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

Method isExecutionTensor

include/NvInfer.h:484–487  ·  view source on GitHub ↗

\brief Whether the tensor is an execution tensor. Tensors are usually execution tensors. The exceptions are tensors used solely for shape calculations or whose contents not needed to compute the outputs. The result of isExecutionTensor() is reliable only when network construction is complete. For example, if a partially built network has no path from a tensor to a network output, isExecutionTen

Source from the content-addressed store, hash-verified

482 //! can be passed instead of a pointer to its contents.
483 //!
484 bool isExecutionTensor() const noexcept
485 {
486 return mImpl->isExecutionTensor();
487 }
488
489 //!
490 //! \brief Name a dimension of an input tensor.

Callers 1

setLayerPrecisionMethod · 0.80

Calls

no outgoing calls

Tested by

no test coverage detected