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

Method getMissing

include/NvInferRuntime.h:1013–1016  ·  view source on GitHub ↗

\brief Get description of missing weights. For example, if some Weights have been set, but the engine was optimized in a way that combines weights, any unsupplied Weights in the combination are considered missing. \param size The number of items that can be safely written to a non-null layerNames or roles. \param layerNames Where to write the layer names. \param roles Where to write the weights

Source from the content-addressed store, hash-verified

1011 //! the engine being refit, and becomes invalid when the engine is destroyed.
1012 //!
1013 int32_t getMissing(int32_t size, char const** layerNames, WeightsRole* roles) noexcept
1014 {
1015 return mImpl->getMissing(size, layerNames, roles);
1016 }
1017
1018 //!
1019 //! \brief Get description of all weights that could be refit.

Callers 2

pyCore.cppFile · 0.80

Calls

no outgoing calls

Tested by

no test coverage detected