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

Method addFullyConnected

include/NvInfer.h:6964–6968  ·  view source on GitHub ↗

\brief Add a fully connected layer to the network. \param input The input tensor to the layer. \param nbOutputs The number of outputs of the layer. \param kernelWeights The kernel weights for the fully connected layer. \param biasWeights The bias weights for the fully connected layer. Weights{} represents no bias. \see IFullyConnectedLayer \warning It is an error to specify a wildcard value for

Source from the content-addressed store, hash-verified

6962 //! \deprecated Deprecated in TensorRT 8.4. Superseded by addMatrixMultiply().
6963 //!
6964 TRT_DEPRECATED IFullyConnectedLayer* addFullyConnected(
6965 ITensor& input, int32_t nbOutputs, Weights kernelWeights, Weights biasWeights) noexcept
6966 {
6967 return mImpl->addFullyConnected(input, nbOutputs, kernelWeights, biasWeights);
6968 }
6969
6970 //!
6971 //! \brief Add an activation layer to the network.

Callers 2

add_fully_connectedFunction · 0.80
parseInnerProductFunction · 0.80

Calls

no outgoing calls

Tested by

no test coverage detected