ngraph.opset2.deformable_convolution

ngraph.opset2.deformable_convolution(data: Union[_pyngraph.Node, int, float, numpy.ndarray], deformable_values: Union[_pyngraph.Node, int, float, numpy.ndarray], filters: Union[_pyngraph.Node, int, float, numpy.ndarray], strides: List[int], pads_begin: List[int], pads_end: List[int], dilations: List[int], auto_pad: str = 'EXPLICIT', group: int = 1, deformable_group: int = 1, name: Optional[str] = None) _pyngraph.Node

Create node performing deformable convolution.

Parameters
  • data – The node providing data batch tensor.

  • filter – The node providing filters tensor.

  • strides – The distance (in pixels) to slide the filter on the feature map over the axes.

  • pads_begin – The number of pixels to add to the beginning along each axis.

  • pads_end – The number of pixels to add to the end along each axis.

  • dilations – The distance in width and height between elements (weights) in the filter.

  • auto_pad – The type of padding. Range of values: explicit, same_upper, same_lower, valid.

  • group – The number of groups which both output and input should be split into.

  • deformable_group – The number of groups which deformable values and output should be split into along the channel axis.

  • name – The optional new name for output node.

Returns

New node performing deformable convolution operation.