projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 4a1e4ef) | patch
Unify PermuteLayer::runTempl and use Object::access (#5778)
authorДилшоджон Умронхонович Пошшоев/AI Tools Lab /SRR/Engineer/삼성전자 <d.poshshoev@samsung.com>
Thu, 25 Jul 2019 02:12:18 +0000 (11:12 +0900)
committer이한종/On-Device Lab(SR)/Engineer/삼성전자 <hanjoung.lee@samsung.com>
Thu, 25 Jul 2019 02:12:18 +0000 (11:12 +0900)
commitea816168191d1916d5a73aa946b61cbbb4ed0f09
tree22fa81fa1b30678c0111646daf1871eda8a42d79tree | snapshot
parent4a1e4ef351ca1834fc81d20c4ffbd42dba1b7223commit | diff
Unify PermuteLayer::runTempl and use Object::access (#5778)

For all types of PermuteNode::Type, runTempl does the same calculation.
The only difference is for rank==4. Unify it and move switch for type
into rank==4 case

Signed-off-by: Dilshodzhon Poshshoev <d.poshshoev@samsung.com>
runtimes/neurun/backend/cpu/kernel/PermuteLayer.h diff | blob | history
Domain: Machine Learning / ML Framework;