projects / platform / core / ml / nntrainer.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: e296266) | patch
[ RNN ] Backwarding Implementation submit/tizen/20210406.094012
authorjijoong.moon <jijoong.moon@samsung.com>
Thu, 25 Mar 2021 07:39:47 +0000 (16:39 +0900)
committerJijoong Moon <jijoong.moon@samsung.com>
Tue, 6 Apr 2021 00:35:59 +0000 (09:35 +0900)
commitce6ced462cb549d32952a6551ba09968c7cc6f9d
tree58d8d70634068e2708de21c8073913ca4b748f66tree | snapshot
parente296266a7a44910d77830b2eb4c9f9d00d9e1769commit | diff
[ RNN ] Backwarding Implementation

This commit includes calculate gradient and derivatives of RNN Layer.

Resolves:

**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>
nntrainer/layers/rnn.cpp diff | blob | history
test/unittest/unittest_nntrainer_layers.cpp diff | blob | history
Domain: Machine Learning / ML Framework;