Age | Commit message (Collapse) | Author | |
---|---|---|---|
2018-11-02 | COMPMID-642: Fixed mismatches in NEDeconvolutionLayer. | Pablo Tello | |
Mismatches are caused by an incorrect implementation of round() in support/ToolchainSupport.h. The current implementation produces incorrect results in aarch64 linux targets( e.g round(0.5) = 0) Change-Id: I5448d9860f9994745466ba074ade92467508817a Reviewed-on: http://mpd-gerrit.cambridge.arm.com/93032 Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> | |||
2018-11-02 | COMPMID-470: Neon Deconvolution. | Pablo Tello | |
Implemented by up-sampling the input with zeros insertions between the input samples and convolving the Deconvolution kernels on the up-sampled result. The upsampling is performed by the function NEDeconvolutionLayerUpsample. Convolving is done by NEDirectConvolutionLayer. Change-Id: I25f7ba7c6b99cd9310797972ede40aeff4a54900 Reviewed-on: http://mpd-gerrit.cambridge.arm.com/85319 Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> |