openvino.runtime.opset2.group_convolution_backprop_data

openvino.runtime.opset2.group_convolution_backprop_data(data: Union[openvino._pyopenvino.Node, int, float, numpy.ndarray], filters: Union[openvino._pyopenvino.Node, int, float, numpy.ndarray], strides: List[int], output_shape: Optional[Union[openvino._pyopenvino.Node, int, float, numpy.ndarray]] = None, pads_begin: Optional[List[int]] = None, pads_end: Optional[List[int]] = None, dilations: Optional[List[int]] = None, auto_pad: str = 'EXPLICIT', output_padding: Optional[List[int]] = None, name: Optional[str] = None) → openvino._pyopenvino.Node

Perform Group Convolution operation on data from input node.

Parameters

• data – The node producing input data.

• filters – The node producing filter data.

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

• output_shape – The node that specifies spatial shape of the output.

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

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

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

• auto_pad –

  Describes how to perform padding. Possible values: EXPLICIT: Pad dimensions are explicity specified SAME_LOWER: Pad dimensions computed to match input shape Ceil(num_dims/2) at the beginning and Floor(num_dims/2) at the end

  SAME_UPPER: Pad dimensions computed to match input shape

  Floor(num_dims/2) at the beginning and Ceil(num_dims/2) at the end

  VALID: No padding

• output_padding – The additional amount of paddings added per each spatial axis in the output tensor.

• name – Optional output node name.

Returns

The new node performing a Group Convolution operation on tensor from input node.