Applies the layer backward to generate input and output gradients.
- Parameter batchSize: The number of input-output pairs to process.
- Parameter input: The input descriptor.
- Parameter output: The output descriptor.
- Parameter inputGradient: The input gradient descriptor.
- Parameter outputGradient: The output gradient descriptor.
Creates a new pooling layer.
- Parameter poolingType: The pooling type.
- Parameter input: The input descriptor.
- Parameter output: The output descriptor.
- Parameter bias: The bias descriptor.
- Parameter activation: The activation function to apply to the result.
- Parameter kernelSize: The pooling kernel size.
- Parameter stride: Increment in input image.
- Parameter padding: The number of virtual zeros added as a border to the input image.
- Parameter filterParameters: Runtime filter parameters.
Applies the layer to several pairs of (input, output) data.
- Parameter batchSize: The number of input-output pairs to process.
- Parameter input: The input descriptor.
- Parameter output: The output descriptor.