openvino.runtime.opset12.deformable_convolution#

openvino.runtime.opset12.deformable_convolution(data: Node | int | float | ndarray, offsets: Node | int | float | ndarray, filters: Node | int | float | ndarray, strides: List[int], pads_begin: List[int], pads_end: List[int], dilations: List[int], mask: Node | int | float | ndarray | None = None, auto_pad: str = 'EXPLICIT', group: int = 1, deformable_group: int = 1, bilinear_interpolation_pad: bool = False, name: str | None = None) → Node#

Return a node which performs deformable convolution operation.

Parameters:

  • data – The node providing data batch tensor.

  • offsets – The node providing offset tensor.

  • filters – 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.

  • mask – The node providing modulation scalar (mask) tensor.

  • 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.

  • bilinear_interpolation_pad – The flag that determines the mode of bilinear interpolation execution.

  • name – The optional new name for output node.

Returns:

New node performing deformable convolution operation.