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

Method getTensorDataType

include/NvInferRuntime.h:1697–1700  ·  view source on GitHub ↗

\brief Determine the required data type for a buffer from its tensor name. \param tensorName The name of an input or output tensor. \return The type of the data in the buffer, or DataType::kFLOAT if the provided name does not map to an input or output tensor. \warning The string tensorName must be null-terminated, and be at most 4096 bytes including the terminator.

Source from the content-addressed store, hash-verified

1695 //! \warning The string tensorName must be null-terminated, and be at most 4096 bytes including the terminator.
1696 //!
1697 DataType getTensorDataType(char const* tensorName) const noexcept
1698 {
1699 return mImpl->getTensorDataType(tensorName);
1700 }
1701
1702 //!
1703 //! \brief Get the maximum batch size which can be used for inference. Should only be called if the engine is built

Callers 1

getTensorInfoMethod · 0.80

Calls

no outgoing calls

Tested by

no test coverage detected