cerebras.modelzoo.config_manager.config_classes.base.data_config.DataProcessorConfig#

class cerebras.modelzoo.config_manager.config_classes.base.data_config.DataProcessorConfig(batch_size: int = <object object at 0x7f0436677b60>, shuffle: bool = True, shuffle_seed: int = 0, num_workers: int = 0, prefetch_factor: Optional[int] = None, persistent_workers: Optional[bool] = None)[source]#
batch_size: int = <object object>#

Batch size to be used

shuffle: bool = True#

Whether or not to shuffle the dataset

shuffle_seed: int = 0#

Seed used for deterministic shuffling

num_workers: int = 0#

The number of PyTorch processes used in the dataloader

prefetch_factor: Optional[int] = None#

The number of batches to prefetch in the dataloader

persistent_workers: Optional[bool] = None#

Whether or not to keep workers persistent between epochs