deepmd.pt.utils.dataloader

deepmd.pt.utils.dataloader#

Attributes#

log

Classes#

DpLoaderSet

A dataset for storing DataLoaders to multiple Systems.

Functions#

`setup_seed`(→ None)
`collate_batch`(→ dict[str, Any])
`get_weighted_sampler`(...)
`get_sampler_from_params`(→ Any)

Module Contents#

deepmd.pt.utils.dataloader.log[source]#

deepmd.pt.utils.dataloader.setup_seed(seed: int | list[int] | tuple[int, Ellipsis]) → None[source]#

class deepmd.pt.utils.dataloader.DpLoaderSet(systems: str | list[str], batch_size: int, type_map: list[str] | None, seed: int | None = None, shuffle: bool = True)[source]#

Bases: torch.utils.data.Dataset

A dataset for storing DataLoaders to multiple Systems.

Parameters:

sys_path: Path to the data system
batch_size: Max frame count in a batch.
type_map: Gives the name of different atom types
seed: Random seed for dataloader
shuffle: If the data are shuffled (Only effective in serial mode. Always shuffle in distributed data parallelism)

systems: list[deepmd.pt.utils.dataset.DeepmdDataSetForLoader] = [][source]#

sampler_list: list[torch.utils.data.distributed.DistributedSampler] = [][source]#

index = [][source]#

total_batch = 0[source]#

dataloaders = [][source]#

batch_sizes = [][source]#

iters = [][source]#

set_noise(noise_settings: dict[str, Any]) → None[source]#

__len__() → int[source]#

__getitem__(idx: int) → dict[str, torch.Tensor][source]#

add_data_requirement(data_requirement: list[deepmd.utils.data.DataRequirementItem]) → None[source]#: Add data requirement for each system in multiple systems.

print_summary(name: str, prob: list[float]) → None[source]#

deepmd.pt.utils.dataloader.collate_batch(batch: list[dict[str, Any]]) → dict[str, Any][source]#

deepmd.pt.utils.dataloader.get_weighted_sampler(training_data: Any, prob_style: str, sys_prob: bool = False) → torch.utils.data.WeightedRandomSampler[source]#

deepmd.pt.utils.dataloader.get_sampler_from_params(_data: Any, _params: dict[str, Any]) → Any[source]#