projects / platform / core / ml / nntrainer.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 92a4494) | patch
[Layer] Add constant derivative layer
authorJihoon Lee <jhoon.it.lee@samsung.com>
Tue, 5 Oct 2021 06:52:47 +0000 (15:52 +0900)
committerJijoong Moon <jijoong.moon@samsung.com>
Thu, 7 Oct 2021 10:20:47 +0000 (19:20 +0900)
commitc010802aa1f64b2303c18ae71e85dc1551eca379
tree561c1e63ac9ec3e2895f59713b7bdc33527df041tree | snapshot
parent92a44945fa267c966e890c3fedd3fad7fb9db87bcommit | diff
[Layer] Add constant derivative layer

This patch adds constant derivative layer. This layer will be used to
simulate a backward operation without any loss.

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

Signed-off-by: Jihoon Lee <jhoon.it.lee@samsung.com>
api/ccapi/include/layer.h diff | blob | history
jni/Android.mk diff | blob | history
nntrainer/app_context.cpp diff | blob | history
nntrainer/layers/loss/constant_derivative_loss_layer.cpp [new file with mode: 0644] blob
nntrainer/layers/loss/constant_derivative_loss_layer.h [new file with mode: 0644] blob
nntrainer/layers/loss/meson.build diff | blob | history
Domain: Machine Learning / ML Framework;