madd

Multiply-add.

This layer performs multiply-add on an input by scale and bias; i.e. .

---

Parameters

• has_relu : Boolean, whether the layer applies a ReLU function to the output.
  The default is false.
• relu_max_value : Number, the max value of ReLU output.
  Valid only when has_relu is true and relu_max_value > 0.0f.
  The default is -1.0f, i.e. there is no max value.

---

Weights

• scale : n-D tensor, scale factor.
  The shape must be a scaler (0D tensor), [channels] (1D tensor) or same as the input. The default is 1.0f (0D tensor).
• bias : n-D tensor, bias.
  The shape must be a scalar (0D tensor), [channels] (1D tensor) or same as the input. The default is 0.0f (0D tensor).