FlexNN 1
Fully connected neural network built from scratch with flexible n-layer design and multiple activations.
Loading...
Searching...
No Matches
FlexNN::Layers::BatchNormParams Struct Reference

Parameters for BatchNorm1D. More...

#include <LayerTypes.hpp>

Public Attributes

int numFeatures = 0
 
float epsilon = 1e-5f
 
float momentum = 0.1f
 

Detailed Description

Parameters for BatchNorm1D.

Epsilon is fixed at 1e-5 in v0.1 and not serialized; momentum is also fixed at 0.1 for running stats update. Future versions may serialize epsilon via aux if needed.

Member Data Documentation

◆ epsilon

float FlexNN::Layers::BatchNormParams::epsilon = 1e-5f

◆ momentum

float FlexNN::Layers::BatchNormParams::momentum = 0.1f

◆ numFeatures

int FlexNN::Layers::BatchNormParams::numFeatures = 0

The documentation for this struct was generated from the following file: