openvino.runtime.opset2.prelu

openvino.runtime.opset2.prelu(data: Union[openvino._pyopenvino.Node, int, float, numpy.ndarray], slope: Union[openvino._pyopenvino.Node, int, float, numpy.ndarray], name: Optional[str] = None) openvino._pyopenvino.Node

Perform Parametrized Relu operation element-wise on data from input node.

Parameters
  • data – The node with data tensor.

  • slope – The node with the multipliers for negative values.

  • name – Optional output node name.

Returns

The new node performing a PRelu operation on tensor’s channels.

PRelu uses the following logic:

if data < 0:
    data = data * slope
elif data >= 0:
    data = data