Class ov::op::internal::RMS#

class RMS : public ov::op::Op#

Operator performing Root Mean Square Normalization.

Note

Performs re-scaling invariance and regularizes the summed input according to RMS statistics

Public Functions

RMS(const Output<Node> &data, const Output<Node> &gamma, double epsilson, const ov::element::Type output_type = ov::element::undefined)#

Constructs an RMS operation.

Parameters:

  • data – Input tensor with data

  • gamma – Gamma values for weight

  • eps – Epsilon for not dividing by zero while normalizing the value

  • output_type – Output element type

virtual void validate_and_infer_types() override#

Verifies that attributes and inputs are consistent and computes output shapes and element types. Must be implemented by concrete child classes so that it can be run any number of times.

Throws if the node is invalid.