openvino.runtime.opset14.group_normalization

openvino.runtime.opset14.group_normalization(data: Union[openvino._pyopenvino.Node, int, float, numpy.ndarray], scale: Union[openvino._pyopenvino.Node, int, float, numpy.ndarray], bias: Union[openvino._pyopenvino.Node, int, float, numpy.ndarray], num_groups: int, epsilon: float, name: Optional[str] = None) → openvino._pyopenvino.Node

Return a node which produces a GroupNormalization operation.

Parameters

• 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.

Returns

GroupNormalization node