torchsig.utils.data_loading.WorkerSeedingDataLoader

class torchsig.utils.data_loading.WorkerSeedingDataLoader(dataset, **kwargs)

Bases: DataLoader, Seedable

A Custom DaaLoader for torchsig that seeds workers differently on worker init based on a shared initial seed;

Methods

add_parent	Add parent Seedable object and set up RNGs accordingly
check_worker_number_rationality
get_distribution
get_second_seed	Gets second seed, usually used to seed both torch and numpy generators with slightly different seeds
init_worker_seed
seed	Seed number generators with given seed.
setup_rngs	Initialize torch and numpy number generators, and update its children.
update_from_parent	Update numpy and torch number generators with parent seed

Attributes

multiprocessing_context
dataset
batch_size
num_workers
pin_memory
drop_last
timeout
sampler
pin_memory_device
prefetch_factor

__init__(dataset, **kwargs)

__repr__() → str

Return repr(self).

add_parent(parent) → None

Add parent Seedable object and set up RNGs accordingly

get_second_seed(seed: int) → int

Gets second seed, usually used to seed both torch and numpy generators with slightly different seeds

Parameters:

seed (int) – Seed to use.

Returns:

New seed.

Return type:

int

seed(seed: int) → None

Seed number generators with given seed.

Parameters:

seed (int) – Seed to use.

setup_rngs() → None

Initialize torch and numpy number generators, and update its children.

update_from_parent() → None

Update numpy and torch number generators with parent seed