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

Method setPostPadding

include/NvInfer.h:2709–2712  ·  view source on GitHub ↗

\brief Set the multi-dimension post-padding of the deconvolution. The output will be trimmed by this number of elements on the end of every dimension. In other words, it resembles the inverse of a convolution layer with this padding size. Negative padding is not supported. Default: (0, 0, ..., 0) If executing this layer on DLA, padding must be 0. \see getPostPadding()

Source from the content-addressed store, hash-verified

2707 //! \see getPostPadding()
2708 //!
2709 void setPostPadding(Dims padding) noexcept
2710 {
2711 mImpl->setPostPadding(padding);
2712 }
2713
2714 //!
2715 //! \brief Get the padding.

Callers

nothing calls this directly

Calls 1

setPostPaddingMethod · 0.45

Tested by

no test coverage detected