Skip to content

Commit 96516ae

Browse files
jcwchenjcwchen
authoredJan 9, 2022
Migration to using main branch (onnx#3925)
* add warning announce Signed-off-by: Chun-Wei Chen <jacky82226@gmail.com> * Rename to main branch globally Signed-off-by: Chun-Wei Chen <jacky82226@gmail.com>
·
v1.12.0v1.11.0
1 parent 6053123 commit 96516ae

36 files changed

+102
-99
lines changed
 

‎.azure-pipelines/Linux-CI.yml

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
trigger:
2-
- master
2+
- main
33

44
jobs:
55
- job: 'Test'

‎.azure-pipelines/MacOS-CI.yml

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
trigger:
2-
- master
2+
- main
33

44
jobs:
55
- job: 'Test'

‎.azure-pipelines/Windows-CI.yml

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
trigger:
2-
- master
2+
- main
33

44
jobs:
55

‎.github/workflows/release_linux_aarch64.yml

+2-2
Original file line numberDiff line numberDiff line change
@@ -5,9 +5,9 @@ on:
55
# Run weekly on Monday 00:00
66
- cron: '00 00 * * MON'
77
push:
8-
branches: [master, rel-*]
8+
branches: [main, rel-*]
99
pull_request:
10-
branches: [rel-*, master]
10+
branches: [main, rel-*]
1111
workflow_dispatch:
1212

1313
jobs:

‎.github/workflows/release_linux_i686.yml

+2-2
Original file line numberDiff line numberDiff line change
@@ -5,9 +5,9 @@ on:
55
# Run weekly on Monday 00:00
66
- cron: '00 00 * * MON'
77
push:
8-
branches: [master, rel-*]
8+
branches: [main, rel-*]
99
pull_request:
10-
branches: [master, rel-*]
10+
branches: [main, rel-*]
1111
workflow_dispatch:
1212

1313
jobs:

‎.github/workflows/release_linux_x86_64.yml

+2-2
Original file line numberDiff line numberDiff line change
@@ -5,9 +5,9 @@ on:
55
# Run weekly on Monday 00:00
66
- cron: '00 00 * * MON'
77
push:
8-
branches: [master, rel-*]
8+
branches: [main, rel-*]
99
pull_request:
10-
branches: [master, rel-*]
10+
branches: [main, rel-*]
1111
workflow_dispatch:
1212

1313
jobs:

‎.github/workflows/release_mac.yml

+2-2
Original file line numberDiff line numberDiff line change
@@ -5,9 +5,9 @@ on:
55
# Run weekly on Monday 00:00
66
- cron: '00 00 * * MON'
77
push:
8-
branches: [master, rel-*]
8+
branches: [main, rel-*]
99
pull_request:
10-
branches: [master, rel-*]
10+
branches: [main, rel-*]
1111
workflow_dispatch:
1212

1313
# Use MACOSX_DEPLOYMENT_TARGET=10.12 to produce compatible wheel

‎.github/workflows/release_win.yml

+2-2
Original file line numberDiff line numberDiff line change
@@ -5,9 +5,9 @@ on:
55
# Run weekly on Monday 00:00
66
- cron: '00 00 * * MON'
77
push:
8-
branches: [master, rel-*]
8+
branches: [main, rel-*]
99
pull_request:
10-
branches: [master, rel-*]
10+
branches: [main, rel-*]
1111
workflow_dispatch:
1212

1313
jobs:

‎.github/workflows/weekly_mac_ci.yml

+1-1
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ on:
88
# run weekly on Sunday 23:59
99
- cron: '59 23 * * SUN'
1010
pull_request:
11-
branches: [master, rel-*]
11+
branches: [main, rel-*]
1212
workflow_dispatch:
1313

1414
jobs:

‎.github/workflows/win_no_exception_ci.yml

+2-2
Original file line numberDiff line numberDiff line change
@@ -2,9 +2,9 @@ name: Windows_No_Exception_CI
22

33
on:
44
push:
5-
branches: [ master, rel-* ]
5+
branches: [ main, rel-* ]
66
pull_request:
7-
branches: [ master, rel-* ]
7+
branches: [ main, rel-* ]
88
jobs:
99
build:
1010
runs-on: windows-latest

‎CONTRIBUTING.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -24,7 +24,7 @@ Attend ONNX Steering Committee meetings - they are open to all in the community.
2424

2525
## Contributing code
2626

27-
You can submit a pull request (PR) with your code. The [SIG](https://github.com/onnx/onnx/blob/master/community/sigs.md) or [Working Group](https://github.com/onnx/onnx/blob/master/community/working-groups.md) that is responsible for the area of the project your PR touches will review it and merge once any comments are addressed.
27+
You can submit a pull request (PR) with your code. The [SIG](community/sigs.md) or [Working Group](community/working-groups.md) that is responsible for the area of the project your PR touches will review it and merge once any comments are addressed.
2828

2929
### DCO
3030
ONNX has adopted the [DCO](https://en.wikipedia.org/wiki/Developer_Certificate_of_Origin). All code repositories under ONNX require a DCO. (ONNX previously used a CLA, which is being replaced with the DCO.)
@@ -38,7 +38,7 @@ NOTE: the sign-off is needed for each commit in the PR, not at the PR level.
3838
If you have old commits that are not signed, use the following commands to squash the old PR (original branch) into a single commit. This is an easier way to signoff old commits in old PR.
3939

4040
```bash
41-
git checkout master
41+
git checkout main
4242
git checkout -b temporary_patch # create a new branch as temporary
4343
git merge --squash original_patch # copy from old branch
4444
git branch -d original_patch # remove old branch

‎README.md

+22-19
Original file line numberDiff line numberDiff line change
@@ -1,10 +1,10 @@
11
<!--- SPDX-License-Identifier: Apache-2.0 -->
22

3-
<p align="center"><img width="40%" src="https://github.com/onnx/onnx/raw/master/docs/ONNX_logo_main.png" /></p>
3+
<p align="center"><img width="40%" src="https://github.com/onnx/onnx/raw/main/docs/ONNX_logo_main.png" /></p>
44

5-
[![Build Status](https://img.shields.io/azure-devops/build/onnx-pipelines/onnx/7?label=Linux&logo=Azure-Pipelines)](https://dev.azure.com/onnx-pipelines/onnx/_build/latest?definitionId=7&branchName=master)
6-
[![Build Status](https://img.shields.io/azure-devops/build/onnx-pipelines/onnx/5?label=Windows&logo=Azure-Pipelines)](https://dev.azure.com/onnx-pipelines/onnx/_build/latest?definitionId=5&branchName=master)
7-
[![Build Status](https://img.shields.io/azure-devops/build/onnx-pipelines/onnx/6?label=MacOS&logo=Azure-Pipelines)](https://dev.azure.com/onnx-pipelines/onnx/_build/latest?definitionId=6&branchName=master)
5+
[![Build Status](https://img.shields.io/azure-devops/build/onnx-pipelines/onnx/7?label=Linux&logo=Azure-Pipelines)](https://dev.azure.com/onnx-pipelines/onnx/_build/latest?definitionId=7&branchName=main)
6+
[![Build Status](https://img.shields.io/azure-devops/build/onnx-pipelines/onnx/5?label=Windows&logo=Azure-Pipelines)](https://dev.azure.com/onnx-pipelines/onnx/_build/latest?definitionId=5&branchName=main)
7+
[![Build Status](https://img.shields.io/azure-devops/build/onnx-pipelines/onnx/6?label=MacOS&logo=Azure-Pipelines)](https://dev.azure.com/onnx-pipelines/onnx/_build/latest?definitionId=6&branchName=main)
88
[![CII Best Practices](https://bestpractices.coreinfrastructure.org/projects/3313/badge)](https://bestpractices.coreinfrastructure.org/projects/3313)
99

1010
[Open Neural Network Exchange (ONNX)](https://onnx.ai) is an open ecosystem that empowers AI developers
@@ -29,6 +29,9 @@ ONNX is [widely supported](http://onnx.ai/supported-tools) and can be found in m
2929
* [Graph Optimization](https://github.com/onnx/optimizer)
3030
* [Opset Version Conversion][version_converter]
3131

32+
# NOTICE: ONNX now uses main branch as default branch
33+
Here are the [steps](https://github.com/onnx/onnx/wiki/How-to-migrate-to-main-branch-in-local-repo) from ONNX wiki for migrating to main branch in local repo.
34+
3235
# Contribute
3336
ONNX is a [community project][community]. We encourage you to join the effort and contribute feedback, ideas, and code. You can participate in the [SIGs][sigs] and [Working Groups][wgs] to shape the future of ONNX.
3437

@@ -273,7 +276,7 @@ pytest
273276

274277
# Development
275278

276-
Check out the [contributor guide](https://github.com/onnx/onnx/blob/master/docs/CONTRIBUTING.md) for instructions.
279+
Check out the [contributor guide](https://github.com/onnx/onnx/blob/main/docs/CONTRIBUTING.md) for instructions.
277280

278281
# License
279282

@@ -289,17 +292,17 @@ NOTE: these are absolute rather than repo-relative because we
289292
this document is rendered by PyPI which doesn't seem to handle
290293
relative links properly. See https://github.com/dhimmel/obonet/issues/12.
291294
-->
292-
[overview]: https://github.com/onnx/onnx/blob/master/docs/Overview.md
293-
[ir]: https://github.com/onnx/onnx/blob/master/docs/IR.md
294-
[versioning]: https://github.com/onnx/onnx/blob/master/docs/Versioning.md
295-
[operators]: https://github.com/onnx/onnx/blob/master/docs/Operators.md
296-
[python_api]: https://github.com/onnx/onnx/blob/master/docs/PythonAPIOverview.md
297-
[shape_inference]: https://github.com/onnx/onnx/blob/master/docs/ShapeInference.md
298-
[version_converter]: https://github.com/onnx/onnx/blob/master/docs/VersionConverter.md
299-
[new_op]: https://github.com/onnx/onnx/blob/master/docs/AddNewOp.md
300-
[community]: https://github.com/onnx/onnx/tree/master/community
301-
[sigs]: https://github.com/onnx/onnx/tree/master/community/sigs.md
302-
[wgs]: https://github.com/onnx/onnx/tree/master/community/working-groups.md
303-
[contributing]: https://github.com/onnx/onnx/blob/master/docs/CONTRIBUTING.md
304-
[CMakeLists]: https://github.com/onnx/onnx/blob/master/CMakeLists.txt
305-
[license]: https://github.com/onnx/onnx/blob/master/LICENSE
295+
[overview]: https://github.com/onnx/onnx/blob/main/docs/Overview.md
296+
[ir]: https://github.com/onnx/onnx/blob/main/docs/IR.md
297+
[versioning]: https://github.com/onnx/onnx/blob/main/docs/Versioning.md
298+
[operators]: https://github.com/onnx/onnx/blob/main/docs/Operators.md
299+
[python_api]: https://github.com/onnx/onnx/blob/main/docs/PythonAPIOverview.md
300+
[shape_inference]: https://github.com/onnx/onnx/blob/main/docs/ShapeInference.md
301+
[version_converter]: https://github.com/onnx/onnx/blob/main/docs/VersionConverter.md
302+
[new_op]: https://github.com/onnx/onnx/blob/main/docs/AddNewOp.md
303+
[community]: https://github.com/onnx/onnx/blob/main/community
304+
[sigs]: https://github.com/onnx/onnx/blob/main/community/sigs.md
305+
[wgs]: https://github.com/onnx/onnx/blob/main/community/working-groups.md
306+
[contributing]: https://github.com/onnx/onnx/blob/main/docs/CONTRIBUTING.md
307+
[CMakeLists]: https://github.com/onnx/onnx/blob/main/CMakeLists.txt
308+
[license]: https://github.com/onnx/onnx/blob/main/LICENSE

‎RELEASE-MANAGEMENT.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@ Releases are versioned according to [ONNX Versioning](docs/Versioning.md). This
1111

1212
On a regular basis, new versions of ONNX are published, representing the aggregate of changes in the IR and operator sets. Such releases use semantic versioning to describe the progression of the standard.
1313

14-
The GitHub repo for ONNX provides release branches where the project is stabilized as per the process described here. Release notes are used to communicate the stability and status of a release. The master branch will be used to continue work for subsequent releases.
14+
The GitHub repo for ONNX provides release branches where the project is stabilized as per the process described here. Release notes are used to communicate the stability and status of a release. The main branch will be used to continue work for subsequent releases.
1515

1616
Major, minor and patch releases will have branch names and version numbers reflecting the nature of the change as per semantic versioning definitions.
1717

@@ -33,7 +33,7 @@ to be produced.
3333

3434
- The release manager announces the initial commit for testing. The first
3535
period lasts a week; any regressions found should be fixed, typically via
36-
the master branch. Incomplete features should be done or excised during this
36+
the main branch. Incomplete features should be done or excised during this
3737
period. A distribution can be made available with an -RC1 suffix.
3838

3939
- The release manager announces a second round of testing (unless it's only a

‎community/sc-election-guidelines.md

+3-3
Original file line numberDiff line numberDiff line change
@@ -4,9 +4,9 @@
44

55
## Introduction
66

7-
To encourage community participation and wider adoption in the industry, ONNX has introduced [open governance](https://github.com/onnx/onnx/wiki/Expanded-ONNX-Steering-Committee-Announced!) in March 2018. The governance has three defined structures to propel the development of ONNX project forward: [Steering Committee](https://github.com/onnx/onnx/tree/master/community#steering-committee), [Special Interest Groups (SIGs)](https://github.com/onnx/onnx/tree/master/community#sig---special-interest-groups), and [Working Groups (WGs)](https://github.com/onnx/onnx/tree/master/community#wg---working-groups). While SIGs and WGs primarily focus on the techinical roadmap of ONNX, the Steering Committe is responsible for setting the vision and governance process of the ONNX community.
7+
To encourage community participation and wider adoption in the industry, ONNX has introduced [open governance](https://github.com/onnx/onnx/wiki/Expanded-ONNX-Steering-Committee-Announced!) in March 2018. The governance has three defined structures to propel the development of ONNX project forward: [Steering Committee](/community/readme.md#steering-committee), [Special Interest Groups (SIGs)](/community/readme.md#sig---special-interest-groups), and [Working Groups (WGs)](/community/readme.md#wg---working-groups). While SIGs and WGs primarily focus on the techinical roadmap of ONNX, the Steering Committe is responsible for setting the vision and governance process of the ONNX community.
88

9-
For the first year of its ONNX open governance, representatives from Facebook, Microsoft, AWS, Intel and Nvidia are chosen to serve as the ONNX Steering Committee to help guide the project. The Steering Committee will be elected by the [Contributors](https://github.com/onnx/onnx/tree/master/community#community-roles) in its second year and will be re-elected every year.
9+
For the first year of its ONNX open governance, representatives from Facebook, Microsoft, AWS, Intel and Nvidia are chosen to serve as the ONNX Steering Committee to help guide the project. The Steering Committee will be elected by the [Contributors](/community/readme.md#community-roles) in its second year and will be re-elected every year.
1010

1111
This document is created to provide guidelines for the election process to ensure maximum transparency and fairness.
1212

@@ -28,7 +28,7 @@ Candidate applications will be accepted in April, and the election will be held
2828
## Eligibility
2929

3030
### Eligibility for Steering Committee candidacy
31-
Candidates will be self-nominated, and they do not necessarly need to be a [Contributor](https://github.com/onnx/onnx/tree/master/community#community-roles) to the ONNX project. The duties of the Steering Committee extend beyond simply contributing code to the ONNX project.
31+
Candidates will be self-nominated, and they do not necessarly need to be a [Contributor](/community/readme.md#community-roles) to the ONNX project. The duties of the Steering Committee extend beyond simply contributing code to the ONNX project.
3232

3333

3434
### Eligibility for voting

‎community/sigs.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22

33
# SIGs - Special Interest Groups
44

5-
As described in the ONNX [governance](https://github.com/onnx/onnx/tree/master/community#sig---special-interest-groups), Special Interest Groups (SIGs) are persistent groups responsible for specific parts of the project. SIGs have open and transparent proceedings to develop goals and implement code contributions. SIGs are also responsible for ongoing maintenance of the code in their areas.
5+
As described in the ONNX [governance](/community/readme.md#sig---special-interest-groups), Special Interest Groups (SIGs) are persistent groups responsible for specific parts of the project. SIGs have open and transparent proceedings to develop goals and implement code contributions. SIGs are also responsible for ongoing maintenance of the code in their areas.
66

77
## Joining a SIG
88

‎community/working-groups.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22

33
# Working Groups
44

5-
As described in the ONNX [governance](https://github.com/onnx/onnx/tree/master/community#wg---working-groups), Working Groups (WGs) are temporary groups formed to address issues that cross SIG boundaries. Working Groups have a have a clear goal measured through specific deliverables and disband after the goal is achieved. Working groups do not own artifacts long term; they create specifications, recommendations, and/or code implementations for submission to the relevant SIGs for approval and acceptance.
5+
As described in the ONNX [governance](/community/readme.md#wg---working-groups), Working Groups (WGs) are temporary groups formed to address issues that cross SIG boundaries. Working Groups have a have a clear goal measured through specific deliverables and disband after the goal is achieved. Working groups do not own artifacts long term; they create specifications, recommendations, and/or code implementations for submission to the relevant SIGs for approval and acceptance.
66

77
## Proposing a new working group
88
New Working Groups are created when there is sufficient interest in a topic area and someone volunteers to be the chair for the group and submits a proposal to the steering committee. The chair facilitates the discussion and helps synthesize proposals and decisions.

‎docs/AddNewOp.md

+10-10
Original file line numberDiff line numberDiff line change
@@ -44,33 +44,33 @@ Once the criteria of proposing new operator/function has been satisfied, you wil
4444
4. Write the mathematic formula or a pseudocode in the description. The core algorithm needs to be very clear.
4545
2. Write a reference implementation in Python, this reference implementation should cover all the expected behavior of the operator. Only in extremely rare case, we will waive this requirement.
4646
3. Operator version: check out our
47-
[versioning doc](https://github.com/onnx/onnx/blob/master/docs/Versioning.md#operator-versioning)
47+
[versioning doc](/docs/Versioning.md#operator-versioning)
4848
4. Write unit test, that cover main usage and corner cases.
4949
1. The testing examples will be extracted to the doc.
5050
2. We also generate binary data for it.
51-
3. Example: https://github.com/onnx/onnx/blob/master/onnx/backend/test/case/node/abs.py
52-
5. Add at least one automatic upgrade test for your operator in https://github.com/onnx/onnx/blob/master/onnx/test/automatic_upgrade_test.py using `_test_op_upgrade`. These tests create a given operator at a given opset version (usually the version the operator was introduced in) and test that the version converter is able to convert them to the highest available version. So for a new operator `_test_op_upgrade` will not test anything, but as soon as the operator gets updated in a future opset the test will autoamtically become nontrivial.
51+
3. Example: [onnx/backend/test/case/node/abs.py](/onnx/backend/test/case/node/abs.py)
52+
5. Add at least one automatic upgrade test for your operator in [onnx/test/automatic_upgrade_test.py](/onnx/test/automatic_upgrade_test.py) using `_test_op_upgrade`. These tests create a given operator at a given opset version (usually the version the operator was introduced in) and test that the version converter is able to convert them to the highest available version. So for a new operator `_test_op_upgrade` will not test anything, but as soon as the operator gets updated in a future opset the test will autoamtically become nontrivial.
5353
6. Update the documentation and generate the test data.
54-
1. Running [the script](https://github.com/onnx/onnx/blob/master/tools/update_doc.sh)
54+
1. Running [the script](/tools/update_doc.sh)
5555
to update the doc and generate the test data.
5656
7. Shape Inference function
5757
1. Please provide a shape inference function in cases where it is meaningful and applicable.
5858
2. In cases where shape inference is not possible, it must have logic to perform
5959
rank inference at the very least (adding right amount of dimensions to the output shape)
60-
3. Shape inference functions must be accompanied by unit tests (https://github.com/onnx/onnx/blob/master/onnx/test/shape_inference_test.py).
61-
4. You can refer to the shape inference function for the `TopK` operator while implementing your own function (https://github.com/onnx/onnx/blob/master/onnx/defs/math/defs.cc#L943)
60+
3. Shape inference functions must be accompanied by unit tests ([onnx/test/shape_inference_test.py](/onnx/test/shape_inference_test.py)).
61+
4. You can refer to the shape inference function for the `TopK` operator while implementing your own function ([onnx/defs/math/defs.cc](/onnx/defs/math/defs.cc))
6262

6363
### Example to Follow
6464
[PR 1959](https://github.com/onnx/onnx/pull/1959) is a good example to follow.
6565

6666
## Step 3: PR Review by Operators SIG <a name="step3_new_operator_or_function"></a>
67-
The [Operators SIG](https://github.com/onnx/sigs/tree/master/operators) is responsible for the operators/functions in the ONNX specification. The SIG regularly meets and reviews PRs.
67+
The [Operators SIG](https://github.com/onnx/sigs/tree/main/operators) is responsible for the operators/functions in the ONNX specification. The SIG regularly meets and reviews PRs.
6868

6969
### Sign-off
70-
At least two sign-off from the Operators SIG [contributors](https://github.com/onnx/onnx/tree/master/community#community-roles).
70+
At least two sign-off from the Operators SIG [contributors](https://github.com/onnx/onnx/tree/main/community#community-roles).
7171

7272
## Step 4: ONNX release <a name="step4_new_operator_or_function"></a>
73-
Once the PR is reviewed and signed off by the Operators SIG, it will be merged. Your new operator/function will be part of the master branch and available to anyone building from source. These are not official releases. ONNX periodically releases official new versions that are a snapshot of the master branch. Your new operator/function will be part of that release.
73+
Once the PR is reviewed and signed off by the Operators SIG, it will be merged. Your new operator/function will be part of the main branch and available to anyone building from source. These are not official releases. ONNX periodically releases official new versions that are a snapshot of the main branch. Your new operator/function will be part of that release.
7474

7575
# Removing operator or function <a name="removing_operator_or_function"></a>
7676
There are a lot of reasons for removing existing ONNX operator or function, such us being replaced with different operator or can be decomposed by a set of other operators. This document describes the criteria of removing an existing ONNX operator from the standard.
@@ -82,7 +82,7 @@ Any operator in ONNX was added because it was required by a model and/or framewo
8282
* Or a set of primitive operators that together can implement the same functionality and behavior of the deprecated operator (Function).
8383
* If the deprecated operator can be decomposed by existing operators then it must be converted to a function.
8484
* If replacement isn’t in ONNX standard yet, then add the replacement operator or set of operators first.
85-
* Add a version adapter which turns the operator into its replacement for the version converter. Example: https://github.com/onnx/onnx/blob/master/onnx/version_converter/adapters/upsample_9_10.h
85+
* Add a version adapter which turns the operator into its replacement for the version converter. Example: [onnx/version_converter/adapters/upsample_9_10.h](/onnx/version_converter/adapters/upsample_9_10.h)
8686
* No grace period is needed for deprecated operators.
8787

8888
## Removing function <a name="removing_function"></a>

‎docs/CIPipelines.md

+14-14
Original file line numberDiff line numberDiff line change
@@ -6,28 +6,28 @@
66

77
|   | When it runs | Config | Test |
88
-- | -- | -- | -- |
9-
[Linux-CI](https://github.com/onnx/onnx/blob/master/.azure-pipelines/Linux-CI.yml) | Every PR | <ul><li>Ubuntu-18.04</li><li>DEBUG=1 or 0</li><li>ONNX_USE_LITE_PROTO=ON or OFF</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_BUILD_TESTS=1</li><li>ONNX_WERROR=ON</li><li>ONNX_ML=1 or 0</li></ul>| <ul><li>ONNX C++ tests</li><li>Test flake8</li><li>Test doc generation</li><li>Test proto generation</li><li>mypy typecheck</li><li>Verify backend node data</li><li>Verify node test generation</li></ul> |
10-
[Windows-CI](https://github.com/onnx/onnx/blob/master/.azure-pipelines/Windows-CI.yml) | Every PR  | <ul><li>vs2017-win2016</li><li>ONNX_USE_LITE_PROTO=ON</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=ON</li><li>ONNX_BUILD_TESTS=1</li><li>ONNX_WERROR=ON</li><li>ONNX_ML=1 or 0</li></ul>| <ul><li>Test building ONNX in conda environment</li><li>Test doc generation</li><li>Test proto generation</li><li>mypy typecheck</li></ul> |
11-
[Mac-CI](https://github.com/onnx/onnx/blob/master/.azure-pipelines/MacOS-CI.yml) | Every PR  | <ul><li>macOS-10.14</li><li>DEBUG=1</li><li>ONNX_USE_LITE_PROTO=ON or OFF</li><li>ONNX_ML=1 or 0</li><li>ONNX_BUILD_TESTS=1</li><li>ONNX_WERROR=ON</li></ul>| <ul><li>ONNX C++ tests</li><li>Test flake8</li><li>Test doc generation</li><li>Test proto generation</li></ul>|
12-
[Windows_No_Exception CI](https://github.com/onnx/onnx/blob/master/.github/workflows/win_no_exception_ci.yml) | Every PR  | <ul><li>vs2019-winlatest</li><li>ONNX_DISABLE_EXCEPTIONS=ON</li><li>ONNX_USE_LITE_PROTO=ON</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_ML=1</li><li>ONNX_USE_MSVC_STATIC_RUNTIME=ON</li><li>ONNX_DISABLE_STATIC_REGISTRATION=ON or OFF</li></ul>| <ul><li>Only ONNX C++ tests</li><li>Test selective schema loading</li></ul> |
13-
[WindowsRelease](https://github.com/onnx/onnx/blob/master/.github/workflows/release_win.yml) | <ul><li>Main branch</li><li>Release branch</li><li>Weekly(1)</li></ul> | <ul><li>Latest Windows</li><li>x86 and x64</li><li>ONNX_USE_LITE_PROTO=ON</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_ML=1</li><li>ONNX_USE_MSVC_STATIC_RUNTIME=OFF</li></ul>| <ul><li> Release Windows wheel</li><li>Release onnx-weekly package</li><li>Verify backend node data</li><li>Verify node test generation</li><li>Verify with different dependency versions - latest numpy version, latest and min supported protobuf version(2)</li><li>Verify ONNX with the latest [ort-nightly](https://test.pypi.org/project/ort-nightly/)(3).</li></ul> |
14-
[LinuxRelease_aarch64](https://github.com/onnx/onnx/blob/master/.github/workflows/release_linux_aarch64.yml) | <ul><li>Main branch</li><li>Release branch</li><li>Weekly</li></ul>  | <ul><li>Latest manylinux2014_aarch64</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_ML=1</li></ul>| <ul><li> Release Linux aarch64 wheel</li><li>Release onnx-weekly package</li><li>Verify backend node data</li><li>Verify node test generation</li><li>Verify with different dependency versions - latest numpy version, latest and min supported protobuf version</li><li>Verify ONNX with the latest ort-nightly.</li></ul> |
15-
[LinuxRelease_i686](https://github.com/onnx/onnx/blob/master/.github/workflows/release_linux_i686.yml) | <ul><li>Main branch</li><li>Release branch</li><li>Weekly</li></ul>  | <ul><li>Latest manylinux2010_x86_64</li><li> Release Linux i686 wheel</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_ML=1</li></ul> | <ul><li>Release onnx-weekly package</li><li>Verify backend node data</li><li>Verify node test generation</li><li>Verify with different dependency versions - latest numpy version, latest and min supported protobuf version</li></ul>
16-
[LinuxRelease_x86_64](https://github.com/onnx/onnx/blob/master/.github/workflows/release_linux_x86_64.yml) | <ul><li>Main branch</li><li>Release branch</li><li>Weekly</li></ul> | <ul><li>Latest manylinux2014_aarch64</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_ML=1</li></ul>| <ul><li> Release Linux x86_64 wheel</li><li>Release onnx-weekly package</li><li>Test TEST_HUB=1(4)</li><li>Verify backend node data</li><li>Verify node test generation</li></li><li>Verify with different dependency versions - latest numpy version, latest and min supported protobuf version</li><li>Verify ONNX with the latest ort-nightly.</li></ul> |
17-
[MacRelease](https://github.com/onnx/onnx/blob/master/.github/workflows/release_win.yml) | <ul><li>Main branch</li><li>Release branch</li><li>Weekly</li></ul> | <ul><li>macos-10.15</li><li> MACOSX_DEPLOYMENT_TARGET=10.12(5) </li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_ML=1</li></ul>| <ul><li>Release Mac wheel</li><li>Release onnx-weekly package</li><li>Verify backend node data</li><li>Verify node test generation</li><li>Verify with different dependency versions - latest numpy version, latest and min supported protobuf version</li><li>Verify ONNX with the latest ort-nightly.</li><li>Test source distribution generation</li><li>Test build with source distribution</li><li>Release onnx-weekly source distribution</li></ul>
18-
[Weekly CI with latest onnx.checker](https://github.com/onnx/onnx/blob/master/.github/workflows/weekly_mac_ci.yml) | weekly(6) |<ul><li>macos-latest</li><li>MACOSX_DEPLOYMENT_TARGET=10.15</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_ML=1</li></ul>| <ul><li>Test latest ONNX checker</li><li>Test latest ONNX shape inference</li><li>With all models from [onnx/models](https://github.com/onnx/models)(7)</li></ul> |  
9+
[Linux-CI](/.azure-pipelines/Linux-CI.yml) | Every PR | <ul><li>Ubuntu-18.04</li><li>DEBUG=1 or 0</li><li>ONNX_USE_LITE_PROTO=ON or OFF</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_BUILD_TESTS=1</li><li>ONNX_WERROR=ON</li><li>ONNX_ML=1 or 0</li></ul>| <ul><li>ONNX C++ tests</li><li>Test flake8</li><li>Test doc generation</li><li>Test proto generation</li><li>mypy typecheck</li><li>Verify backend node data</li><li>Verify node test generation</li></ul> |
10+
[Windows-CI](/.azure-pipelines/Windows-CI.yml) | Every PR  | <ul><li>vs2017-win2016</li><li>ONNX_USE_LITE_PROTO=ON</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=ON</li><li>ONNX_BUILD_TESTS=1</li><li>ONNX_WERROR=ON</li><li>ONNX_ML=1 or 0</li></ul>| <ul><li>Test building ONNX in conda environment</li><li>Test doc generation</li><li>Test proto generation</li><li>mypy typecheck</li></ul> |
11+
[Mac-CI](/.azure-pipelines/MacOS-CI.yml) | Every PR  | <ul><li>macOS-10.14</li><li>DEBUG=1</li><li>ONNX_USE_LITE_PROTO=ON or OFF</li><li>ONNX_ML=1 or 0</li><li>ONNX_BUILD_TESTS=1</li><li>ONNX_WERROR=ON</li></ul>| <ul><li>ONNX C++ tests</li><li>Test flake8</li><li>Test doc generation</li><li>Test proto generation</li></ul>|
12+
[Windows_No_Exception CI](/.github/workflows/win_no_exception_ci.yml) | Every PR  | <ul><li>vs2019-winlatest</li><li>ONNX_DISABLE_EXCEPTIONS=ON</li><li>ONNX_USE_LITE_PROTO=ON</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_ML=1</li><li>ONNX_USE_MSVC_STATIC_RUNTIME=ON</li><li>ONNX_DISABLE_STATIC_REGISTRATION=ON or OFF</li></ul>| <ul><li>Only ONNX C++ tests</li><li>Test selective schema loading</li></ul> |
13+
[WindowsRelease](/.github/workflows/release_win.yml) | <ul><li>Main branch</li><li>Release branch</li><li>Weekly(1)</li></ul> | <ul><li>Latest Windows</li><li>x86 and x64</li><li>ONNX_USE_LITE_PROTO=ON</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_ML=1</li><li>ONNX_USE_MSVC_STATIC_RUNTIME=OFF</li></ul>| <ul><li> Release Windows wheel</li><li>Release onnx-weekly package</li><li>Verify backend node data</li><li>Verify node test generation</li><li>Verify with different dependency versions - latest numpy version, latest and min supported protobuf version(2)</li><li>Verify ONNX with the latest [ort-nightly](https://test.pypi.org/project/ort-nightly/)(3).</li></ul> |
14+
[LinuxRelease_aarch64](/.github/workflows/release_linux_aarch64.yml) | <ul><li>Main branch</li><li>Release branch</li><li>Weekly</li></ul>  | <ul><li>Latest manylinux2014_aarch64</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_ML=1</li></ul>| <ul><li> Release Linux aarch64 wheel</li><li>Release onnx-weekly package</li><li>Verify backend node data</li><li>Verify node test generation</li><li>Verify with different dependency versions - latest numpy version, latest and min supported protobuf version</li><li>Verify ONNX with the latest ort-nightly.</li></ul> |
15+
[LinuxRelease_i686](/.github/workflows/release_linux_i686.yml) | <ul><li>Main branch</li><li>Release branch</li><li>Weekly</li></ul>  | <ul><li>Latest manylinux2010_x86_64</li><li> Release Linux i686 wheel</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_ML=1</li></ul> | <ul><li>Release onnx-weekly package</li><li>Verify backend node data</li><li>Verify node test generation</li><li>Verify with different dependency versions - latest numpy version, latest and min supported protobuf version</li></ul>
16+
[LinuxRelease_x86_64](/.github/workflows/release_linux_x86_64.yml) | <ul><li>Main branch</li><li>Release branch</li><li>Weekly</li></ul> | <ul><li>Latest manylinux2014_aarch64</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_ML=1</li></ul>| <ul><li> Release Linux x86_64 wheel</li><li>Release onnx-weekly package</li><li>Test TEST_HUB=1(4)</li><li>Verify backend node data</li><li>Verify node test generation</li></li><li>Verify with different dependency versions - latest numpy version, latest and min supported protobuf version</li><li>Verify ONNX with the latest ort-nightly.</li></ul> |
17+
[MacRelease](/.github/workflows/release_win.yml) | <ul><li>Main branch</li><li>Release branch</li><li>Weekly</li></ul> | <ul><li>macos-10.15</li><li> MACOSX_DEPLOYMENT_TARGET=10.12(5) </li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_ML=1</li></ul>| <ul><li>Release Mac wheel</li><li>Release onnx-weekly package</li><li>Verify backend node data</li><li>Verify node test generation</li><li>Verify with different dependency versions - latest numpy version, latest and min supported protobuf version</li><li>Verify ONNX with the latest ort-nightly.</li><li>Test source distribution generation</li><li>Test build with source distribution</li><li>Release onnx-weekly source distribution</li></ul>
18+
[Weekly CI with latest onnx.checker](/.github/workflows/weekly_mac_ci.yml) | weekly(6) |<ul><li>macos-latest</li><li>MACOSX_DEPLOYMENT_TARGET=10.15</li><li>ONNX_USE_PROTOBUF_SHARED_LIBS=OFF</li><li>ONNX_ML=1</li></ul>| <ul><li>Test latest ONNX checker</li><li>Test latest ONNX shape inference</li><li>With all models from [onnx/models](https://github.com/onnx/models)(7)</li></ul> |  
1919

2020
* (1) When the release CIs will run:
2121
* After a PR has been merged into main/rel-* branch
2222
* Run weekly (Sunday midnight) and release Python wheel to [onnx-weekly](https://test.pypi.org/project/onnx-weekly/) package on TestPyPI.
2323
* Any PR targeting rel-* branch
2424
* To manually run them, add a PR label "run release CIs" (only maintainers have permission).
25-
* (2) Minimum supported versions are listed [here](https://github.com/onnx/onnx/blob/master/requirements.txt).
26-
* (3) [Test](https://github.com/onnx/onnx/blob/master/onnx/test/test_with_ort.py) ONNX Python wheel with `onnxruntime.InferenceSession` from latest ONNXRuntime. Please note that ort-nightly does not support Linux-i686 and Windows-x86 thus their verification are skipped.
27-
* (4) TEST_HUB=1 will test [onnx.hub](https://github.com/onnx/onnx/blob/master/onnx/test/hub_test.py) by using this API to download an ONNX model from onnx/models. This test is restricted to only 1 pipeline for saving quota usage.
25+
* (2) Minimum supported versions are listed [here](/requirements.txt).
26+
* (3) [Test](/onnx/test/test_with_ort.py) ONNX Python wheel with `onnxruntime.InferenceSession` from latest ONNXRuntime. Please note that ort-nightly does not support Linux-i686 and Windows-x86 thus their verification are skipped.
27+
* (4) TEST_HUB=1 will test [onnx.hub](/onnx/test/hub_test.py) by using this API to download an ONNX model from onnx/models. This test is restricted to only 1 pipeline for saving quota usage.
2828
* (5) Although the build envioronment is macos-10.15, use MACOSX_DEPLOYMENT_TARGET=10.12 and -p [macosx_10_12_x86_64](https://github.com/onnx/onnx/blob/2e048660ffa8243596aaf3338e60c7c0575458f2/.github/workflows/release_mac.yml#L74) to force the wheel to support 10.12+.
2929

3030
* (6):
3131
* The ONNX Model Zoo test will run weekly (Sunday midnight)
3232
* To manually trigger it, add a PR label "test ONNX Model Zoo" (only maintainers have permission). Please note that it will need a lot of download bandwidth from [onnx/models](https://github.com/onnx/models) so use it with caution.
33-
* (7) Some old deprecated models (opset-1) are [skipped](https://github.com/onnx/onnx/blob/master/workflow_scripts/config.py).
33+
* (7) Some old deprecated models (opset-1) are [skipped](/workflow_scripts/config.py).

‎docs/CONTRIBUTING.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -99,7 +99,7 @@ Every PR needs to pass CIs before merge. CI pipelines details are [here](CIPipel
9999

100100
# License
101101

102-
[Apache License v2.0](https://github.com/onnx/onnx/blob/master/LICENSE)
102+
[Apache License v2.0](/LICENSE)
103103

104104
# Code of Conduct
105105

‎docs/ImplementingAnOnnxBackend.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ An ONNX backend is a library that can run ONNX models. Since many deep learning
88

99
#### Unified backend interface
1010

11-
ONNX has defined a unified (Python) backend interface at https://github.com/onnx/onnx/blob/master/onnx/backend/base.py.
11+
ONNX has defined a unified (Python) backend interface at [onnx/backend/base.py](/onnx/backend/base.py).
1212

1313
There are three core concepts in this interface: `Device`, `Backend` and `BackendRep`.
1414

‎docs/ManagingExperimentalOps.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -20,11 +20,11 @@ Old operator |New Operator
2020

2121
## Adding Experimental Operators [Deprecated - as of v1.5 experimental ops are no longer supported]
2222

23-
The experimental flag in ONNX operator definitions indicates that a customer of ONNX may not be able to take a long term dependency on that op. Ops in the ONNX namespace (ai.onnx) in the _master_ branch, whether experimental or not, go through the regular review process.
23+
The experimental flag in ONNX operator definitions indicates that a customer of ONNX may not be able to take a long term dependency on that op. Ops in the ONNX namespace (ai.onnx) in the _main_ branch, whether experimental or not, go through the regular review process.
2424

2525
Experimental ops that are being worked on that do not have consensus yet can be managed in one of 2 ways:
2626
1. Use a fork or branch – what you do in the fork or branch is entirely up to you. When you are ready, you can submit a PR using the normal process. This is the recommended way.
27-
2. If a fork/branch is not workable (for example due to complexity of mapping different branches between multiple repos), put the experimental ops in a custom namespace in the master branch.
27+
2. If a fork/branch is not workable (for example due to complexity of mapping different branches between multiple repos), put the experimental ops in a custom namespace in the main branch.
2828
The specific process for this is:
2929
* Submit an Issue with a proposal explaining the motivation and plan. It does not need to include detailed technical design. Issues will be tagged as "experimental op".
3030
* Reviewers will generally approve by default unless the proposal directly conflicts with existing ops or somehow goes against general ONNX strategy. Approval is indicated by adding the "experiment approved" tag.

‎docs/OnnxBackendTest.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -15,6 +15,6 @@ There are two types of tests in this suite – Node Tests and Model Tests:
1515

1616
As ONNX aims to become the spec of deep learning models format, it's important to ensure that there is no ambiguity in each ONNX operator's definition; adding more test cases is the only way to enforce this.
1717

18-
Node Tests are created as Python/Numpy code in https://github.com/onnx/onnx/tree/master/onnx/backend/test/case/node, and then exported to protobuf files to https://github.com/onnx/onnx/tree/master/onnx/backend/test/data/node as the source of truth by invoking the shell command `backend-test-tools generate-data`. Test cases of each operator lives in one standalone file, e.g. for the operator [Add](https://github.com/onnx/onnx/blob/master/docs/Operators.md#Add), its test cases are in [add.py](https://github.com/onnx/onnx/blob/master/onnx/backend/test/case/node/add.py), and each `expect(...)` statement in the code corresponds to one test case. The source code of all `export.*` functions will be also embedded as example code snippets in the [Operators documentation page](https://github.com/onnx/onnx/blob/master/docs/Operators.md). You are contributing to both the test and the documentation!
18+
Node Tests are created as Python/Numpy code in [onnx/backend/test/case/node](/onnx/backend/test/case/node), and then exported to protobuf files to [onnx/backend/test/data/node](/onnx/backend/test/data/node) as the source of truth by invoking the shell command `backend-test-tools generate-data`. Test cases of each operator lives in one standalone file, e.g. for the operator [Add](/docs/Operators.md#Add), its test cases are in [add.py](/onnx/backend/test/case/node/add.py), and each `expect(...)` statement in the code corresponds to one test case. The source code of all `export.*` functions will be also embedded as example code snippets in the [Operators documentation page](/docs/Operators.md). You are contributing to both the test and the documentation!
1919

2020
For Model Tests, since each model protobuf file can be large in size, we don't place the file directly in the repo. Rather, we upload them to the cloud, and download them on demand when running the tests. Each test case consists of one model definition protobuf file, and several pairs of input and output files. Adding a new test case involves some manual work from admins (like uploading the files to the cloud), so if you have an ONNX model that you would like to contribute, please contact us.

‎docs/OnnxReleases.md

+7-7
Original file line numberDiff line numberDiff line change
@@ -10,18 +10,18 @@ The ONNX project, going forward, will plan to release roughly on a four month ca
1010
* Prepare a change log for the release –
1111
* ``git log --pretty=format:"%h - %s" <tag of the previous release>...<new tag>``
1212
* And draft a new release statement - https://github.com/onnx/onnx/releases listing out the new features and bug fixes, and potential changes being introduced in the release.
13-
* Before creating the release branch, increase `VERSION_NUMBER` in the main branch. The following files will be updated: [VERSION_NUMBER file](https://github.com/onnx/onnx/blob/master/VERSION_NUMBER) and
14-
[version.h](../onnx/common/version.h)
13+
* Before creating the release branch, increase `VERSION_NUMBER` in the main branch. The following files will be updated: [VERSION_NUMBER file](/VERSION_NUMBER) and
14+
[version.h](/onnx/common/version.h)
1515

1616
* Please use a VERSION_NUMBER smaller than the target (release VERSION_NUMBER) and larger than the previous one to test TestPyPI before using the target VERSION_NUMBER.
1717

1818
* Make sure that the IR version number and opset version numbers are up-to-date in
19-
[ONNX proto files](../onnx/onnx.in.proto),
19+
[ONNX proto files](/onnx/onnx.in.proto),
2020
[Versioning.md](Versioning.md),
21-
[schema.h](../onnx/defs/schema.h),
22-
[helper.py](../onnx/helper.py) and [helper_test.py](../onnx/test/helper_test.py). Please note that this also needs to be happened in the main branch before creating the release branch.
21+
[schema.h](/onnx/defs/schema.h),
22+
[helper.py](/onnx/helper.py) and [helper_test.py](/onnx/test/helper_test.py). Please note that this also needs to be happened in the main branch before creating the release branch.
2323

24-
* Create a release branch (please use rel-* as the branch name) from master. Checkout the release tag in a clean branch on your local repo. Make sure all tests pass on that branch.
24+
* Create a release branch (please use rel-* as the branch name) from main. Checkout the release tag in a clean branch on your local repo. Make sure all tests pass on that branch.
2525
* Create an issue in onnxruntime to update onnx commit in onnxruntime to the release branch commit and run all the CI and packaging pipelines.
2626

2727
## Upload to TestPyPI
@@ -70,7 +70,7 @@ The ONNX project, going forward, will plan to release roughly on a four month ca
7070

7171
**Partner Validation**
7272

73-
* Test with onnxruntime package: To test the interaction with onnxruntime, use ONNX functions like `load`, `checker.check_model`, `shape_inference.infer_shapes`, `save` with onnxruntime functions like `InferenceSession` and `InferenceSession.run` on certain example ONNX model. For example, run the test script from [test_with_ort.py](../onnx/test/test_with_ort.py) with installed onnxruntime package.
73+
* Test with onnxruntime package: To test the interaction with onnxruntime, use ONNX functions like `load`, `checker.check_model`, `shape_inference.infer_shapes`, `save` with onnxruntime functions like `InferenceSession` and `InferenceSession.run` on certain example ONNX model. For example, run the test script from [test_with_ort.py](/onnx/test/test_with_ort.py) with installed onnxruntime package.
7474

7575
* Test with ONNX converters: Create GitHub issues in converters repos to provide them the package links and have them test the TestPyPI packages.
7676
* https://github.com/pytorch/pytorch

‎docs/PythonAPIOverview.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -108,7 +108,7 @@ from onnx import AttributeProto, TensorProto, GraphProto
108108

109109

110110
# The protobuf definition can be found here:
111-
# https://github.com/onnx/onnx/blob/master/onnx/onnx.proto
111+
# https://github.com/onnx/onnx/blob/main/onnx/onnx.proto
112112

113113

114114
# Create one input (ValueInfoProto)
@@ -240,7 +240,7 @@ original_model = onnx.load(model_path)
240240
print('The model before conversion:\n{}'.format(original_model))
241241

242242
# A full list of supported adapters can be found here:
243-
# https://github.com/onnx/onnx/blob/master/onnx/version_converter.py#L21
243+
# https://github.com/onnx/onnx/blob/main/onnx/version_converter.py#L21
244244
# Apply the version conversion on the original model
245245
converted_model = version_converter.convert_version(original_model, <int target_version>)
246246

‎docs/proposals/NLPinONNXproposal.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -41,7 +41,7 @@ Vanilla seq2seq with attention and non-backtracking beam search does NOT include
4141

4242
## Standard Recurrent Network Constructs
4343

44-
Standard recurrent network architectures such as LSTM or GRU are very common, and we can get very far supporting these. We already have the [LSTM](https://github.com/onnx/onnx/blob/master/docs/Operators.md#LSTM) and [GRU](https://github.com/onnx/onnx/blob/master/docs/Operators.md#GRU) operators, which execute the standard LSTM and GRU[4] operations over a sequence of inputs. These high-level operators are great, since they give backends a semantic view of the computation to be performed, and thus backends can make informed decisions about optimization. Many NLP use cases can get away with using just these operators.
44+
Standard recurrent network architectures such as LSTM or GRU are very common, and we can get very far supporting these. We already have the [LSTM](/docs/Operators.md#LSTM) and [GRU](/docs/Operators.md#GRU) operators, which execute the standard LSTM and GRU[4] operations over a sequence of inputs. These high-level operators are great, since they give backends a semantic view of the computation to be performed, and thus backends can make informed decisions about optimization. Many NLP use cases can get away with using just these operators.
4545

4646
[4] http://colah.github.io/posts/2015-08-Understanding-LSTMs/
4747

‎onnx/checker.cc

+1-1
Original file line numberDiff line numberDiff line change
@@ -758,7 +758,7 @@ void check_model_local_functions(
758758
const ModelProto& model,
759759
const CheckerContext& ctx,
760760
const LexicalScopeContext& parent_lex) {
761-
// make a copy of model opset imports to maintain a master copy of opset imports across the model and
761+
// make a copy of model opset imports to maintain a main copy of opset imports across the model and
762762
// all model local functions to verify opset compatibility
763763
std::unordered_map<std::string, int> model_opset_imports(ctx.get_opset_imports());
764764

‎onnx/examples/make_model.ipynb

+1-1
Original file line numberDiff line numberDiff line change
@@ -90,7 +90,7 @@
9090
"\n",
9191
"\n",
9292
"# The protobuf definition can be found here:\n",
93-
"# https://github.com/onnx/onnx/blob/master/onnx/onnx.proto\n",
93+
"# https://github.com/onnx/onnx/blob/main/onnx/onnx.proto\n",
9494
"\n",
9595
"\n",
9696
"# Create one input (ValueInfoProto)\n",

‎onnx/helper.py

+1-1
Original file line numberDiff line numberDiff line change
@@ -24,7 +24,7 @@
2424
VersionTableType = List[VersionRowType]
2525
AssignmentBindingType = List[Tuple[Text, Text]]
2626

27-
# This is a copy of the documented version in https://github.com/onnx/onnx/blob/master/docs/Versioning.md#released-versions
27+
# This is a copy of the documented version in https://github.com/onnx/onnx/blob/main/docs/Versioning.md#released-versions
2828
# Both must be updated whenever a new version of ONNX is released.
2929
VERSION_TABLE = [
3030
# Release-version, IR version, ai.onnx version, ai.onnx.ml version, (optional) ai.onnx.training version

‎onnx/onnx-data.in.proto

+1-1
Original file line numberDiff line numberDiff line change
@@ -29,7 +29,7 @@ import "onnx/onnx.proto";
2929
// no symbolic/constant value. Finally, "Sequence<Tensor<float, omitted>>" means
3030
// that the different tensors can have different ranks, when the "shape" itself
3131
// is omitted from the tensor-type. For a more complete description, refer to
32-
// https://github.com/onnx/onnx/blob/master/docs/IR.md#static-tensor-shapes.
32+
// https://github.com/onnx/onnx/blob/main/docs/IR.md#static-tensor-shapes.
3333
//
3434
message SequenceProto {
3535

‎onnx/onnx-data.proto

+1-1
Original file line numberDiff line numberDiff line change
@@ -30,7 +30,7 @@ import "onnx/onnx-ml.proto";
3030
// no symbolic/constant value. Finally, "Sequence<Tensor<float, omitted>>" means
3131
// that the different tensors can have different ranks, when the "shape" itself
3232
// is omitted from the tensor-type. For a more complete description, refer to
33-
// https://github.com/onnx/onnx/blob/master/docs/IR.md#static-tensor-shapes.
33+
// https://github.com/onnx/onnx/blob/main/docs/IR.md#static-tensor-shapes.
3434
//
3535
message SequenceProto {
3636

‎onnx/onnx-data.proto3

+1-1
Original file line numberDiff line numberDiff line change
@@ -30,7 +30,7 @@ import "onnx/onnx-ml.proto3";
3030
// no symbolic/constant value. Finally, "Sequence<Tensor<float, omitted>>" means
3131
// that the different tensors can have different ranks, when the "shape" itself
3232
// is omitted from the tensor-type. For a more complete description, refer to
33-
// https://github.com/onnx/onnx/blob/master/docs/IR.md#static-tensor-shapes.
33+
// https://github.com/onnx/onnx/blob/main/docs/IR.md#static-tensor-shapes.
3434
//
3535
message SequenceProto {
3636

‎onnx/onnx-ml.proto

+2-2
Original file line numberDiff line numberDiff line change
@@ -659,7 +659,7 @@ message TensorShapeProto {
659659
// Standard denotation can optionally be used to denote tensor
660660
// dimensions with standard semantic descriptions to ensure
661661
// that operations are applied to the correct axis of a tensor.
662-
// Refer to https://github.com/onnx/onnx/blob/master/docs/DimensionDenotation.md#denotation-definition
662+
// Refer to https://github.com/onnx/onnx/blob/main/docs/DimensionDenotation.md#denotation-definition
663663
// for pre-defined dimension denotations.
664664
optional string denotation = 3;
665665
};
@@ -754,7 +754,7 @@ message TypeProto {
754754

755755
// An optional denotation can be used to denote the whole
756756
// type with a standard semantic description as to what is
757-
// stored inside. Refer to https://github.com/onnx/onnx/blob/master/docs/TypeDenotation.md#type-denotation-definition
757+
// stored inside. Refer to https://github.com/onnx/onnx/blob/main/docs/TypeDenotation.md#type-denotation-definition
758758
// for pre-defined type denotations.
759759
optional string denotation = 6;
760760
}

‎onnx/onnx-ml.proto3

+2-2
Original file line numberDiff line numberDiff line change
@@ -659,7 +659,7 @@ message TensorShapeProto {
659659
// Standard denotation can optionally be used to denote tensor
660660
// dimensions with standard semantic descriptions to ensure
661661
// that operations are applied to the correct axis of a tensor.
662-
// Refer to https://github.com/onnx/onnx/blob/master/docs/DimensionDenotation.md#denotation-definition
662+
// Refer to https://github.com/onnx/onnx/blob/main/docs/DimensionDenotation.md#denotation-definition
663663
// for pre-defined dimension denotations.
664664
string denotation = 3;
665665
};
@@ -754,7 +754,7 @@ message TypeProto {
754754

755755
// An optional denotation can be used to denote the whole
756756
// type with a standard semantic description as to what is
757-
// stored inside. Refer to https://github.com/onnx/onnx/blob/master/docs/TypeDenotation.md#type-denotation-definition
757+
// stored inside. Refer to https://github.com/onnx/onnx/blob/main/docs/TypeDenotation.md#type-denotation-definition
758758
// for pre-defined type denotations.
759759
string denotation = 6;
760760
}

‎onnx/onnx.in.proto

+2-2
Original file line numberDiff line numberDiff line change
@@ -656,7 +656,7 @@ message TensorShapeProto {
656656
// Standard denotation can optionally be used to denote tensor
657657
// dimensions with standard semantic descriptions to ensure
658658
// that operations are applied to the correct axis of a tensor.
659-
// Refer to https://github.com/onnx/onnx/blob/master/docs/DimensionDenotation.md#denotation-definition
659+
// Refer to https://github.com/onnx/onnx/blob/main/docs/DimensionDenotation.md#denotation-definition
660660
// for pre-defined dimension denotations.
661661
optional string denotation = 3;
662662
};
@@ -755,7 +755,7 @@ message TypeProto {
755755

756756
// An optional denotation can be used to denote the whole
757757
// type with a standard semantic description as to what is
758-
// stored inside. Refer to https://github.com/onnx/onnx/blob/master/docs/TypeDenotation.md#type-denotation-definition
758+
// stored inside. Refer to https://github.com/onnx/onnx/blob/main/docs/TypeDenotation.md#type-denotation-definition
759759
// for pre-defined type denotations.
760760
optional string denotation = 6;
761761
}

‎onnx/onnx.proto

+2-2
Original file line numberDiff line numberDiff line change
@@ -657,7 +657,7 @@ message TensorShapeProto {
657657
// Standard denotation can optionally be used to denote tensor
658658
// dimensions with standard semantic descriptions to ensure
659659
// that operations are applied to the correct axis of a tensor.
660-
// Refer to https://github.com/onnx/onnx/blob/master/docs/DimensionDenotation.md#denotation-definition
660+
// Refer to https://github.com/onnx/onnx/blob/main/docs/DimensionDenotation.md#denotation-definition
661661
// for pre-defined dimension denotations.
662662
optional string denotation = 3;
663663
};
@@ -738,7 +738,7 @@ message TypeProto {
738738

739739
// An optional denotation can be used to denote the whole
740740
// type with a standard semantic description as to what is
741-
// stored inside. Refer to https://github.com/onnx/onnx/blob/master/docs/TypeDenotation.md#type-denotation-definition
741+
// stored inside. Refer to https://github.com/onnx/onnx/blob/main/docs/TypeDenotation.md#type-denotation-definition
742742
// for pre-defined type denotations.
743743
optional string denotation = 6;
744744
}

‎onnx/onnx.proto3

+2-2
Original file line numberDiff line numberDiff line change
@@ -657,7 +657,7 @@ message TensorShapeProto {
657657
// Standard denotation can optionally be used to denote tensor
658658
// dimensions with standard semantic descriptions to ensure
659659
// that operations are applied to the correct axis of a tensor.
660-
// Refer to https://github.com/onnx/onnx/blob/master/docs/DimensionDenotation.md#denotation-definition
660+
// Refer to https://github.com/onnx/onnx/blob/main/docs/DimensionDenotation.md#denotation-definition
661661
// for pre-defined dimension denotations.
662662
string denotation = 3;
663663
};
@@ -738,7 +738,7 @@ message TypeProto {
738738

739739
// An optional denotation can be used to denote the whole
740740
// type with a standard semantic description as to what is
741-
// stored inside. Refer to https://github.com/onnx/onnx/blob/master/docs/TypeDenotation.md#type-denotation-definition
741+
// stored inside. Refer to https://github.com/onnx/onnx/blob/main/docs/TypeDenotation.md#type-denotation-definition
742742
// for pre-defined type denotations.
743743
string denotation = 6;
744744
}

0 commit comments

Comments
 (0)
Please sign in to comment.