projects / platform / upstream / armnn.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 91c4171) | patch
MLCE-278-IVGCVSW-5530 FusedActivation issues
authorMike Kelly <mike.kelly@arm.com>
Tue, 17 Nov 2020 11:41:38 +0000 (11:41 +0000)
committerTeresaARM <teresa.charlinreyes@arm.com>
Tue, 17 Nov 2020 12:57:52 +0000 (12:57 +0000)
commit1ac690a12d4952acb8c06b41f0492ed47524b1f1
tree2a9e5c8c6e68215e4a579b9e47aac132439a5e8etree | snapshot
parent91c4171421633b3ff9764bd586f43137aef0ff1acommit | diff
MLCE-278-IVGCVSW-5530 FusedActivation issues

 * GetOverriddenDataType was returning incorrect quantization data
 * Optimized CpuAcc and GpuAcc SubGraphs fail validation on debug versions
   of ArmNN

Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ie97935cc2af67bd9aeebc94b63dafa458bd1aa8c
src/backends/aclCommon/ArmComputeSubgraphUtils.hpp diff | blob | history
src/backends/cl/ClBackend.cpp diff | blob | history
src/backends/neon/NeonBackend.cpp diff | blob | history
Domain: Machine Learning / ML Framework;