Double. The scaling parameter. Default is 0.0001.
Double. A constant.
Double. The exponent. Default is 0.75.
The number of channels to sum over.
Format of input data. Either DataFormat.NCHW (dimOrdering='th') or DataFormat.NHWC (dimOrdering='tf'). Default is NCHW.
A Single Shape, does not include the batch dimension.
Double.
Double. The scaling parameter. Default is 0.0001.
Double.
Double. The exponent. Default is 0.75.
Format of input data.
Format of input data. Either DataFormat.NCHW (dimOrdering='th') or DataFormat.NHWC (dimOrdering='tf'). Default is NCHW.
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.
Double.
Double. A constant.
The number of channels to sum over.
(Since version 0.3.0) please use recommended saveModule(path, overWrite)
Local Response Normalization between different feature maps.
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.
Numeric type of parameter(e.g. weight, bias). Only support float/double now.