The side length of the square region to sum over. Default is 5.
The scaling parameter. Default is 1.0.
The exponent. Default is 0.75.
A Single Shape, does not include the batch dimension.
The scaling parameter.
The scaling parameter. Default is 1.0.
The exponent.
The exponent. Default is 0.75.
Build graph: some other modules point to current module
Build graph: some other modules point to current module
upstream variables
Variable containing current module
A Single Shape, does not include the batch dimension.
The side length of the square region to sum over.
The side length of the square region to sum over. Default is 5.
(Since version 0.3.0) please use recommended saveModule(path, overWrite)
The local response normalization layer performs a kind of "lateral inhibition" by normalizing over local input regions. The local regions extend spatially, in separate channels (i.e., they have shape 1 x size x size).
When you use this layer as the first layer of a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
Remark: This layer is from Torch and wrapped in Keras style.
The numeric type of parameter(e.g. weight, bias). Only support float/double now.