INNER CODE UNIT · Python
number_dataset
clovaai/deep-text-recognition-benchmark · dataset.py:51
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'
selected_d_log += f'num samples of {selected_d} per batch: {opt.batch_size} x {float(batch_ratio_d)} (batch_ratio) = {_batch_size}'
print(selected_d_log)
log.write(selected_d_log + '\n')
batch_size_list.append(str(_batch_size))
Total_batch_size += _batch_size
_data_loader = torch.utils.data.DataLoader(
_dataset, batch_size=_batch_size,
shuffle=True,
num_workers=int(opt.workers),
collate_fn=_AlignCollate, pin_memory=True)
self.data_loader_list.append(_data_loader)