PaddleOCR/ppocr/data/simple_dataset.py

# copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
#
# 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 traceback

import numpy as np
import os
import random

from PIL import Image
from paddle.io import Dataset
from ppocr.data.text2Image import create_image, delete_image, my_image_aug
from .imaug import transform, create_operators
import sys
sys.setrecursionlimit(100000)


class SimpleDataSet(Dataset):
    def __init__(self, config, mode, logger, seed=None):
        super(SimpleDataSet, self).__init__()
        self.logger = logger

        global_config = config['Global']
        # 读取Train相关参数
        dataset_config = config[mode]['dataset']
        loader_config = config[mode]['loader']

        self.delimiter = dataset_config.get('delimiter', '\t')

        # 图片路径对应文字txt
        label_file_list = dataset_config.pop('label_file_list')
        data_source_num = len(label_file_list)
        ratio_list = dataset_config.get("ratio_list", [1.0])
        if isinstance(ratio_list, (float, int)):
            ratio_list = [float(ratio_list)] * int(data_source_num)

        assert len(
            ratio_list
        ) == data_source_num, "The length of ratio_list should be the same as the file_list."

        # 图片路径
        self.data_dir = dataset_config['data_dir']
        self.do_shuffle = loader_config['shuffle']

        self.seed = seed
        logger.info("Initialize indexs of datasets:%s" % label_file_list)
        self.data_lines = self.get_image_info_list(label_file_list, ratio_list)
        self.data_idx_order_list = list(range(len(self.data_lines)))
        if mode.lower() == "train":
            self.shuffle_data_random()
        self.ops = create_operators(dataset_config['transforms'], global_config)

    def get_image_info_list(self, file_list, ratio_list):
        if isinstance(file_list, str):
            file_list = [file_list]
        data_lines = []
        for idx, file in enumerate(file_list):
            with open(file, "rb") as f:
                lines = f.readlines()
                random.seed(self.seed)
                lines = random.sample(lines,
                                      round(len(lines) * ratio_list[idx]))
                data_lines.extend(lines)
        return data_lines

    def shuffle_data_random(self):
        if self.do_shuffle:
            random.seed(self.seed)
            random.shuffle(self.data_lines)
        return

    def __getitem__(self, idx):
        file_idx = self.data_idx_order_list[idx]
        data_line = self.data_lines[file_idx]
        try:
            data_line = data_line.decode('utf-8')
            substr = data_line.strip("\n").split(self.delimiter)

            # 图片文件路径、图片文字标识
            file_name = substr[0]
            label = substr[1]

            if file_name[:5] != "image":
                # 临时按Label创建图片
                create_image(self.data_dir, file_name, label)

                # 读取图片
                img_path = os.path.join(self.data_dir, file_name)
                data = {'img_path': img_path, 'label': label}
                if not os.path.exists(img_path):
                    raise Exception("{} does not exist!".format(img_path))
                with open(data['img_path'], 'rb') as f:
                    img = f.read()
                    data['image'] = img
                outs = transform(data, self.ops)

                # 删除临时图片文件
                delete_image(self.data_dir, file_name)
            else:
                # 直接读取文件中有的图片
                img_path = os.path.join(self.data_dir, file_name)
                data = {'img_path': img_path, 'label': label}
                if not os.path.exists(img_path):
                    raise Exception("{} does not exist!".format(img_path))

                # img_pil = Image.open(img_path)
                # img_pil = my_image_aug(img_pil)
                # img_pil.save(img_path)

                with open(data['img_path'], 'rb') as f:
                    img = f.read()
                    data['image'] = img
                outs = transform(data, self.ops)

        except Exception as e:
            traceback.print_exc()
            self.logger.error(
                "When parsing line {}, error happened with msg: {}".format(
                    data_line, e))
            outs = None
        if outs is None:
            return self.__getitem__(np.random.randint(self.__len__()))
        return outs

    def __len__(self):
        return len(self.data_idx_order_list)