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

Method isShapeTensor

include/NvInfer.h:461–464  ·  view source on GitHub ↗

\brief Whether the tensor is a shape tensor. A shape tensor is a tensor that is related to shape calculations. It must have type Int32, Bool, or Float, and its shape must be determinable at build time. Furthermore, it must be needed as a shape tensor, either marked as a network shape output via markOutputForShapes(), or as a layer input that is required to be a shape tensor, such as the second in

Source from the content-addressed store, hash-verified

459 //! \see INetworkDefinition::markOutputForShapes(), ICudaEngine::isShapeBinding()
460 //!
461 bool isShapeTensor() const noexcept
462 {
463 return mImpl->isShapeTensor();
464 }
465
466 //!
467 //! \brief Whether the tensor is an execution tensor.

Callers 3

setLayerPrecisionsFunction · 0.80
setLayerOutputTypesFunction · 0.80
setupNetworkAndConfigFunction · 0.80

Calls

no outgoing calls

Tested by

no test coverage detected