projects / platform / upstream / armnn.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 2ba48d2) | patch
IVGCVSW-3860 Per-channel QSymm8 support of DepthwiseConvolution2d in Cl
authorTeresa Charlin <teresa.charlinreyes@arm.com>
Fri, 29 Nov 2019 13:59:18 +0000 (13:59 +0000)
committerTeresa Charlin <teresa.charlinreyes@arm.com>
Fri, 29 Nov 2019 13:59:18 +0000 (13:59 +0000)
commita68d8530d3dcfc7c54b9c2bfa00b407f45145253
tree224f2b65857dc6f725b4e4c491097af604eeca1ftree | snapshot
parent2ba48d251d0fe4dca214497ac33283106ca0973bcommit | diff
IVGCVSW-3860 Per-channel QSymm8 support of DepthwiseConvolution2d in Cl
    *Add the call to ReorderWeightChannelsForAcl for QuantizedSymm8PerAxis weights

Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I0d2e4c8328753ad15858130945b4fbb193943dfa
src/backends/backendsCommon/WorkloadUtils.cpp diff | blob | history
src/backends/cl/test/ClLayerTests.cpp diff | blob | history
Domain: Machine Learning / ML Framework;