openvino.runtime.opset15.col2im#

openvino.runtime.opset15.col2im(data: Node | int | float | ndarray, output_size: Node | int | float | ndarray, kernel_size: Node | int | float | ndarray, strides: List[int] | None = None, dilations: List[int] | None = None, pads_begin: List[int] | None = None, pads_end: List[int] | None = None, name: str | None = None) → Node#

Perform data movement operation which combines sliding blocks into an image tensor.

Parameters:

  • data – The node providing input data.

  • output_size – Shape of the spatial dimensions of the output image.

  • kernel_size – Size of the sliding blocks.

  • strides – Stride on the sliding blocks in the input spatial dimensions. Defaults to [1, 1].

  • dilations – The dilation of filter elements (distance between elements). Defaults to [1, 1].

  • pads_begin – The number of pixels added at the beginning along each axis. Defaults to [0, 0].

  • pads_end – The number of pixels added at the end along each axis. Defaults to [0, 0].

  • name – The optional name for the created output node.

Returns:

The new node performing Col2Im operation.