ngraph.opset4.interpolate

ngraph.opset4.interpolate(image: _pyngraph.Node, output_shape: Union[_pyngraph.Node, int, float, numpy.ndarray], attrs: dict, name: Optional[str] = None) _pyngraph.Node

Perform interpolation of independent slices in input tensor.

Parameters
  • image – The node providing input tensor with data for interpolation.

  • output_shape – 1D tensor describing output shape for spatial axes.

  • attrs – The dictionary containing key, value pairs for attributes.

  • name – Optional name for the output node.

Returns

Node representing interpolation operation.

Available attributes are:

  • axes Specify spatial dimension indices where interpolation is applied.

    Type: List of non-negative integer numbers. Required: yes.

  • mode Specifies type of interpolation.

    Range of values: one of {nearest, linear, cubic, area} Type: string Required: yes

  • align_corners A flag that specifies whether to align corners or not. True means the

    alignment is applied, False means the alignment isn’t applied. Range of values: True or False. Default: True. Required: no

  • antialias A flag that specifies whether to perform anti-aliasing.
    Range of values: False - do not perform anti-aliasing

    True - perform anti-aliasing

    Default value: False Required: no

  • pads_begin Specify the number of pixels to add to the beginning of the image being

    interpolated. A scalar that specifies padding for each spatial dimension. Range of values: list of non-negative integer numbers. Default value: 0 Required: no

  • pads_end Specify the number of pixels to add to the beginning of the image being

    interpolated. A scalar that specifies padding for each spatial dimension. Range of values: list of non-negative integer numbers. Default value: 0 Required: no

Example of attribute dictionary:

# just required ones
attrs = {
    'axes': [2, 3],
    'mode': 'cubic',
}

attrs = {
    'axes': [2, 3],
    'mode': 'cubic',
    'antialias': True,
    'pads_begin': [2, 2, 2],
}

Optional attributes which are absent from dictionary will be set with corresponding default.