maxpool3d_layer_type

maxpool3d_layer_type(
   input_shape,
   batch_size,
   pool_size=2,
   stride=2
)

The maxpool3d_layer_type derived type provides a 2D maximum pooling layer (e.g. maximum pooling over two spatial dimensions).

This layer creates a pooling kernel that is applied as a mask with the layer input to produce tensor of outputs. For each pooling window, the output is set to the maximum value within the window over the input data.

Arguments

• input_shape: The shape of the input data for one sample. This is required only if this layer is the first (non-input) layer of the network.
• batch_size: Integer. The number samples in a batch. This is optional (the enclosing network structure can handle it instead).
• pool_size: An integer or 1D-array of 3 integers. Specifies the width and depth of the pooling window. Providing a scalar integer specifies the same value for all dimensions. Default = 2.
• stride: An integer or 1D-array of 3 integers. Specifies the strides of the pooling along each spatial dimension. Providing a scalar integer specifies the same value for all dimensions. Default = 2.