Class LayerNorm
java.lang.Object
ai.beestream.jitnn.nn.Module
ai.beestream.jitnn.nn.LayerNorm
- All Implemented Interfaces:
AutoCloseable
LayerNorm over the last axis, with weight 1 and bias 0 initially, like PyTorch's
nn.LayerNorm.-
Constructor Summary
Constructors -
Method Summary
Methods inherited from class Module
buffer, buffers, child, close, isClosed, isTraining, loadStateDict, parameter, parameterCount, parameters, stateDict, train, zeroGrad
-
Constructor Details
-
LayerNorm
public LayerNorm(int features) LayerNorm overfeaturesvalues, with eps 1e-5 and a bias. -
LayerNorm
public LayerNorm(int features, float eps, boolean bias) LayerNorm overfeaturesvalues with the given eps, with or without a bias.
-
-
Method Details
-
weight
The scale [features]. -
bias
The shift [features], or null without one. -
forward
-