projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 830a49c) | patch
[mir_onnx] Reimplement Gemm converter through FullyConnected (#6604)
authorСергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 <s.barannikov@samsung.com>
Wed, 14 Aug 2019 09:22:24 +0000 (18:22 +0900)
committer박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 <jh1302.park@samsung.com>
Wed, 14 Aug 2019 09:22:24 +0000 (18:22 +0900)
commit05c7b00c2a4cd514360cffb5974cb9ef863f26d6
treec0e5848a8d186d442953e59d1be81df55490403dtree | snapshot
parent830a49cc83d6a5551562af1df54e805112abf29fcommit | diff
[mir_onnx] Reimplement Gemm converter through FullyConnected (#6604)

`GemmOp` is almost the same thing as `FullyConnectedOp`. It was only used in the ONNX importer.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
compiler/mir-onnx-importer/ONNXHelpers.h diff | blob | history
compiler/mir-onnx-importer/Op/Gemm.cpp diff | blob | history
Domain: Machine Learning / ML Framework;