projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 2ade35e) | patch
Introduce float softrmax cpu kernel (#4911)
author오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 <hseok82.oh@samsung.com>
Mon, 1 Apr 2019 10:09:05 +0000 (19:09 +0900)
committerGitHub Enterprise <noreply-CODE@samsung.com>
Mon, 1 Apr 2019 10:09:05 +0000 (19:09 +0900)
commit4f5fb7baae25d7edf91a9feff83f2d83d9199c18
treea02c16e1589383bcb7d29e57f1330a5681b28ed1tree | snapshot
parent2ade35e42320121d583e907d4737fe29a903f6c8commit | diff
Introduce float softrmax cpu kernel (#4911)

* Introduce float softrmax cpu kernel

Introduce float softmax cpu kernel from tflite
Use kernel in neurun cpu backend

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
* Fix release build bug
libs/cker/include/cker/Shape.h diff | blob | history
libs/cker/include/cker/operation/SoftMax.h [new file with mode: 0644] blob
runtimes/neurun/backend/cpu/kernel/SoftMaxLayer.cc diff | blob | history
Domain: Machine Learning / ML Framework;