projects / platform / core / ml / nntrainer.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 57e4df8) | patch
[tensor] Reduce num of operations for tensor sum
authorParichay Kapoor <pk.kapoor@samsung.com>
Fri, 17 Sep 2021 04:27:26 +0000 (13:27 +0900)
committerJijoong Moon <jijoong.moon@samsung.com>
Thu, 23 Sep 2021 05:55:48 +0000 (14:55 +0900)
commitd0f3db7d6b6c19d5769f112268b907dde4938181
tree81f1fe1ba79228c4cfb60f2bc13d996b87805785tree | snapshot
parent57e4df81fde9998ba7bbf8c04591742d59a3718ccommit | diff
[tensor] Reduce num of operations for tensor sum

This patch reduces the number of operations required for tensor sum by
accumulating the consecutive axes in order to increase the precision of
the operation.

Signed-off-by: Parichay Kapoor <pk.kapoor@samsung.com>
nntrainer/tensor/tensor.cpp diff | blob | history
nntrainer/tensor/tensor.h diff | blob | history
Domain: Machine Learning / ML Framework;