diff options
| author | Georgios Pinitas <georgios.pinitas@arm.com> | 2020-09-04 15:25:24 +0100 |
|---|---|---|
| committer | Michele Di Giorgio <michele.digiorgio@arm.com> | 2020-09-08 13:58:36 +0000 |
| commit | 7d0adc602b3a3ff66184632fd388b25384a9bc99 (patch) | |
| tree | cc314f8902eef0d037fd9353c3e01b2feca526ff /docs | |
| parent | e8f05da5fb919aa209e1bf0e5c70dd15fff84b7f (diff) | |
| download | ComputeLibrary-7d0adc602b3a3ff66184632fd388b25384a9bc99.tar.gz | |
COMPMID-3151: Remove NEDepthwiseConvolutionLayer3x3Kernel
Prefer NEDepthwiseConvolutionLayerNativeKernel as it has a native format
of NHWC avoiding extra transformation to the NCHW domain.
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: If5d8de11691b8ef7f4c3816941f87417d0c8646b
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3930
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'docs')
| -rw-r--r-- | docs/00_introduction.dox | 12 |
1 files changed, 6 insertions, 6 deletions
diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox index 9db7e57cbe..0ba1d3ef0b 100644 --- a/docs/00_introduction.dox +++ b/docs/00_introduction.dox @@ -415,7 +415,7 @@ v20.02 Public major release - @ref NEComparisonOperationKernel - @ref NEConvolutionLayer - @ref NEDepthwiseConvolutionLayer - - @ref NEDepthwiseConvolutionLayer3x3Kernel + - NEDepthwiseConvolutionLayer3x3Kernel - @ref NEDirectConvolutionLayerOutputStageKernel - @ref NEElementwiseComparison - @ref NEElementwiseMax @@ -427,7 +427,7 @@ v20.02 Public major release - @ref NEPoolingLayer - @ref NEPReluLayer - Added support for QSYMM8_PER_CHANNEL in: - - @ref NEDepthwiseConvolutionLayer3x3Kernel + - NEDepthwiseConvolutionLayer3x3Kernel - Added support for split sizes in: - @ref CLSplit - @ref NESplit @@ -795,11 +795,11 @@ v18.11 Public major release - @ref CLL2NormalizeLayer - Added QASYMM8 support to the following kernels: - @ref CLScaleKernel - - @ref NEDepthwiseConvolutionLayer3x3Kernel + - NEDepthwiseConvolutionLayer3x3Kernel - @ref CLPixelWiseMultiplicationKernel - Added FP16 support to the following kernels: - @ref CLDepthwiseConvolutionLayer3x3NHWCKernel - - @ref NEDepthwiseConvolutionLayer3x3Kernel + - NEDepthwiseConvolutionLayer3x3Kernel - @ref CLNormalizePlanarYUVLayerKernel - @ref CLWinogradConvolutionLayer (5x5 kernel) - More tests added to both validation and benchmarking suites. @@ -950,7 +950,7 @@ v18.01 Public maintenance release - Refactored NEON Winograd (NEWinogradLayerKernel) - Added @ref NEDirectConvolutionLayerOutputStageKernel - Added QASYMM8 support to the following NEON kernels: - - @ref NEDepthwiseConvolutionLayer3x3Kernel + - NEDepthwiseConvolutionLayer3x3Kernel - @ref NEFillBorderKernel - @ref NEPoolingLayerKernel - Added new examples: @@ -994,7 +994,7 @@ v17.12 Public major release - New NEON kernels / functions - arm_compute::NEGEMMLowpAArch64A53Kernel / arm_compute::NEGEMMLowpAArch64Kernel / arm_compute::NEGEMMLowpAArch64V8P4Kernel / arm_compute::NEGEMMInterleavedBlockedKernel / arm_compute::NEGEMMLowpAssemblyMatrixMultiplyCore - arm_compute::NEHGEMMAArch64FP16Kernel - - @ref NEDepthwiseConvolutionLayer3x3Kernel / NEDepthwiseIm2ColKernel / NEGEMMMatrixVectorMultiplyKernel / NEDepthwiseVectorToTensorKernel / @ref NEDepthwiseConvolutionLayer + - NEDepthwiseConvolutionLayer3x3Kernel / NEDepthwiseIm2ColKernel / NEGEMMMatrixVectorMultiplyKernel / NEDepthwiseVectorToTensorKernel / @ref NEDepthwiseConvolutionLayer - @ref NEGEMMLowpOffsetContributionKernel / @ref NEGEMMLowpMatrixAReductionKernel / @ref NEGEMMLowpMatrixBReductionKernel / @ref NEGEMMLowpMatrixMultiplyCore - @ref NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel / @ref NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint - NEWinogradLayer / NEWinogradLayerKernel |