Method setPrecision

include/NvInfer.h:659–662

\brief Set the computational precision of this layer Setting the precision allows TensorRT to choose an implementation which run at this computational precision. TensorRT could still choose a non-conforming fastest implementation that ignores the requested precision. To force choosing an implementation with the requested precision, set exactly one of the following flags, which differ in what happ

    //! \see getPrecision() precisionIsSet() resetPrecision()
    //!
    void setPrecision(DataType dataType) noexcept
    {
        mLayer->setPrecision(dataType);
    }

    //!
    //! \brief get the computational precision of this layer