OpenOCR/tools/data/text_lmdb_dataset.py

import os
import lmdb
import numpy as np
from torch.utils.data import Dataset

from openrec.preprocess import create_operators, transform


class TextLMDBDataSet(Dataset):

    def __init__(self, config, mode, logger, seed=None, epoch=1, task='rec'):
        super(TextLMDBDataSet, self).__init__()

        global_config = config['Global']
        dataset_config = config[mode]['dataset']
        loader_config = config[mode]['loader']
        loader_config['batch_size_per_card']
        data_dir = dataset_config['data_dir']
        self.do_shuffle = loader_config['shuffle']

        self.lmdb_sets = self.load_hierarchical_lmdb_dataset(data_dir)
        logger.info(f'Initialize indexs of datasets: {data_dir}')
        self.data_idx_order_list = self.dataset_traversal()
        if self.do_shuffle:
            np.random.shuffle(self.data_idx_order_list)
        self.ops = create_operators(dataset_config['transforms'],
                                    global_config)
        self.ext_op_transform_idx = dataset_config.get('ext_op_transform_idx',
                                                       1)

        ratio_list = dataset_config.get('ratio_list', [1.0])
        self.need_reset = True in [x < 1 for x in ratio_list]

    def load_hierarchical_lmdb_dataset(self, data_dir):
        lmdb_sets = {}
        dataset_idx = 0
        for dirpath, dirnames, filenames in os.walk(data_dir + '/'):
            if not dirnames:
                env = lmdb.open(
                    dirpath,
                    max_readers=32,
                    readonly=True,
                    lock=False,
                    readahead=False,
                    meminit=False,
                )
                txn = env.begin(write=False)
                num_samples = int(txn.get('num-samples'.encode()))
                lmdb_sets[dataset_idx] = {
                    'dirpath': dirpath,
                    'env': env,
                    'txn': txn,
                    'num_samples': num_samples,
                }
                dataset_idx += 1
        return lmdb_sets

    def dataset_traversal(self):
        lmdb_num = len(self.lmdb_sets)
        total_sample_num = 0
        for lno in range(lmdb_num):
            total_sample_num += self.lmdb_sets[lno]['num_samples']
        data_idx_order_list = np.zeros((total_sample_num, 2))
        beg_idx = 0
        for lno in range(lmdb_num):
            tmp_sample_num = self.lmdb_sets[lno]['num_samples']
            end_idx = beg_idx + tmp_sample_num
            data_idx_order_list[beg_idx:end_idx, 0] = lno
            data_idx_order_list[beg_idx:end_idx,
                                1] = list(range(tmp_sample_num))
            data_idx_order_list[beg_idx:end_idx, 1] += 1
            beg_idx = beg_idx + tmp_sample_num
        return data_idx_order_list

    def get_ext_data(self):
        ext_data_num = 0
        for op in self.ops:
            if hasattr(op, 'ext_data_num'):
                ext_data_num = getattr(op, 'ext_data_num')
                break
        load_data_ops = self.ops[:self.ext_op_transform_idx]
        ext_data = []

        while len(ext_data) < ext_data_num:
            lmdb_idx, file_idx = self.data_idx_order_list[np.random.randint(
                len(self))]
            lmdb_idx = int(lmdb_idx)
            file_idx = int(file_idx)
            sample_info = self.get_lmdb_sample_info(
                self.lmdb_sets[lmdb_idx]['txn'], file_idx)
            if sample_info is None:
                continue
            label = sample_info
            data = {'label': label}
            data = transform(data, load_data_ops)
            if data is None:
                continue
            ext_data.append(data)
        return ext_data

    def get_lmdb_sample_info(self,
                             txn,
                             index,
                             normalize_unicode=True,
                             remove_whitespace=True,
                             max_length=True):
        label_key = 'label-%09d'.encode() % index
        label = txn.get(label_key)
        if label is None:
            return None
        label = label.decode('utf-8')

        return label

    def __getitem__(self, idx):
        lmdb_idx, file_idx = self.data_idx_order_list[idx]
        lmdb_idx = int(lmdb_idx)
        file_idx = int(file_idx)
        sample_info = self.get_lmdb_sample_info(
            self.lmdb_sets[lmdb_idx]['txn'], file_idx)
        if sample_info is None:
            return self.__getitem__(np.random.randint(self.__len__()))
        label = sample_info
        data = {'label': label}
        outs = transform(data, self.ops)
        if outs is None:
            return self.__getitem__(np.random.randint(self.__len__()))
        return outs

    def __len__(self):
        return self.data_idx_order_list.shape[0]