split to blocks with padding

dataset.py

def _split_to_blocks(self, data, tags, block_size, padding_size):
    data_blocks = []
    tags_blocks = []
    for file_data, file_tags in zip(data, tags):
        for start_index in range(0, len(file_data), block_size):
            data_blocks.append(self._get_padded_data(file_data, start_index, block_size, padding_size))
            tags_blocks.append(file_tags[start_index: start_index + block_size])

    return data_blocks, tags_blocks

def _get_padded_data(self, file_data, index, block_size, padding_size):
    left_padding_number = int(padding_size / 2)
    right_padding_number = padding_size - left_padding_number

    # If there is data availble before the block we will use it for padding. Otherwise we will use FILE_START.
    # Same for FILE_END.
    left_padding = numpy.array([FILE_START] * (left_padding_number - index), dtype=int)
    right_padding = numpy.array([FILE_END] * (right_padding_number - max(file_data.size - index - block_size, 0)), dtype=int)
    block = file_data[max(index - left_padding_number, 0): index + block_size + right_padding_number]

    return numpy.concatenate([left_padding, block, right_padding])