FunctionIdentificationDataset class

dataset.py

class FunctionIdentificationDataset(torch.utils.data.Dataset):
    def __init__(self, root_directory, block_size, padding_size):
        data, tags = self._preprocess_data(root_directory)
        self._data_blocks, self._tags_blocks = self._split_to_blocks(data, tags, block_size, padding_size)

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

    def __getitem__(self, idx):
        return self._data_blocks[idx], self._tags_blocks[idx]