deepmd.pt.model.network.layernorm

Attributes

Classes

Functions

empty_t(shape, precision)

Module Contents

deepmd.pt.model.network.layernorm.device[source]

deepmd.pt.model.network.layernorm.empty_t(shape, precision)[source]

class deepmd.pt.model.network.layernorm.LayerNorm(num_in, eps: float = 1e-05, uni_init: bool = True, bavg: float = 0.0, stddev: float = 1.0, precision: str = DEFAULT_PRECISION, trainable: bool = True, seed: int | List[int] | None = None)[source]

Bases: torch.nn.Module

eps[source]

uni_init[source]

num_in[source]

precision[source]

prec[source]

matrix[source]

bias[source]

random_generator[source]

trainable[source]

dim_out() → int[source]

forward(xx: torch.Tensor) → torch.Tensor[source]

One Layer Norm used by DP model.

Parameters:

xxtorch.Tensor: The input of index.

Returns:

yy: torch.Tensor: The output.

serialize() → dict[source]

Serialize the layer to a dict.

Returns:

dict: The serialized layer.

classmethod deserialize(data: dict) → LayerNorm[source]

Deserialize the layer from a dict.

Parameters:

datadict: The dict to deserialize from.