projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 9bd14f6) | patch
[moco/ONNX] Enable converting initializer and input tensor to loco node (#3577)
author남궁석/On-Device Lab(SR)/Engineer/삼성전자 <sk.namkoong@samsung.com>
Wed, 29 May 2019 04:26:34 +0000 (13:26 +0900)
committer박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 <saehie.park@samsung.com>
Wed, 29 May 2019 04:26:34 +0000 (13:26 +0900)
commit9b1399cd55e921da581c9854d899486ce5b5470d
tree36b7607862fc74fefbcbff2397b1df07c53fb356tree | snapshot
parent9bd14f602f36ebdfa4f98c0b7da8fb060985ff9ccommit | diff
[moco/ONNX] Enable converting initializer and input tensor to loco node (#3577)

Until now, `moco` didn't handle for converting initializer and input tensors to `loco` node.
By substituting initializer to `loco::ConstGen` and converting input tensors to `loco::Pull`,
this commit will ebable converting initializer and input tensor to `loco` node

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
contrib/moco/lib/frontend/onnx/src/Frontend.cpp diff | blob | history
Domain: Machine Learning / ML Framework;