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

Method setBiasWeights

include/NvInfer.h:1242–1245  ·  view source on GitHub ↗

\brief Set the bias weights for the convolution. Bias is optional. To omit bias, set the count value of the weights structure to zero. The bias is applied per-channel, so the number of weights (if non-zero) must be equal to the number of output feature maps. \see getBiasWeights()

Source from the content-addressed store, hash-verified

1240 //! \see getBiasWeights()
1241 //!
1242 void setBiasWeights(Weights weights) noexcept
1243 {
1244 mImpl->setBiasWeights(weights);
1245 }
1246
1247 //!
1248 //! \brief Get the bias weights for the convolution.

Callers 3

parseDeconvolutionFunction · 0.45
setBiasWeightsFunction · 0.45
setBiasWeightsMethod · 0.45

Calls

no outgoing calls

Tested by

no test coverage detected