projects / platform / upstream / armnn.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 3a93dfa) | patch
IVGCVSW-4158 FP16 Mobilenet V1 and V2 30% regression on ArmNN on Mate20
authorSadik Armagan <sadik.armagan@arm.com>
Fri, 22 Nov 2019 12:52:28 +0000 (12:52 +0000)
committerKevin May <kevin.may@arm.com>
Sat, 23 Nov 2019 14:37:32 +0000 (14:37 +0000)
commite131a0b179babb03bf9e372a145fa464f916ff81
tree9aa7100950077b83287df2e896e8208c469b3423tree | snapshot
parent3a93dfa9af49188910a715689c9fb7fc381fa03dcommit | diff
IVGCVSW-4158 FP16 Mobilenet V1 and V2 30% regression on ArmNN on Mate20

* Enable FP16 mixed precision for Android Q

Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I5ddb94b13385e1fec39e4407dffc8e4bc6b8d64a
Android.mk diff | blob | history
src/backends/cl/workloads/ClPooling2dWorkload.cpp diff | blob | history
Domain: Machine Learning / ML Framework;