projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 9c5fce8) | patch
[nnc] Fix interpreter deconv implementation (#2756)
authorVladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 <v.plazun@samsung.com>
Wed, 26 Dec 2018 14:18:41 +0000 (17:18 +0300)
committerEfimov Alexander/AI Tools Lab/./Samsung Electronics <a.efimov@samsung.com>
Wed, 26 Dec 2018 14:18:41 +0000 (17:18 +0300)
commite1eb1d18549f63e57704c2503c000f57205a19e9
treedf8b2ea26db0d252bee2b9721de9b4910603c1c7tree | snapshot
parent9c5fce82ba68d84b7d8bdc6a162fe9cffe757714commit | diff
[nnc] Fix interpreter deconv implementation (#2756)

Rotate kernel index prior to input index calculation

Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
contrib/nnc/passes/interpreter/ops/DeConv2D.cpp diff | blob | history
Domain: Machine Learning / ML Framework;