[ONNX] Support nd mask index in opset >= 11

[BowenBao]

Fixes below pattern for opset >= 11

return tensor[tensor > 0]

where rank of tensor > 1.

[dr-ci]

💊 CI failures summary and remediations

As of commit 7b0ebaa (more details on the Dr. CI page):

---

• 2/2 failures possibly* introduced in this PR
  • 1/2 non-CircleCI failure(s)

---

🕵️ 1 new failure recognized by patterns

The following CI failures do not appear to be due to upstream breakages:

pytorch_linux_xenial_py3_6_gcc5_4_build (1/1)

Step: "Build" (full log | diagnosis details | 🔁 rerun)

Oct 27 17:49:11 caused by: Connection refused (os error 111)

Oct 27 17:49:11 ++++ extract_trap_cmd 
Oct 27 17:49:11 ++++ printf '%s\n' '' 
Oct 27 17:49:11 +++ printf '%s\n' cleanup 
Oct 27 17:49:11 ++ trap -- ' 
Oct 27 17:49:11 cleanup' EXIT 
Oct 27 17:49:11 ++ [[ pytorch-linux-xenial-py3.6-gcc5.4-build != *pytorch-win-* ]] 
Oct 27 17:49:11 ++ which sccache 
Oct 27 17:49:11 ++ sccache --stop-server 
Oct 27 17:49:11 Stopping sccache server... 
Oct 27 17:49:11 error: couldn't connect to server 
Oct 27 17:49:11 caused by: Connection refused (os error 111) 
Oct 27 17:49:11 ++ true 
Oct 27 17:49:11 ++ rm /var/lib/jenkins/sccache_error.log 
Oct 27 17:49:11 rm: cannot remove '/var/lib/jenkins/sccache_error.log': No such file or directory 
Oct 27 17:49:11 ++ true 
Oct 27 17:49:11 ++ [[ pytorch-linux-xenial-py3.6-gcc5.4-build == *rocm* ]] 
Oct 27 17:49:11 ++ SCCACHE_ERROR_LOG=/var/lib/jenkins/sccache_error.log 
Oct 27 17:49:11 ++ SCCACHE_IDLE_TIMEOUT=1200 
Oct 27 17:49:11 ++ RUST_LOG=sccache::server=error 
Oct 27 17:49:11 ++ sccache --start-server 
Oct 27 17:49:11 Starting sccache server... 

---

ci.pytorch.org: 1 failed

• Failed: pr/pytorch-linux-bionic-rocm3.8-py3.6

---

This comment was automatically generated by Dr. CI (expand for details).

Follow this link to opt-out of these comments for your Pull Requests.

Please report bugs/suggestions on the GitHub issue tracker or post in the (internal) Dr. CI Users group.

See how this bot performed.

This comment has been revised 24 times.

[dr-ci]

💊 CI failures summary and remediations

As of commit 837538e0a6 (more details on the Dr. CI page):

---

✅ None of the CI failures appear to be your fault 💚

---

• 6/6 broken upstream at merge base 0495998 on Sep 23 from 2:28pm to 5:42pm PDT (8 commits; d2b0450 - e9aa689)

---

🚧 6 fixed upstream failures:

These were probably caused by upstream breakages that were already fixed.

Please rebase on the viable/strict branch (expand for instructions)

If your commit is newer than viable/strict, you can try basing on an older, stable commit:

git fetch https://github.com/pytorch/pytorch viable/strict
git rebase --onto FETCH_HEAD $(git merge-base origin/master HEAD)

If your commit is older than viable/strict:

git fetch https://github.com/pytorch/pytorch viable/strict
git rebase FETCH_HEAD

Check out the recency history of this "viable master" tracking branch.

• binary_windows_libtorch_3_7_cpu_debug_build on Sep 23 from 2:28pm to 5:42pm PDT (8 commits; d2b0450 - e9aa689)
  • 🔁 rerun
• pytorch_windows_vs2019_py36_cuda10.1_build on Sep 23 from 2:28pm to 5:42pm PDT (8 commits; d2b0450 - e9aa689)
  • 🔁 rerun
• pytorch_windows_vs2019_py36_cpu_build on Sep 23 from 2:28pm to 5:42pm PDT (8 commits; d2b0450 - e9aa689)
  • 🔁 rerun
• pytorch_windows_vs2019_py36_cuda11.0_build on Sep 23 from 2:28pm to 5:42pm PDT (8 commits; d2b0450 - e9aa689)
  • 🔁 rerun
• binary_windows_libtorch_3_7_cpu_release_build on Sep 23 from 2:28pm to 5:42pm PDT (8 commits; d2b0450 - e9aa689)
  • 🔁 rerun
• pytorch_macos_10_13_py3_build on Sep 23 from 2:28pm to 5:42pm PDT (8 commits; d2b0450 - e9aa689)
  • 🔁 rerun

---

This comment was automatically generated by Dr. CI (expand for details).

Follow this link to opt-out of these comments for your Pull Requests.

Please report bugs/suggestions on the GitHub issue tracker or post in the (internal) Dr. CI Users group.

See how this bot performed.

[neginraoof]

LGTM. Thanks.

[facebook-github-bot]

@bzinodev has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

[facebook-github-bot]

@bzinodev has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

[codecov]

Codecov Report

Merging #45252 into master will decrease coverage by 0.57%.
The diff coverage is 7.14%.

@@            Coverage Diff             @@
##           master   #45252      +/-   ##
==========================================
- Coverage   68.94%   68.37%   -0.58%     
==========================================
  Files         434      413      -21     
  Lines       56188    54592    -1596     
==========================================
- Hits        38740    37326    -1414     
+ Misses      17448    17266     -182     

[facebook-github-bot]

@bzinodev has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

[BowenBao]

@bzinodev - hey any updates on this one? Is there test breakage blocking the merge? please let me know how i could help.

[facebook-github-bot]

@bzinodev has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

[facebook-github-bot]

@bzinodev has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

[facebook-github-bot]

@bzinodev merged this pull request in 129b412.