INNER CODE UNIT · Python
_batch_size
clovaai/deep-text-recognition-benchmark · dataset.py:39
_batch_size = max(round(opt.batch_size * float(batch_ratio_d)), 1)
print(dashed_line)
log.write(dashed_line + '\n')
_dataset, _dataset_log = hierarchical_dataset(root=opt.train_data, opt=opt, select_data=[selected_d])
total_number_dataset = len(_dataset)
log.write(_dataset_log)
"""
The total number of data can be modified with opt.total_data_usage_ratio.
ex) opt.total_data_usage_ratio = 1 indicates 100% usage, and 0.2 indicates 20% usage.
See 4.2 section in our paper.
"""
number_dataset = int(total_number_dataset * float(opt.total_data_usage_ratio))
dataset_split = [number_dataset, total_number_dataset - number_dataset]
indices = range(total_number_dataset)
_dataset, _ = [Subset(_dataset, indices[offset - length:offset])
for offset, length in zip(_accumulate(dataset_split), dataset_split)]
selected_d_log = f'num total samples of {selected_d}: {total_number_dataset} x {opt.total_data_usage_ratio} (total_data_usage_ratio) = {len(_dataset)}\n'