NVIDIA Holoscan SDK v0.5.1
Holoscan v0.5.1

Class TensorRTInferenceOp

Base Type

class TensorRTInferenceOp : public holoscan::ops::GXFOperator

Operator class to perform the inference of the model.

This wraps a GXF Codelet(<a class="reference internal" href="classnvidia_1_1gxf_1_1TensorRtInference.html#classnvidia_1_1gxf_1_1TensorRtInference" target="_self">nvidia::gxf::TensorRtInference</a>).

Public Functions

template<typename ArgT, typename ...ArgsT, typename = std::enable_if_t<!std::is_base_of_v<holoscan::Operator, std::decay_t<ArgT>> && (std::is_same_v<holoscan::Arg, std::decay_t<ArgT>> || std::is_same_v<holoscan::ArgList, std::decay_t<ArgT>> || std::is_base_of_v<holoscan::Condition, typename holoscan::type_info<ArgT>::derived_type> || std::is_base_of_v<holoscan::Resource, typename holoscan::type_info<ArgT>::derived_type>)>>
inline TensorRTInferenceOp(ArgT &&arg, ArgsT&&... args)

TensorRTInferenceOp() = default

inline virtual const char *gxf_typename() const override

Get the type name of the GXF component.

The returned string is the type name of the GXF component and is used to create the GXF component.

Example: “nvidia::holoscan::AJASource”

Returns

The type name of the GXF component.

virtual void setup(OperatorSpec &spec) override

Define the operator specification.

Parameters

spec – The reference to the operator specification.

© Copyright 2022-2023, NVIDIA. Last updated on Jul 28, 2023.