J
Jethong 已提交
69
            postprocess_params["mode"] = args.e2e_pgnet_mode
J
Jethong 已提交
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
            self.e2e_pgnet_polygon = args.e2e_pgnet_polygon
        else:
            logger.info("unknown e2e_algorithm:{}".format(self.e2e_algorithm))
            sys.exit(0)

        self.preprocess_op = create_operators(pre_process_list)
        self.postprocess_op = build_post_process(postprocess_params)
        self.predictor, self.input_tensor, self.output_tensors = utility.create_predictor(
            args, 'e2e', logger)  # paddle.jit.load(args.det_model_dir)
        # self.predictor.eval()

    def clip_det_res(self, points, img_height, img_width):
        for pno in range(points.shape[0]):
            points[pno, 0] = int(min(max(points[pno, 0], 0), img_width - 1))
            points[pno, 1] = int(min(max(points[pno, 1], 0), img_height - 1))
        return points

    def filter_tag_det_res_only_clip(self, dt_boxes, image_shape):
        img_height, img_width = image_shape[0:2]
        dt_boxes_new = []
        for box in dt_boxes:
            box = self.clip_det_res(box, img_height, img_width)
            dt_boxes_new.append(box)
        dt_boxes = np.array(dt_boxes_new)
        return dt_boxes

    def __call__(self, img):
J
Jethong 已提交
97

J
Jethong 已提交
98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117
        ori_im = img.copy()
        data = {'image': img}
        data = transform(data, self.preprocess_op)
        img, shape_list = data
        if img is None:
            return None, 0
        img = np.expand_dims(img, axis=0)
        shape_list = np.expand_dims(shape_list, axis=0)
        img = img.copy()
        starttime = time.time()

        self.input_tensor.copy_from_cpu(img)
        self.predictor.run()
        outputs = []
        for output_tensor in self.output_tensors:
            output = output_tensor.copy_to_cpu()
            outputs.append(output)

        preds = {}
        if self.e2e_algorithm == 'PGNet':
J
Jethong 已提交
118 119
            preds['f_border'] = outputs[0]
            preds['f_char'] = outputs[1]
J
Jethong 已提交
120
            preds['f_direction'] = outputs[2]
J
Jethong 已提交
121
            preds['f_score'] = outputs[3]
J
Jethong 已提交
122 123 124 125 126 127 128 129 130 131 132 133
        else:
            raise NotImplementedError
        post_result = self.postprocess_op(preds, shape_list)
        points, strs = post_result['points'], post_result['strs']
        dt_boxes = self.filter_tag_det_res_only_clip(points, ori_im.shape)
        elapse = time.time() - starttime
        return dt_boxes, strs, elapse


if __name__ == "__main__":
    args = utility.parse_args()
    image_file_list = get_image_file_list(args.image_dir)
J
Jethong 已提交
134
    text_detector = TextE2E(args)
J
Jethong 已提交
135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154
    count = 0
    total_time = 0
    draw_img_save = "./inference_results"
    if not os.path.exists(draw_img_save):
        os.makedirs(draw_img_save)
    for image_file in image_file_list:
        img, flag = check_and_read_gif(image_file)
        if not flag:
            img = cv2.imread(image_file)
        if img is None:
            logger.info("error in loading image:{}".format(image_file))
            continue
        points, strs, elapse = text_detector(img)
        if count > 0:
            total_time += elapse
        count += 1
        logger.info("Predict time of {}: {}".format(image_file, elapse))
        src_im = utility.draw_e2e_res(points, strs, image_file)
        img_name_pure = os.path.split(image_file)[-1]
        img_path = os.path.join(draw_img_save,
J
Jethong 已提交
155
                                "e2e_res_{}".format(img_name_pure))
J
Jethong 已提交
156 157 158 159
        cv2.imwrite(img_path, src_im)
        logger.info("The visualized image saved in {}".format(img_path))
    if count > 1:
        logger.info("Avg Time: {}".format(total_time / (count - 1)))