* Rename ONNXRUNTIME_API_STATUSCALL to ONNXRUNTIME_API_CALL since it's just for calling convention, there's no status return value implied.
* Missed a function
* remove input edges while removing a node.
* put comments on how to remove a node without using resolve.
* fix test failure
* fix test failure.
* fix format
* try to guess and fix mac ci failure.
* change add remove edge api.
* update IR
* update comments
* fix comments.
* Add conv+activation fusion.
* Adding tests
* Adding activation LeakyRelu.
* Refactoring the code to use a fusedConv custom op instead of changing
the original conv op at runtime.
* fix build issue.
* fix build issue.
* In order to reduce binary size:
1. reuse onnx shape inference for conv
2. remove most doc.
* Accomodating PR comments.
* Accomodating PR comments
* Remove unused variables
* separate ops from kernels so that folks don't need to depend on kernels when doing export
* resolve conflicts.
* fix comments and warnings in linux
* fix build break in linux
* fix build break.
* fix the wrong dependency that framework needs providres.
* Added tests for C# types
* added multithread c# test
* Added pretrained tests
* Added function to load data from PB file
* added exec task for protoc
* Use windows specific C-runtime based solution for lowercasing/uppercasing.
This worksaround cpp runtime bug with std::locale construction.
* Address review comments.
* Implement separator tokenizer with TST.
TODO: Clarify what to do if the output is empty and no start/end text
markers required. Also see if the current search algo is acceptable.
* Add utf8 util test
* For empty output produce [C] -> [C][0], [N][C] -> [N][C][0]
* Augument TST search with match conflict resolution in favor of
earlier specified pattern matches.
* Address MAcOS build error.
* Adjust error message
* Address review comments.
* Remove nested loops.
* Remove 3rd party utf8 validation code.
* Address review comments part I.
* Move padding outside start/end markers.
Split unit tests for invidividual test cases.
* Fix a common prefix bug reported by Xavier.
* Upgrade gpu build to CUDA 10 + cudnn 7.3
* update the yaml file for python package building
* switch to the cuda9.1 docker file if the CUDA_VER is cuda9.1-cudnn7.1
* Add build step to remove the cuda msbuildcutomization file after build, otherwise, the cuda high version could impact the lower version build
* update vs path
* update the path
