- Linking onnxruntime with JNI_LIBRARIES includes some unnecessary links to native libraries (e.g. libawt) which are not actually used or required by the output onnx library. This causes unsatisfied link exceptions when trying to load the onnx library without including these libraries.
* Documentation for API Breaking Changes
* Add version 2 of the API, plus update documentation
* Add a static assert to ensure version 1 of API we shipped does not change in size.
1. Enable warning "4503" # Decorated name length exceeded.
2. Enable warning "4146" # unary minus operator applied to unsigned type.
3. Enable float64 support for the Softmax operator
4. Enable compliance checks for Windows x86 32bits build
5. Use TryBatchParallelFor to replace some fallback code in mlas pooling.cc
6. Fix Android CI pipeline.
Clear error when throwing an exception for a failed CUDA call so that there is only one error mechanism being used at a time.
Minor improvements to logging to aid debugging of BFCArena behaviour.
Also update onnxruntime_perf_test to catch the exception from the call to Run and return a Status. Otherwise it exits with an 'unknown exception' error.
* Implement Bitonic and Radix TopK
* remove needless print out
* fix com err
* add negative support
* fix comments
Co-authored-by: Randy <45701928+RandyShuai@users.noreply.github.com>
* add calibration tool
* add model for e2e example
* format readme
* some more formatting updates
* plus a few more updates
* plus review comments
* plus updates
* more updates
Disable DML in Windows GPU CI build for now, because there are some wired model test failure and I don't know how to fix it. Will seek help from WinML team.
* Add bert related transformers to doc
* Add execution provider and comment for bert optimizations
* Add comment about accuracy impact of approximation
* use correct type for for loop
* explicitly specify void for parameters of OrtGetApiBase because the function is defined in c, so when the function is just (), it is interpreted as having an unknown number of parameters. This was causing compiler warning C4276.
* Remove allocator type from the key comparison in ExecutionProviders.
Remove usage of DummyArena as it's no longer necessary.
* Fix x86 tests where arena allocator is disabled.
Make initialization of OrtMemoryInfo clearer by adding Invalid enum value.
* Make OrtValueNameIdxMap::MaxIdx more intuitive.
WinML would like to update the googletest submodule. They want some newer features (namely GTEST_SKIP to skip tests programmatically and be able to skip entire fixtures easily) and would need to update the submodule version.
However, because the new version of code hit a bug in gcc, even though the bug is already fixed in the latest gcc but we're using gcc 4.8.x and it won't get patched for the bug, so we have to do a compromise, change our code a little bit to make it work.
The gcc bug: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=51213
Add defs and imlementation for OneHotEncoders, adjuist date_time_transformer kernel and test.
Add OneHotEncoder kernel test.
Add HashOneHotVectorizerTransformer unit test.
This does not link due to multiple definitions of functions
that are included into header from a CPP file.
