projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 3481a24) | patch
[exo] Introducing FuseReluPass (#8176)
author윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 <hyunsik.yoon@samsung.com>
Wed, 16 Oct 2019 07:48:10 +0000 (16:48 +0900)
committer박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 <saehie.park@samsung.com>
Wed, 16 Oct 2019 07:48:10 +0000 (16:48 +0900)
commit5475964f0c5d6b25c9fa857060693328801e5b5b
tree8e364f83f508dd62f16c66db021ea650031194f6tree | snapshot
parent3481a24c6b8a17b57c37eaed8250b36ed217304fcommit | diff
[exo] Introducing FuseReluPass (#8176)

* [exo] Introducing FuseReluPass

This introduces FuseReluPass, which fuse relu/relu6 into 10 TensorFlow Lite ops.
This commit adds code that finds candidate subgraph.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* remove unused var (to avoid CI error)

* Update compiler/exo/src/Pass/FuseReluPass.h

Co-Authored-By: hyunsik-yoon <hyunsik.yoon@samsung.com>
compiler/exo/src/Pass/FuseReluPass.cpp [new file with mode: 0644] blob
compiler/exo/src/Pass/FuseReluPass.h [new file with mode: 0644] blob
Domain: Machine Learning / ML Framework;