Class ov::op::v1::ConvolutionBackpropData

class ConvolutionBackpropData : public ov::op::util::ConvolutionBackPropBase

Data batch backprop for batched convolution operation.

Public Functions

ConvolutionBackpropData() = default

Constructs a batched-convolution data batch-backprop operation.

virtual void validate_and_infer_types() override

Verifies that attributes and inputs are consistent and computes output shapes and element types. Must be implemented by concrete child classes so that it can be run any number of times.

Throws if the node is invalid.

const PartialShape get_output_shape() const

The output spatial dimensions shape.

void infer_conv_backprop_output_spatial_shape(const std::vector<Dimension> &input_data_shape, const std::vector<Dimension> &filters_shape, const Strides &strides, const Strides &dilations, const CoordinateDiff &pads_begin, const CoordinateDiff &pads_end, const CoordinateDiff &output_padding, std::vector<Dimension> &output_spatial_shape)

Calculates output spatial features size.

  • input_data_shape[in] The input data partial shape

  • filters_shape[in] The filters partial shape

  • strides[in] The strides values.

  • dilations[in] The dilations values.

  • pads_begin[in] The paddings at the beginning of axis.

  • pads_end[in] The paddings at the end of axis.

  • output_padding[in] The output padding values.

  • output_spatial_shape – The placeholder for computed output spatial partial shape.