ngraph.opset6.batch_norm_inference

ngraph.opset6.batch_norm_inference(data: Union[_pyngraph.Node, int, float, numpy.ndarray], gamma: Union[_pyngraph.Node, int, float, numpy.ndarray], beta: Union[_pyngraph.Node, int, float, numpy.ndarray], mean: Union[_pyngraph.Node, int, float, numpy.ndarray], variance: Union[_pyngraph.Node, int, float, numpy.ndarray], epsilon: float, name: Optional[str] = None) _pyngraph.Node

Perform layer normalizes a input tensor by mean and variance with appling scale and offset.

Parameters
  • data – The input tensor with data for normalization.

  • gamma – The scalar scaling for normalized value.

  • beta – The bias added to the scaled normalized value.

  • mean – The value for mean normalization.

  • variance – The value for variance normalization.

  • epsilon – The number to be added to the variance to avoid division by zero when normalizing a value.

  • name – The optional name of the output node.

:return:: The new node which performs BatchNormInference.