projects / platform / core / ml / nntrainer.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: aae1735) | patch
Let assign activation fuction per layer
authorjijoong.moon <jijoong.moon@samsung.com>
Wed, 18 Mar 2020 00:13:42 +0000 (09:13 +0900)
committer문지중/On-Device Lab(SR)/Principal Engineer/삼성전자 <jijoong.moon@samsung.com>
Wed, 18 Mar 2020 00:41:55 +0000 (09:41 +0900)
commit6aeecc65d010a9555917f4a1000566223d3d7293
tree7a5b31efa654fb851242ff555b40e01a8bed0b38tree | snapshot
parentaae17359d166eaf43eabffb3b27ab4418891d815commit | diff
Let assign activation fuction per layer

make it possible to assign activation fuction per each layer.

Also, make softmax as an activation function and only softmax and
sigmoid is avaliable for the output layer.

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
include/layers.h diff | blob | history
src/layers.cpp diff | blob | history
src/neuralnet.cpp diff | blob | history
Domain: Machine Learning / ML Framework;