ONNX release 1.12.0 #11640

etiotto · 2022-05-26T17:54:35Z

We are releasing ONNX 1.12.0. A release branch is created (https://github.com/onnx/onnx/tree/rel-1.12.0). The planned release date is the week of 2022-06-06.

It is important to integrate ONNX release branch into ORT ASAP so that any issues and incompatibilities can be detected and resolved before the ONNX release. Please follow instructions at (https://github.com/microsoft/onnxruntime/blob/master/docs/How_To_Update_ONNX_Dev_Notes.md) to integrate with the ONNX release branch. Please implement CPU kernels for new and updated ONNX ops. A list of new and updated ops can be found at (https://github.com/onnx/onnx/wiki/Logistics-for-ONNX-Release-1.12.0).

Changes in ONNX are documented in Logistics-for-ONNX-Release-1.12.0 wiki (or in the 1.12.0 release note).

In case a bug in ONNX is detected during integration of ONNX 1.12.0, please contact the ONNX Release Manager @etiotto so that the bug is fixed in the ONNX release branch for the Integration to continue.

snnn · 2022-05-26T20:39:23Z

The last time it took 3 months. I hope you don't need to wait on this.

RyanUnderhill · 2022-05-26T20:57:32Z

Just a note that the release branch/release date above is showing the previous release.

Fixes microsoft#11640

garymm · 2022-05-26T23:07:57Z

@snnn asking for help on these instructions from the "How to Update ONNX" page:

please tell Changming deploying the new test data along with other test models to our CI build machines

I'm telling you :-) LMK if there's anything I need to do.

manually queue a build for every packaging pipeline for your branch.

How do I do that?

snnn · 2022-05-27T00:20:04Z

Below are all the pipelines. You can find them at https://aiinfra.visualstudio.com/Lotus/_build

Pipeline name	filename
DML Nuget Pipeline	nuget/gpu-esrp-pipeline.yml
Linux GPU(cuda10.2) Validation Pipeline	linux-gpu-cuda-11-pipeline.yml
Linux Multi GPU CI Pipeline	linux-multi-gpu-ci-pipeline.yml
Linux Multi GPU TensorRT CI Pipeline	linux-multi-gpu-tensorrt-ci-pipeline.yml
Npm Packaging Pipeline	npm-packaging-pipeline.yml
Nuget WindowsAI Pipeline	nuget/templates/windowsai.yml
OLive-pipeline	py-package-build-pipeline.yml
ONNX Runtime Web Pipeline	web-packaging-pipeline.yml
Python Packaging Pipeline (Training CPU)	orttraining-py-packaging-pipeline-cpu.yml
Python Packaging Pipeline (Training Cuda 10.2)	orttraining-py-packaging-pipeline-cuda102.yml
Python Packaging Pipeline (Training Cuda 11.3)	orttraining-py-packaging-pipeline-cuda113.yml
Python Packaging Pipeline (Training Cuda 11.5)	orttraining-py-packaging-pipeline-cuda115.yml
Python packaging pipeline	py-packaging-pipeline.yml
Windows GPU(cuda10.2) Validation Pipeline	win-gpu-cuda-10-2-pipeline.yml
Zip-Nuget-Java-Nodejs Packaging Pipeline	c-api-noopenmp-packaging-pipelines.yml
onnxruntime-ios-packaging-pipeline	mac-ios-packaging-pipeline.yml

You can also use https://github.com/microsoft/azure-devops-python-api to write a script for doing this. I had one, but I couldn't find it anymore.

Fixes microsoft#11640

garymm · 2022-06-02T00:46:42Z

Finally got the tests to run. Lots of failures: https://dev.azure.com/onnxruntime/onnxruntime/_build/results?buildId=658069&view=logs&j=7536d2cd-87d4-54fe-4891-bfbbf2741d83&t=47129eb0-b626-5be0-6e77-09fcb6185efd

Will dig into them tomorrow.

garymm · 2022-06-03T23:11:03Z

Status update before I head off for the weekend:

I figured out how to run the ONNX conformance tests via the nodeJS API. The tests that were initially failing were all for newly added ops.

This is what I've been using to build and test:

./build.sh --cmake_generator Ninja --config Debug --skip_submodule_sync --parallel --enable_onnx_tests --enable_transformers_tool_test --build_nodejs --update --build
cd js/node
npm test -- --parallel --grep 'test_(blackmanwindow|blackmanwindow|dft|hammingwindow|hannwindow|layer_normalization|melweightmatrix|stft)'

After registering op implementations in #11733, the remaining test failures are in this file:
test-out.txt

Some of the actual vs expected are quite close and I am hoping we can configure the test runner to ignore the diffs.
Some of them are quite far and I fear there're bugs in either ORT or the function defs or the test data.

CC @xadupre @smk2007

snnn · 2022-06-04T00:06:56Z

@fs-eire any comment to the above?

smk2007 · 2022-06-04T01:18:30Z

Status update before I head off for the weekend:

I figured out how to run the ONNX conformance tests via the nodeJS API. The tests that were initially failing were all for newly added ops.

This is what I've been using to build and test:
./build.sh --cmake_generator Ninja --config Debug --skip_submodule_sync --parallel --enable_onnx_tests --enable_transformers_tool_test --build_nodejs --update --build
cd js/node
npm test -- --parallel --grep 'test_(blackmanwindow|blackmanwindow|dft|hammingwindow|hannwindow|layer_normalization|melweightmatrix|stft)'
After registering op implementations in #11733, the remaining test failures are in this file: test-out.txt

Some of the actual vs expected are quite close and I am hoping we can configure the test runner to ignore the diffs. Some of them are quite far and I fear there're bugs in either ORT or the function defs or the test data.

CC @xadupre @smk2007

Hi, I took a look.

Window Functions Tests (Hann, Hamming, Blackman)
The issue here is that we added the periodic attribute to the function late in the CR process.
Now the tests have ONNX tests have 2 issues.

They are generating functions that do not take into account the periodic attribute in the function definition.
The default behavior in ONNX runtime has not been updated to match, and is missing the periodic attribute the contrib op definition always generated the "periodic" (window size instead of window size -1 ) window and not the "symmetric" window. The ONNX test has a few issues in the window functions (constants are incorrectly set).

DFT Tests
The DFT seems like it just needs to have precision in the tests updated. Where do I do that?

STFT Tests
The STFT test is also wrong because it hasnt taken into consideration that the default output will be onesided, and so it is made the expected dimension 16, instead of half+1 (9). I can update this test as well.

I added this PR to address: onnx/onnx#4249

gramalingam · 2022-06-05T16:32:30Z

@wschin : are the layer-normalization error differences expected? (Please see: https://github.com/microsoft/onnxruntime/files/8836128/test-out.txt ). I wonder if there is some subtle difference in the ONNX reference implementation/function and actual? Error margin is around 1% but more in one case. It also looks like there is a shape error in one case?

garymm · 2022-06-07T18:00:32Z

After incorporating onnx/onnx#4249, I still see these failures (there are other failures but I don't expect those to have been fixed by the PR):

test_blackmanwindow_symmetric_expanded
[ERR_ASSERTION]: Expected values to be strictly deep-equal:
+ actual - expected

  [
+   9
-   10
  ]
      + expected - actual

       [
      -  9
      +  10
       ]

test_hammingwindow_symmetric_expanded
[ERR_ASSERTION]: Expected values to be strictly deep-equal:
+ actual - expected

  [
+   9
-   10
  ]
      + expected - actual

       [
      -  9
      +  10
       ]

test_hannwindow_symmetric_expanded
[ERR_ASSERTION]: Expected values to be strictly deep-equal:
+ actual - expected

  [
+   9
-   10
  ]
      + expected - actual

       [
      -  9
      +  10
       ]
      
test_stft
[ERR_ASSERTION]: actual[269]=0.00008392586460104212, expected[269]=-12.363648414611816

@smk2007 @xadupre can you PTAL?

gramalingam · 2022-06-07T18:02:40Z

From what Sheil mentioned, the ORT implementation also needs a change, to support the newly added "periodic" attribute?

garymm · 2022-06-07T18:33:23Z

@gramalingam I don't think that should apply to the _expanded tests which expand the function body before passing it to ORT. Please correct me.

smk2007 · 2022-06-07T19:16:41Z

@gramalingam I don't think that should apply to the _expanded tests which expand the function body before passing it to ORT. Please correct me.

@gramalingam @garymm
Window functions fix
Looked into it. For the symmetric case, the functions are using "Size_FP" when they should be using the original size passed in ("Periodic_Size_FP") to generate the range of values...

STFT fix
The error was in the test again, and is related to incorrect slicing of the input signal. Effectively the input signal was being sliced, and then the dft was being performed, rather than vice-verse. I have validated the output from the onnx test with the ORT implementation:

The fix for STFT has been added to & the fixes for the symmetric tests are here: onnx/onnx#4256

garymm · 2022-06-07T20:19:19Z

These are different tests right? test_dft vs test_stft?

Oops, deleted comment

garymm · 2022-06-07T20:23:44Z

There's currently no way to specify a tolerance for a specific test. I'm looking into adding that.
It'd be ideal if we could find some small change to the implementation to make the output match the reference output more closely so we don't have to relax the tolerance, so if you have any ideas there LMK.

smk2007 · 2022-06-07T22:11:24Z

There's currently no way to specify a tolerance for a specific test. I'm looking into adding that. It'd be ideal if we could find some small change to the implementation to make the output match the reference output more closely so we don't have to relax the tolerance, so if you have any ideas there LMK.

Not sure here, taking a look.

Prior to this every test shared the same global tolerances. This meant that if an ONNX test failed due to a small but acceptable difference in output, the only alternative was to disable the test entirely. In op set 17, the DFT operator is being added. Without this change, the tests for that operator fail because the output is off by about 5e-5. It's better to keep test coverage for this new op rather than disable the test entirely. Also prior to this change, the global tolerances were not shared between JavaScript and Python tests. Now they are. Unblocks microsoft#11640.

garymm · 2022-06-07T22:45:15Z

I put up a PR to support per-test tolerances: #11775

Does anyone know if the C++ onnx_test_runner runs in CI? If so then I'll need to update the PR to cover the C++ as well. So far I haven't found it actually being run in CI.

Unlike the previous code, this handles version strings like "1.12.0rc3". Unblocks microsoft#11640.

Fixes microsoft#11640

Note code is mostly being moved, not added. These ops were previously only registered as Microsoft contrib ops and only built if `BUILD_MS_EXPERIMENTAL_OPS=1`. They've been added to the ai.onnx standard op set in version 17. Main components of this change: * Move the kernels from the conrib_ops directory to the core directory. * Add function bodies for ms experimental ops. This will allow old models that use the contrib ops to continue to function. All the function bodies consist of a single op (the new standard op), so performance overhead should be minimal. Minor clean-up also in this change: * De-duplicate get_scalar_value_from_tensor: put it in a new utils.h. * Fix some bugs that caused compilation errors with the experimental ops. Tested with `build.sh --ms_experimental` * Fix some spelling errors and lint violations. * Replace a couple of switch statements with `MLTypeCallDispatcher`. * Use `InlineVector` instead of `std::vector`. Unblocks microsoft#11640

wschin · 2022-06-10T01:32:14Z

Sorry. My original test script has a bug. This PR, onnx/onnx#4263, should unblock layer normalization tests.

Note code is mostly being moved, not added. These ops were previously only registered as Microsoft contrib ops and only built if `BUILD_MS_EXPERIMENTAL_OPS=1`. They've been added to the ai.onnx standard op set in version 17. Main components of this change: * Move the kernels from the conrib_ops directory to the core directory. * Add function bodies for ms experimental ops. This will allow old models that use the contrib ops to continue to function. All the function bodies consist of a single op (the new standard op), so performance overhead should be minimal. Minor clean-up also in this change: * De-duplicate get_scalar_value_from_tensor: put it in a new utils.h. * Fix some bugs that caused compilation errors with the experimental ops. Tested with `build.sh --ms_experimental` * Fix some spelling errors and lint violations. * Replace a couple of switch statements with `MLTypeCallDispatcher`. * Use `InlineVector` instead of `std::vector`. Unblocks microsoft#11640

Unlike the previous code, this handles version strings like "1.12.0rc3". Unblocks #11640.

Prior to this every test shared the same tolerances. This meant that if an ONNX test failed due to a small but acceptable difference in output, the only alternative was to disable the test entirely. In op set 17, the DFT operator is being added. Without this change, the tests for that operator fail because the output is off by about 5e-5. It's better to keep test coverage for this new op rather than disable the test entirely. Also prior to this change, the global tolerances were not shared between C++, JavaScript, and Python tests. Now they are. Also fix various minor issues raised by linters. Unblocks #11640.

Fixes microsoft#11640

Note code is mostly being moved, not added. These ops were previously only registered as Microsoft contrib ops and only built if `BUILD_MS_EXPERIMENTAL_OPS=1`. They've been added to the ai.onnx standard op set in version 17. Main components of this change: * Move the kernels from the conrib_ops directory to the core directory. * Add function bodies for ms experimental ops. This will allow old models that use the contrib ops to continue to function. All the function bodies consist of a single op (the new standard op), so performance overhead should be minimal. Minor clean-up also in this change: * De-duplicate get_scalar_value_from_tensor: put it in a new utils.h. * Fix some bugs that caused compilation errors with the experimental ops. Tested with `build.sh --ms_experimental` * Fix some spelling errors and lint violations. * Replace a couple of switch statements with `MLTypeCallDispatcher`. * Use `InlineVector` instead of `std::vector`. Unblocks microsoft#11640

Fixes microsoft#11640

Note code is mostly being moved, not added. These ops were previously only registered as Microsoft contrib ops and only built if `BUILD_MS_EXPERIMENTAL_OPS=1`. They've been added to the ai.onnx standard op set in version 17. Main components of this change: * Move the kernels from the conrib_ops directory to the core directory. * Add function bodies for ms experimental ops. This will allow old models that use the contrib ops to continue to function. All the function bodies consist of a single op (the new standard op), so performance overhead should be minimal. Minor clean-up also in this change: * De-duplicate get_scalar_value_from_tensor: put it in a new utils.h. * Fix some bugs that caused compilation errors with the experimental ops. Tested with `build.sh --ms_experimental` * Fix some spelling errors and lint violations. * Replace a couple of switch statements with `MLTypeCallDispatcher`. * Use `InlineVector` instead of `std::vector`. Unblocks microsoft#11640

Fixes microsoft#11640

Follow-ups that need to happen after this and before the next ORT release: * Support SequenceMap with #11731 * Support signal ops with #11778 Follow-ups that need to happen after this but don't necessarily need to happen before the release: * Implement LayerNormalization kernel for opset version 17: #11916 Fixes #11640

Note code is mostly being moved, not added. These ops were previously only registered as Microsoft contrib ops and only built if `BUILD_MS_EXPERIMENTAL_OPS=1`. They've been added to the ai.onnx standard op set in version 17. Main components of this change: * Move the kernels from the conrib_ops directory to the core directory. * Add function bodies for ms experimental ops. This will allow old models that use the contrib ops to continue to function. All the function bodies consist of a single op (the new standard op), so performance overhead should be minimal. Minor clean-up also in this change: * De-duplicate get_scalar_value_from_tensor: put it in a new utils.h. * Fix some bugs that caused compilation errors with the experimental ops. Tested with `build.sh --ms_experimental` * Fix some spelling errors and lint violations. * Replace a couple of switch statements with `MLTypeCallDispatcher`. * Use `InlineVector` instead of `std::vector`. Unblocks microsoft#11640

* Register signal ops for op set 17 Note code is mostly being moved, not added. These ops were previously only registered as Microsoft contrib ops and only built if `BUILD_MS_EXPERIMENTAL_OPS=1`. They've been added to the ai.onnx standard op set in version 17. Main components of this change: * Move the kernels from the conrib_ops directory to the core directory. * Add function bodies for ms experimental ops. This will allow old models that use the contrib ops to continue to function. All the function bodies consist of a single op (the new standard op), so performance overhead should be minimal. Minor clean-up also in this change: * De-duplicate get_scalar_value_from_tensor: put it in a new utils.h. * Fix some bugs that caused compilation errors with the experimental ops. Tested with `build.sh --ms_experimental` * Fix some spelling errors and lint violations. * Replace a couple of switch statements with `MLTypeCallDispatcher`. * Use `InlineVector` instead of `std::vector`. Unblocks #11640

Follow-ups that need to happen after this and before the next ORT release: * Support SequenceMap with #11731 * Support signal ops with #11778 Follow-ups that need to happen after this but don't necessarily need to happen before the release: * Implement LayerNormalization kernel for opset version 17: #11916 Fixes #11640

* Register signal ops for op set 17 Note code is mostly being moved, not added. These ops were previously only registered as Microsoft contrib ops and only built if `BUILD_MS_EXPERIMENTAL_OPS=1`. They've been added to the ai.onnx standard op set in version 17. Main components of this change: * Move the kernels from the conrib_ops directory to the core directory. * Add function bodies for ms experimental ops. This will allow old models that use the contrib ops to continue to function. All the function bodies consist of a single op (the new standard op), so performance overhead should be minimal. Minor clean-up also in this change: * De-duplicate get_scalar_value_from_tensor: put it in a new utils.h. * Fix some bugs that caused compilation errors with the experimental ops. Tested with `build.sh --ms_experimental` * Fix some spelling errors and lint violations. * Replace a couple of switch statements with `MLTypeCallDispatcher`. * Use `InlineVector` instead of `std::vector`. Unblocks #11640

Follow-ups that need to happen after this and before the next ORT release: * Support SequenceMap with #11731 * Support signal ops with #11778 Follow-ups that need to happen after this but don't necessarily need to happen before the release: * Implement LayerNormalization kernel for opset version 17: #11916 Fixes #11640

* Register signal ops for op set 17 Note code is mostly being moved, not added. These ops were previously only registered as Microsoft contrib ops and only built if `BUILD_MS_EXPERIMENTAL_OPS=1`. They've been added to the ai.onnx standard op set in version 17. Main components of this change: * Move the kernels from the conrib_ops directory to the core directory. * Add function bodies for ms experimental ops. This will allow old models that use the contrib ops to continue to function. All the function bodies consist of a single op (the new standard op), so performance overhead should be minimal. Minor clean-up also in this change: * De-duplicate get_scalar_value_from_tensor: put it in a new utils.h. * Fix some bugs that caused compilation errors with the experimental ops. Tested with `build.sh --ms_experimental` * Fix some spelling errors and lint violations. * Replace a couple of switch statements with `MLTypeCallDispatcher`. * Use `InlineVector` instead of `std::vector`. Unblocks #11640

Follow-ups that need to happen after this and before the next ORT release: * Support SequenceMap with #11731 * Support signal ops with #11778 Follow-ups that need to happen after this but don't necessarily need to happen before the release: * Implement LayerNormalization kernel for opset version 17: #11916 Fixes #11640

* Register signal ops for op set 17 Note code is mostly being moved, not added. These ops were previously only registered as Microsoft contrib ops and only built if `BUILD_MS_EXPERIMENTAL_OPS=1`. They've been added to the ai.onnx standard op set in version 17. Main components of this change: * Move the kernels from the conrib_ops directory to the core directory. * Add function bodies for ms experimental ops. This will allow old models that use the contrib ops to continue to function. All the function bodies consist of a single op (the new standard op), so performance overhead should be minimal. Minor clean-up also in this change: * De-duplicate get_scalar_value_from_tensor: put it in a new utils.h. * Fix some bugs that caused compilation errors with the experimental ops. Tested with `build.sh --ms_experimental` * Fix some spelling errors and lint violations. * Replace a couple of switch statements with `MLTypeCallDispatcher`. * Use `InlineVector` instead of `std::vector`. Unblocks #11640

* Update ONNX to 1.12 (#11924) Follow-ups that need to happen after this and before the next ORT release: * Support SequenceMap with #11731 * Support signal ops with #11778 Follow-ups that need to happen after this but don't necessarily need to happen before the release: * Implement LayerNormalization kernel for opset version 17: #11916 Fixes #11640 * Dll version fix ovep4.1 (#11953) * Setting default version values for ovep dlls as well * Update backend_manager.cc Co-authored-by: mayavijx <[email protected]> Co-authored-by: mohsin <[email protected]> * Optimize t5 encoder in beam search (#11926) * ooptimize t5 encoder * update * update * update * refactor expand impl * cuda tests passed * update * alignment * more alignments * review comments * Allow saving on CPU usage for infrequent inference requests by reducing thread spinning (#11841) Introduce Start/Stop threadpool spinning switch Add a session config option to force spinning stop at the end of the Run() * Restructure function inliner (#11731) * Add nested function call tests * Add overload for Specialize * Pass symboltable to onnx shape inference * Avoid renaming empty names * Enable sequence_map tests which failed before this change * Deprecate APIs returning raw ptrs and provide replacements (#11922) Provider better documentation * register signal ops for opset 17 (#11778) * Register signal ops for op set 17 Note code is mostly being moved, not added. These ops were previously only registered as Microsoft contrib ops and only built if `BUILD_MS_EXPERIMENTAL_OPS=1`. They've been added to the ai.onnx standard op set in version 17. Main components of this change: * Move the kernels from the conrib_ops directory to the core directory. * Add function bodies for ms experimental ops. This will allow old models that use the contrib ops to continue to function. All the function bodies consist of a single op (the new standard op), so performance overhead should be minimal. Minor clean-up also in this change: * De-duplicate get_scalar_value_from_tensor: put it in a new utils.h. * Fix some bugs that caused compilation errors with the experimental ops. Tested with `build.sh --ms_experimental` * Fix some spelling errors and lint violations. * Replace a couple of switch statements with `MLTypeCallDispatcher`. * Use `InlineVector` instead of `std::vector`. Unblocks #11640 * Include opset 15 in Conv+BatchNormalization fusion (#11960) * Fix WinML Tests are still targetting deprecated (deleted) experimental signal op definitions (#12006) * fix winml tests * remove legacy test * switch idft -> dft+inverse attr * upgrade opset 13->17 for signal ops tests * [C# Tests] Add support for double tensor output in TestPreTrainedModels. (#12008) Add support for double tensor output in TestPreTrainedModels. * DML EP ResNet50 opset 15 fails in ONNX checker for FusedBatchNormalization lacking training_mode attribute (#12010) FusedBatchNormalization include training_mode attribute * Generalize native op creation (#11539) * create op from ep * read input count from context * create holder to host nodes * fix typo * cast type before comparison * throw error on API fail * silence warning from minimal build * switch to unique_ptr with deleter to host nodes * fix typo * fix build err for minimal * fix build err for minimal * add UT for conv * enable test on CUDA * add comment * fix typo * use gsl::span and string view for Node constructor * Added two APIs - CopyKernelInfo and ReleaseKernelInfo * pass gsl::span by value * switch to span<NodeArg* const> to allow for reference to const containers * fix typo * fix reduced build err * fix reduced build err * refactoring node construction logic * rename exceptions * add input and output count as arguments for op creation * refactor static member * use ORT_CATCH instead of catch * cancel try catch * add static value name map * format input definition and set err code * fix comments * fix typo * [DML EP] Pad operator: Handle negative pad counts (#11974) * Pad fallback to CPU * Added queryPad in operatorRegistration.cpp * Acknowledged PR comments * Used any_of * used none_of instead of any_of Co-authored-by: Sumit Agarwal <[email protected]> * Add warning about future computation change for ConvTranspose with auto_pad (#11984) * Add warning about future computation change for Convtranspose with auto_pad * improve msg * update TODO to make lint happy * update more contents for warning and add if * valid was not infected * move it into kernel registration * parse auto_pad myself * try to use conv_transpose_attrs_.auto_pad directly * update roialign cuda impl to onnx opset16 (#12036) * roialign opset16 * fix * fix * Fix windows eager build break by pinning to torch version 1.11.0 (#12033) Fix windows and linux eager build to torch 1.11.0. * Skip Constant Folding for ops producing an optional type output (#11839) * Disable sequence-type tests since C# infra doesn't support well (#12037) * Extend lifetime of KernelDef when creating a standalone op (#12057) place tmp kernel def as local variable to cover the lifetime of kernel creation * Add targets files for new .net6 frameworks (#12016) * Add net6 targets. Remove maccatalyst as we don't have a native build targetting that. * Set platform in macos targets * Add targetFramework entries * Move NativeLib.DllName definition and set using preprocessor values for simplicity. Couldn't get it to build with the preprocessor based setup when it was in a separate file. Update the nuspec generation to set platform version for .net6 targets. TODO: Validate versions. I copied them from the managed nuget package the packaging pipeline generated prior to adding targets. Possibly w could/should lower some of the versions. Hopefully the need to specify a version goes away when the release version of VS2022 supports .net6. * Try android 31.1 as https://github.com/actions/virtual-environments/blob/main/images/win/Windows2022-Readme.md suggests that should be available on the CI machines * Fix patch version mismatch Add some extra debug info in case it helps * Debug nuget location in CI * Add workspace entry back in * Add steps * One more attempt with hardcoded nuget.exe path and original android31.0 version * Better fix - found explicit nuget download and updated version there. * flake8 fixes * Fix black complaints. * Exit Microsoft_ML_OnnxRuntime_CheckPrerequisites for net6 iOS. * Removed outdated comment * Fix DML custom operators which set descriptor heap to command list (#12059) * Make C# runtest.sh automatically set latest opset (#12039) * Update C# runtest.sh for opset 17 Should have been part of #11924 * get appropriate opset version from onnx doc * use absolute rather than relative path * fix typo in var name * Disable DML command list reuse for Xbox (#12063) disable cl reuse for xbox * Add data type check in ConvAddRelu fusion (#12058) * Add undocumented attribute to disable generation of Java bindings from the Android AAR. (#12075) The generated bindings causes C# build errors that require workaround code. Disabling generation should avoid the need for any workarounds. As the user has the C# ORT package with the C# to C bindings there's no need for binding generation that calls the ORT Java API (which is C# -> Java ->C). * enable the extensions custom build for java and android (#11823) * generate quantization parameter for outputs (#12089) * DML EP Update to DML 1.9 (#12090) * Update to DML 1.9 * Appease obnoxious Python formatting tool * Fix orttraining-linux-ci-pipeline - Symbolic shape infer (#11965) fix symbolic shape error due to upgraded numpy + legacy sympy * check consumers of dq node before swap dq and transpose (#12099) * check consumers of dq node before swap dq and transpose * add unit test Co-authored-by: Gary Miguel <[email protected]> Co-authored-by: Preetha Veeramalai <[email protected]> Co-authored-by: mayavijx <[email protected]> Co-authored-by: mohsin <[email protected]> Co-authored-by: Ye Wang <[email protected]> Co-authored-by: Dmitri Smirnov <[email protected]> Co-authored-by: G. Ramalingam <[email protected]> Co-authored-by: Dwayne Robinson <[email protected]> Co-authored-by: Sheil Kumar <[email protected]> Co-authored-by: Edward Chen <[email protected]> Co-authored-by: sumitsays <[email protected]> Co-authored-by: Sumit Agarwal <[email protected]> Co-authored-by: Chun-Wei Chen <[email protected]> Co-authored-by: George Wu <[email protected]> Co-authored-by: Wil Brady <[email protected]> Co-authored-by: Hariharan Seshadri <[email protected]> Co-authored-by: Wei-Sheng Chin <[email protected]> Co-authored-by: Scott McKay <[email protected]> Co-authored-by: Jeff Bloomfield <[email protected]> Co-authored-by: Justin Stoecker <[email protected]> Co-authored-by: Wenbing Li <[email protected]> Co-authored-by: Yufeng Li <[email protected]> Co-authored-by: pengwa <[email protected]>

Follow-ups that need to happen after this and before the next ORT release: * Support SequenceMap with microsoft#11731 * Support signal ops with microsoft#11778 Follow-ups that need to happen after this but don't necessarily need to happen before the release: * Implement LayerNormalization kernel for opset version 17: microsoft#11916 Fixes microsoft#11640

RyanUnderhill added the component:onnx label May 26, 2022

snnn added the contributions welcome external contributions welcome label May 26, 2022

RyanUnderhill assigned garymm May 26, 2022

garymm added a commit to garymm/onnxruntime that referenced this issue May 26, 2022

Update ONNX to 1.12

5eda5fb

Fixes microsoft#11640

garymm mentioned this issue May 26, 2022

Update ONNX to 1.12 #11642

Closed

garymm added a commit to garymm/onnxruntime that referenced this issue May 31, 2022

Update ONNX to 1.12

614e0a3

Fixes microsoft#11640

garymm added a commit to garymm/onnxruntime that referenced this issue Jun 1, 2022

Update ONNX to 1.12

4604956

Fixes microsoft#11640

garymm mentioned this issue Jun 7, 2022

Support per-test tolerances for ONNX tests #11775

Merged

garymm mentioned this issue Jun 9, 2022

register signal ops for opset 17 #11778

Merged

garymm added a commit to garymm/onnxruntime that referenced this issue Jun 9, 2022

Python backend: use packaging.version to parse ONNX version

aceaa0a

Unlike the previous code, this handles version strings like "1.12.0rc3". Unblocks microsoft#11640.

garymm mentioned this issue Jun 9, 2022

Python backend: use packaging.version to parse ONNX version #11800

Merged

garymm added a commit to garymm/onnxruntime that referenced this issue Jun 9, 2022

Update ONNX to 1.12

c07c2c0

Fixes microsoft#11640

garymm added a commit that referenced this issue Jun 14, 2022

Python backend: use packaging.version to parse ONNX version (#11800)

52f6db1

Unlike the previous code, this handles version strings like "1.12.0rc3". Unblocks #11640.

garymm added a commit to garymm/onnxruntime that referenced this issue Jun 15, 2022

Update ONNX to 1.12

369bc17

Fixes microsoft#11640

garymm added a commit to garymm/onnxruntime that referenced this issue Jun 17, 2022

Update ONNX to 1.12

82ef2b7

Fixes microsoft#11640

garymm added a commit to garymm/onnxruntime that referenced this issue Jun 20, 2022

Update ONNX to 1.12

9eeba74

Fixes microsoft#11640

garymm added a commit to garymm/onnxruntime that referenced this issue Jun 20, 2022

Update ONNX to 1.12

88ed461

Fixes microsoft#11640

garymm mentioned this issue Jun 21, 2022

Update ONNX to 1.12 #11924

Merged

garymm closed this as completed in #11924 Jun 22, 2022

ksaur mentioned this issue Aug 3, 2022

Make onnx dependencies optional microsoft/hummingbird#613

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

ONNX release 1.12.0 #11640

ONNX release 1.12.0 #11640

etiotto commented May 26, 2022 •

edited by garymm

Loading

snnn commented May 26, 2022 •

edited

Loading

RyanUnderhill commented May 26, 2022

garymm commented May 26, 2022

snnn commented May 27, 2022

garymm commented Jun 2, 2022

garymm commented Jun 3, 2022

snnn commented Jun 4, 2022

smk2007 commented Jun 4, 2022 •

edited

Loading

gramalingam commented Jun 5, 2022 •

edited

Loading

garymm commented Jun 7, 2022

gramalingam commented Jun 7, 2022

garymm commented Jun 7, 2022 •

edited

Loading

smk2007 commented Jun 7, 2022 •

edited

Loading

garymm commented Jun 7, 2022

garymm commented Jun 7, 2022

smk2007 commented Jun 7, 2022

garymm commented Jun 7, 2022

wschin commented Jun 10, 2022

ONNX release 1.12.0 #11640

ONNX release 1.12.0 #11640

Comments

etiotto commented May 26, 2022 • edited by garymm Loading

snnn commented May 26, 2022 • edited Loading

RyanUnderhill commented May 26, 2022

garymm commented May 26, 2022

snnn commented May 27, 2022

garymm commented Jun 2, 2022

garymm commented Jun 3, 2022

snnn commented Jun 4, 2022

smk2007 commented Jun 4, 2022 • edited Loading

gramalingam commented Jun 5, 2022 • edited Loading

garymm commented Jun 7, 2022

gramalingam commented Jun 7, 2022

garymm commented Jun 7, 2022 • edited Loading

smk2007 commented Jun 7, 2022 • edited Loading

garymm commented Jun 7, 2022

garymm commented Jun 7, 2022

smk2007 commented Jun 7, 2022

garymm commented Jun 7, 2022

wschin commented Jun 10, 2022

etiotto commented May 26, 2022 •

edited by garymm

Loading

snnn commented May 26, 2022 •

edited

Loading

smk2007 commented Jun 4, 2022 •

edited

Loading

gramalingam commented Jun 5, 2022 •

edited

Loading

garymm commented Jun 7, 2022 •

edited

Loading

smk2007 commented Jun 7, 2022 •

edited

Loading