projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: c11987e) | patch
[neurun] Support explicit padding and activation for Conv2D (#4330)
author김수진/On-Device Lab(SR)/Engineer/삼성전자 <sjsujin.kim@samsung.com>
Mon, 28 Jan 2019 07:56:02 +0000 (16:56 +0900)
committer오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 <hseok82.oh@samsung.com>
Mon, 28 Jan 2019 07:56:02 +0000 (16:56 +0900)
commit93fcc937c5ac956dca18c469063429eda3de9c41
tree5a2ee48a74aee9014e8cae9607c1798c2c60ace9tree | snapshot
parentc11987e6e0e769ef68c9d4d543c6de3c601f79ebcommit | diff
[neurun] Support explicit padding and activation for Conv2D (#4330)

we can pass all of generated `Conv2D` tests(except `quant8` tests).

This commit supports explicit padding and activation for `Conv2D` to pass related tests.

Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
runtimes/neurun/src/backend/acl_cl/StageGenerator.cc diff | blob | history
runtimes/neurun/src/backend/cpu/StageGenerator.cc diff | blob | history
runtimes/neurun/src/frontend/model.cc diff | blob | history
runtimes/neurun/src/model/operation/Conv2DNode.cc diff | blob | history
runtimes/neurun/src/model/operation/Conv2DNode.h diff | blob | history
tests/nnapi/nnapi_gtest.skip.armv7l-linux.neurun diff | blob | history
tests/nnapi/nnapi_gtest.skip.armv7l-linux.neurun.cpu diff | blob | history
Domain: Machine Learning / ML Framework;