Class InstanceNorm
java.lang.Object
ai.beestream.jitnn.nn.Module
ai.beestream.jitnn.nn.InstanceNorm
- All Implemented Interfaces:
AutoCloseable
InstanceNorm over [N, C, ...]: each sample and channel normalised over its positions, PyTorch's
nn.InstanceNorm1d/2d/3d without running statistics; affine optional (PyTorch's default: none).
-
Constructor Summary
ConstructorsConstructorDescriptionInstanceNorm(int channels, float eps, boolean affine) InstanceNorm ofchannelschannels with the given eps, with or without a per-channel affine (weight 1, bias 0 at the start). -
Method Summary
Methods inherited from class Module
buffer, buffers, child, close, isClosed, isTraining, loadStateDict, parameter, parameterCount, parameters, stateDict, train, zeroGrad
-
Constructor Details
-
InstanceNorm
public InstanceNorm(int channels, float eps, boolean affine) InstanceNorm ofchannelschannels with the given eps, with or without a per-channel affine (weight 1, bias 0 at the start).
-
-
Method Details
-
forward
-