This class implements a layer which performs max pooling on a set of three-dimensional multi-channel images.
void SetFilterHeight( int filterHeight );
void SetFilterWidth( int filterWidth );
void SetFilterDepth( int filterDepth );Sets the filter size.
void SetStrideHeight( int strideHeight );
void SetStrideWidth( int strideWidth );
void SetStrideDepth( int strideDepth );Sets the filter stride. The default value is 1.
The layer has no trainable parameters.
The single input accepts a blob of the following dimensions:
BatchLength * BatchWidth * ListSize- the number of images in the setHeight- images' heightWidth- images' widthDepth- images' depthChannels- the number of channels the image format uses
The single output contains a blob of the dimensions:
BatchLengthis equal to the inputBatchLength.BatchWidthis equal to the inputBatchWidth.ListSizeis equal to the inputListSize.Heightcan be calculated from the inputHeightas(Height - FilterHeight)/StrideHeight + 1.Widthcan be calculated from the inputWidthas(Width - FilterWidth)/StrideWidth + 1.Depthcan be calculated from the inputDepthas(Depth - FilterDepth)/StrideDepth + 1.Channelsis equal to the inputChannels.