projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 1fc35a1) | patch
Add NN importer interface and memory mapper (#168)
authorDmitry Mozolev/SRR-AI Tools Lab/./삼성전자 <d.mozolev@samsung.com>
Wed, 16 May 2018 08:23:36 +0000 (11:23 +0300)
committer박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 <jh1302.park@samsung.com>
Wed, 16 May 2018 08:23:36 +0000 (17:23 +0900)
commit83bfd00c576a064551333361c28f032e46059b5c
treecd6b2801cfec4f7a84c5e9fd9f7f4d758e5c0341tree | snapshot
parent1fc35a170326a474b3ec0f7562589ad6f6372433commit | diff
Add NN importer interface and memory mapper (#168)

* Add NN importer interface and memory mapper

This commit adds common code needed by NN model importers which is

- abstract interface for NN model importers targeting CPU/GPU (possibly
  also will be ok for DSP/NPU)
- code for memory mapped access of NN model files to avoid unnecessary
  data copying (trained NN models can be large)

Signed-off-by: Dmitry Mozolev <d.mozolev@samsung.com>
* Add NN importer interface and memory mapper

Change namespace names

Signed-off-by: Dmitry Mozolev <d.mozolev@samsung.com>
contrib/nnc/CMakeLists.txt diff | blob | history
contrib/nnc/libs/CMakeLists.txt [new file with mode: 0644] blob
contrib/nnc/libs/frontend/CMakeLists.txt [new file with mode: 0644] blob
contrib/nnc/libs/frontend/common/model_allocation.cpp [new file with mode: 0644] blob
contrib/nnc/libs/frontend/include/model_allocation.h [new file with mode: 0644] blob
contrib/nnc/libs/frontend/include/nn_importer.h [new file with mode: 0644] blob
Domain: Machine Learning / ML Framework;