openvino.runtime.opset12.group_normalization(data: Node | int | float | ndarray, scale: Node | int | float | ndarray, bias: Node | int | float | ndarray, num_groups: int, epsilon: float, name: str | None = None) Node#

Return a node which produces a GroupNormalization operation.

  • data – The input tensor to be normalized.

  • scale – The tensor containing the scale values for each channel.

  • bias – The tensor containing the bias values for each channel.

  • num_groups – Specifies the number of groups that the channel dimension will be divided into.

  • epsilon – A very small value added to the variance for numerical stability. Ensures that division by zero does not occur for any normalized element.


GroupNormalization node