`deepmd.pt.model.network.layernorm`

Module Contents

Classes

LayerNorm

Base class for all neural network modules.

Attributes

device

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

Bases: deepmd.pt.model.network.mlp.MLPLayer

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:: training (bool) – Boolean represents whether this module is in training or evaluation mode.

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.