MCPcopy Create free account
hub / github.com/NVIDIA/TensorRT / fetchOutputData

Method fetchOutputData

samples/common/sampleInference.cpp:802–810  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

800 }
801
802 void fetchOutputData(bool sync)
803 {
804 mBindings.transferOutputToHost(getStream(StreamType::kOUTPUT));
805 // additional sync to avoid overlapping with inference execution.
806 if (sync)
807 {
808 getStream(StreamType::kOUTPUT).synchronize();
809 }
810 }
811
812private:
813 void moveNext()

Callers 1

inferenceExecutionFunction · 0.80

Calls 2

transferOutputToHostMethod · 0.80
synchronizeMethod · 0.45

Tested by

no test coverage detected