openvino.runtime.opset1.batch_norm_inference#

openvino.runtime.opset1.batch_norm_inference(data: Node | int | float | ndarray, gamma: Node | int | float | ndarray, beta: Node | int | float | ndarray, mean: Node | int | float | ndarray, variance: Node | int | float | ndarray, epsilon: float, name: str | None = None) → 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.

Returns:

The new node which performs BatchNormInference.