projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 7a6f6c2) | patch
[Interp] Introduce softmax operation in interpreter (#5370)
author오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 <hseok82.oh@samsung.com>
Tue, 11 Jun 2019 22:27:37 +0000 (07:27 +0900)
committer박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 <saehie.park@samsung.com>
Tue, 11 Jun 2019 22:27:37 +0000 (07:27 +0900)
commite9ce29b90cb604f7285b08143907a9d8cc1db7c0
tree8dfe14b65b478d4d2806c495b06e9e83ffca111ctree | snapshot
parent7a6f6c283fc27351960c6fd0961aa08fd01d03edcommit | diff
[Interp] Introduce softmax operation in interpreter (#5370)

* [Interp] Introduce softmax operation in interpreter

Introduce softmax operation for float32 type input & output in interpreter

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
* Fix based on review

- Use dynamic_cast
- Move internal function to anonymous namespace
- Remove return
libs/cker/include/cker/gemmlowp/FixedPoint.h diff | blob | history
runtimes/neurun/core/src/exec/interp/operations/SoftMax.cc diff | blob | history
Domain: Machine Learning / ML Framework;