onnxruntime/include/onnxruntime/core
Weixing Zhang 696ab8a194
Create a separate component for graph optimization. (#421)
* Create a project for graph optimizer.

Move optimizer related code to the folder optimizer.

* Fix build failures.

* rebase and fix build failures.

* fix build failure.

* fix build failure with cuda path.

* fix python build failure.

* Move two transformers(memcpy and insert_cast) from framework to optimizer.

* rebase.

* SessionState should not depend on optimizer.
2019-02-04 15:45:12 -08:00
..
common The CUDA compiler doesn't support gsl::suppress so disable when __NVCC__ is defined. (#358) 2019-01-22 17:42:33 +10:00
framework C API - Remove reference counting (#344) 2019-01-25 19:41:10 -08:00
graph Create a separate component for graph optimization. (#421) 2019-02-04 15:45:12 -08:00
optimizer Create a separate component for graph optimization. (#421) 2019-02-04 15:45:12 -08:00
platform Use nsync for implementing condition variable 2019-01-21 22:59:42 -08:00
providers C API - Remove reference counting (#344) 2019-01-25 19:41:10 -08:00
session Rename OrtInitialize to OrtCreateEnv in preparation for future. (#399) 2019-01-29 15:03:18 -08:00