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 numpy as np
import os
import random
from paddle.io import Dataset

from .imaug import transform, create_operators


class SimpleDataSet(Dataset):
    def __init__(self, config, mode, logger):
        super(SimpleDataSet, self).__init__()
        self.logger = logger

        global_config = config['Global']
        dataset_config = config[mode]['dataset']
        loader_config = config[mode]['loader']
        if 'data_num_per_epoch' in loader_config.keys():
            data_num_per_epoch = loader_config['data_num_per_epoch']
        else:
            data_num_per_epoch = None

        self.delimiter = dataset_config.get('delimiter', '\t')
        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)] * len(data_source_num)

        assert len(
            ratio_list
        ) == data_source_num, "The length of ratio_list should be the same as the file_list."
        self.data_dir = dataset_config['data_dir']
        self.do_shuffle = loader_config['shuffle']

        logger.info("Initialize indexs of datasets:%s" % label_file_list)
        self.data_lines = self.get_image_info_list(label_file_list, ratio_list,
                                                   data_num_per_epoch)
        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 _sample_dataset(self, datas, sample_ratio, data_num_per_epoch=None):
        sample_num = round(len(datas) * sample_ratio)

        if data_num_per_epoch is not None:
            sample_num = int(data_num_per_epoch * sample_ratio)

        nums, rem = int(sample_num // len(datas)), int(sample_num % len(datas))
        return list(datas) * nums + random.sample(datas, rem)

    def get_image_info_list(self,
                            file_list,
                            ratio_list,
                            data_num_per_epoch=None):
        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()
                lines = self._sample_dataset(lines, ratio_list[idx],
                                             data_num_per_epoch)
                data_lines.extend(lines)
        return data_lines

    def shuffle_data_random(self):
        if self.do_shuffle:
            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)
            file_name = substr[0]
            label = substr[1]
            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)
        except Exception as e:
            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)