avgpool3d_layer_type

avgpool3d_layer_type(
   input_shape,
   batch_size,
   pool_size=2,
   stride=2
)

The avgpool3d_layer_type derived type provides a 3D average pooling layer (e.g. average 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 average of the values 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 height width, and depth of the pooling windowl. 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.