optimum_benchmark/preprocessors/dataset_preprocessor.py [307:317]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    dataset: Dataset,
    pretrained_processor: PretrainedProcessor,
    scenario_config: EnergyStarConfig,
    **kwargs,
) -> Dataset:
    if scenario_config.input_shapes["batch_size"] == 1:
        # Remove empty samples when batch_size is 1 because empty inputs will make the model fail
        dataset = dataset.filter(lambda example: example[scenario_config.image_column_name] != "")

    if scenario_config.num_samples != -1:
        dataset = dataset.select(range(scenario_config.num_samples))
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum_benchmark/preprocessors/dataset_preprocessor.py [334:344]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    dataset: Dataset,
    pretrained_processor: PretrainedProcessor,
    scenario_config: EnergyStarConfig,
    **kwargs,
) -> Dataset:
    if scenario_config.input_shapes["batch_size"] == 1:
        # Remove empty samples when batch_size is 1 because empty inputs will make the model fail
        dataset = dataset.filter(lambda example: example[scenario_config.image_column_name] != "")

    if scenario_config.num_samples != -1:
        dataset = dataset.select(range(scenario_config.num_samples))
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -