[moco/tf] basic Conv2D (padding not yet implemented) (#3731)
author윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 <hyunsik.yoon@samsung.com>
Thu, 13 Jun 2019 09:26:32 +0000 (18:26 +0900)
committer박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 <saehie.park@samsung.com>
Thu, 13 Jun 2019 09:26:32 +0000 (18:26 +0900)
commit89929377397e02967833c9f1bf26bdca32b61df8
treeaec9851162c97e29837982b3a377504731ad15f0
parent95a47cc1000a80daffc6ff6356cea39c703661fc
[moco/tf] basic Conv2D (padding not yet implemented) (#3731)

* [moco/tf] basic Conv2D (padding not yet implemented)

This adds basic implementation of Conv2D.
Padding and `FixShapeTransform` is not yet implemented.

Note: To run the test, `FixShape()` for Conv2D should be implemented. So I added a minimum implementation in this commit.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* renaming vars

* split one GraphUpdate into two

* assert for padding

* supporting NCHW in FeatureDecode
contrib/moco/lib/frontend/tf/src/Op/Conv2D.cpp [new file with mode: 0644]
contrib/moco/lib/frontend/tf/src/Op/Conv2D.test.cpp [new file with mode: 0644]
contrib/moco/lib/frontend/tf/src/Transforms/FixShapeTransform.cpp
contrib/moco/lib/frontend/tf/src/Transforms/MocoNodes.lst