infer_e2e.py 4.2 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 37 38 39 40 41 42 43 44 45 46 47
# 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.

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import numpy as np

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 json
import paddle

from ppocr.data import create_operators, transform
from ppocr.modeling.architectures import build_model
from ppocr.postprocess import build_post_process
from ppocr.utils.save_load import init_model
from ppocr.utils.utility import get_image_file_list
import tools.program as program


def draw_e2e_res(dt_boxes, strs, config, img, img_name):
    if len(dt_boxes) > 0:
        src_im = img
        for box, str in zip(dt_boxes, strs):
            box = box.astype(np.int32).reshape((-1, 1, 2))
            cv2.polylines(src_im, [box], True, color=(255, 255, 0), thickness=2)
48 49 50 51 52 53 54 55
            cv2.putText(
                src_im,
                str,
                org=(int(box[0, 0, 0]), int(box[0, 0, 1])),
                fontFace=cv2.FONT_HERSHEY_COMPLEX,
                fontScale=0.7,
                color=(0, 255, 0),
                thickness=1)
J
Jethong 已提交
56 57 58 59 60 61 62 63
        save_det_path = os.path.dirname(config['Global'][
            'save_res_path']) + "/e2e_results/"
        if not os.path.exists(save_det_path):
            os.makedirs(save_det_path)
        save_path = os.path.join(save_det_path, os.path.basename(img_name))
        cv2.imwrite(save_path, src_im)
        logger.info("The e2e Image saved in {}".format(save_path))

64

J
Jethong 已提交
65 66 67 68 69 70 71 72 73
def main():
    global_config = config['Global']

    # build model
    model = build_model(config['Architecture'])

    init_model(config, model, logger)

    # build post process
J
Jethong 已提交
74 75
    post_process_class = build_post_process(config['PostProcess'],
                                            global_config)
J
Jethong 已提交
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

    # create data ops
    transforms = []
    for op in config['Eval']['dataset']['transforms']:
        op_name = list(op)[0]
        if 'Label' in op_name:
            continue
        elif op_name == 'KeepKeys':
            op[op_name]['keep_keys'] = ['image', 'shape']
        transforms.append(op)

    ops = create_operators(transforms, global_config)

    save_res_path = config['Global']['save_res_path']
    if not os.path.exists(os.path.dirname(save_res_path)):
        os.makedirs(os.path.dirname(save_res_path))

    model.eval()
    with open(save_res_path, "wb") as fout:
        for file in get_image_file_list(config['Global']['infer_img']):
            logger.info("infer_img: {}".format(file))
            with open(file, 'rb') as f:
                img = f.read()
                data = {'image': img}
            batch = transform(data, ops)
            images = np.expand_dims(batch[0], axis=0)
            shape_list = np.expand_dims(batch[1], axis=0)
            images = paddle.to_tensor(images)
            preds = model(images)
            post_result = post_process_class(preds, shape_list)
J
Jethong 已提交
106
            points, strs = post_result['points'], post_result['texts']
J
Jethong 已提交
107 108 109 110 111 112 113 114 115 116 117 118 119 120 121
            # write resule
            dt_boxes_json = []
            for poly, str in zip(points, strs):
                tmp_json = {"transcription": str}
                tmp_json['points'] = poly.tolist()
                dt_boxes_json.append(tmp_json)
            otstr = file + "\t" + json.dumps(dt_boxes_json) + "\n"
            fout.write(otstr.encode())
            src_img = cv2.imread(file)
            draw_e2e_res(points, strs, config, src_img, file)
    logger.info("success!")


if __name__ == '__main__':
    config, device, logger, vdl_writer = program.preprocess()
122
    main()