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

Method getAll

include/NvInferRuntime.h:1030–1033  ·  view source on GitHub ↗

\brief Get description of all weights that could be refit. \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 roles. \return The number of Weights that could be refit. If layerNames!=nullptr, each written pointer points to a string owned by the engine being refit,

Source from the content-addressed store, hash-verified

1028 //! the engine being refit, and becomes invalid when the engine is destroyed.
1029 //!
1030 int32_t getAll(int32_t size, char const** layerNames, WeightsRole* roles) noexcept
1031 {
1032 return mImpl->getAll(size, layerNames, roles);
1033 }
1034
1035 //!
1036 //! \deprecated Deprecated in TRT 8.0. Superseded by `delete`.

Callers 2

pyCore.cppFile · 0.80
getLayerWeightsRolePairFunction · 0.80

Calls

no outgoing calls

Tested by

no test coverage detected