The input tensor. The 4-D input tensor is treated as a 3-D array of 1D vectors (along the last dimension), and each vector is normalized independently.
Optional
depthRadius: numberThe number of adjacent channels in the 1D normalization window.
Optional
bias: numberA constant bias term for the basis.
Optional
alpha: numberA scale factor, usually positive.
Optional
beta: numberAn exponent.
Generated using TypeDoc
Normalizes the activation of a local neighborhood across or within channels.