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

Method addDeconvolution

include/NvInfer.h:7102–7106  ·  view source on GitHub ↗

\brief Add a deconvolution layer to the network. \param input The input tensor to the layer. \param nbOutputMaps The number of output feature maps. \param kernelSize The HW-dimensions of the deconvolution kernel. \param kernelWeights The kernel weights for the deconvolution. \param biasWeights The bias weights for the deconvolution. Weights{} represents no bias. \see IDeconvolutionLayer \warnin

Source from the content-addressed store, hash-verified

7100 //! \deprecated Superseded by addDeconvolutionNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0
7101 //!
7102 TRT_DEPRECATED IDeconvolutionLayer* addDeconvolution(
7103 ITensor& input, int32_t nbOutputMaps, DimsHW kernelSize, Weights kernelWeights, Weights biasWeights) noexcept
7104 {
7105 return mImpl->addDeconvolution(input, nbOutputMaps, kernelSize, kernelWeights, biasWeights);
7106 }
7107
7108 //!
7109 //! \brief Add an elementwise layer to the network.

Callers 2

add_deconvolutionFunction · 0.80
parseDeconvolutionFunction · 0.80

Calls

no outgoing calls

Tested by

no test coverage detected