openvino.runtime.opset12.squared_difference(x1: Node | int | float | ndarray, x2: Node | int | float | ndarray, auto_broadcast: str = 'NUMPY', name: str | None = None) Node#

Perform an element-wise squared difference between two tensors.

f[ y[i] = (x_1[i] - x_2[i])^2 f]

  • x1 – The node with first input tensor.

  • x2 – The node with second input tensor.

  • auto_broadcast – The type of broadcasting that specifies mapping of input tensor axes to output shape axes. Range of values: numpy, explicit.

  • name – Optional new name for output node.


The new node performing a squared difference between two tensors.