ngraph.opset4.avg_pool

ngraph.opset4.avg_pool(data_batch: Union[_pyngraph.Node, int, float, numpy.ndarray], strides: List[int], pads_begin: List[int], pads_end: List[int], kernel_shape: List[int], exclude_pad: bool, rounding_type: str = 'floor', auto_pad: Optional[str] = None, name: Optional[str] = None)_pyngraph.Node

Return average pooling node.

Parameters
  • data_batch – The input node providing data.

  • strides – The window movement strides.

  • pads_begin – The input data optional padding below filled with zeros.

  • pads_end – The input data optional padding below filled with zeros.

  • kernel_shape – The pooling window shape.

  • exclude_pad – Whether or not to include zero padding in average computations.

  • rounding_type – Determines used rounding schema when computing output shape. Acceptable values are: [‘floor’, ‘ceil’]

  • auto_pad – Determines how the padding is calculated. Acceptable values: [None, ‘same_upper’, ‘same_lower’, ‘valid’]

  • name – Optional name for the new output node.

Returns

New node with AvgPool operation applied on its data.