[ONNX] Update the sequence of initializers in exported graph so that it is as same as inputs.

[fatcat-z]

In the process of export, initializers were saved in a C++ map container. Map will automatically sort the elements when an insertion happened. This causes initializers lose the insertion sequence which is supposed to be kept.

So update the backend code to create initializers following up on the inputs sequence in a final stage where initializers were not kept in a map container.

[facebook-github-bot]

💊 CI failures summary and remediations

As of commit efd09b9 (more details on the Dr. CI page):

---

• 2/2 failures introduced in this PR

---

🕵️ 2 new failures recognized by patterns

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

pytorch_linux_backward_compatibility_check_test (1/2)

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

Jan 05 09:53:32 The PR is introducing backward incompatible changes to the operator library. Please contact PyTorch team to confirm whether this change is wanted or not.

Jan 05 09:53:32 processing existing schema:  alltoall(__torch__.torch.classes.dist_c10d.ProcessGroup _0, Tensor[] _1, Tensor[] _2) -> (__torch__.torch.classes.dist_c10d.Work _0)
Jan 05 09:53:32 processing existing schema:  send(__torch__.torch.classes.dist_c10d.ProcessGroup _0, Tensor[] _1, int _2, int _3) -> (__torch__.torch.classes.dist_c10d.Work _0)
Jan 05 09:53:32 processing existing schema:  recv(__torch__.torch.classes.dist_c10d.ProcessGroup _0, Tensor[] _1, int _2, int _3) -> (__torch__.torch.classes.dist_c10d.Work _0)
Jan 05 09:53:32 processing existing schema:  recv_anysource(__torch__.torch.classes.dist_c10d.ProcessGroup _0, Tensor[] _1, int _2) -> (__torch__.torch.classes.dist_c10d.Work _0)
Jan 05 09:53:32 processing existing schema:  barrier(__torch__.torch.classes.dist_c10d.ProcessGroup _0) -> (__torch__.torch.classes.dist_c10d.Work _0)
Jan 05 09:53:32 processing existing schema:  __init__(__torch__.torch.classes.dist_c10d.frontend _0) -> (None _0)
Jan 05 09:53:32 processing existing schema:  new_process_group_helper(__torch__.torch.classes.dist_c10d.frontend _0, int _1, int _2, int[] _3, str _4, __torch__.torch.classes.dist_c10d.Store _5, str? _6, int _7) -> (__torch__.torch.classes.dist_c10d.ProcessGroup _0)
Jan 05 09:53:32 processing existing schema:  get_process_group_by_name(__torch__.torch.classes.dist_c10d.frontend _0, str _1) -> (__torch__.torch.classes.dist_c10d.ProcessGroup _0)
Jan 05 09:53:32 processing existing schema:  get_name_of_process_group(__torch__.torch.classes.dist_c10d.frontend _0, __torch__.torch.classes.dist_c10d.ProcessGroup _1) -> (str _0)
Jan 05 09:53:32 processing existing schema:  __init__(__torch__.torch.classes.dist_rpc.WorkerInfo _0, str _1, int _2) -> (None _0)
Jan 05 09:53:32 The PR is introducing backward incompatible changes to the operator library. Please contact PyTorch team to confirm whether this change is wanted or not. 
Jan 05 09:53:32 
Jan 05 09:53:32 Broken ops: [
Jan 05 09:53:32 	aten::_test_ambiguous_defaults.a(Tensor dummy, int a=1, int b=1) -> (Tensor)
Jan 05 09:53:32 	aten::_test_ambiguous_defaults.b(Tensor dummy, int a=2, str b="2") -> (Tensor)
Jan 05 09:53:32 ]
Jan 05 09:53:32 =================== sccache compilation log ===================
Jan 05 09:53:32 + cleanup
Jan 05 09:53:32 + retcode=1
Jan 05 09:53:32 + set +x
Jan 05 09:53:32 =========== If your build fails, please take a look at the log above for possible reasons ===========

pytorch_windows_vs2019_py36_cuda10.1_test1 (2/2)

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

RuntimeError: test_nn failed!

  test_ReflectionPad2d (__main__.TestNN) ... ok (1.176s)
  test_ReflectionPad2d_alert_nondeterministic_cuda (__main__.TestNN) ... ok (0.011s)
  test_ReflectionPad2d_cuda (__main__.TestNN) ... ok (0.014s)
  test_ReplicationPad1d (__main__.TestNN) ... ok (0.069s)
  test_ReplicationPad1d_alert_nondeterministic_cuda (__main__.TestNN) ... ok (0.014s)
  test_ReplicationPad1d_cuda (__main__.TestNN) ... Traceback (most recent call last):
  File "run_test.py", line 910, in <module>
    main()
  File "run_test.py", line 889, in main
    raise RuntimeError(err_message)
RuntimeError: test_nn failed!

(base) circleci@PACKER-5FD865C5 C:\Users\circleci\project\test>if ERRORLEVEL 1 exit /b 1 
+ cleanup
+ retcode=1
+ set +x


Exited with code exit status 1

---

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 to the (internal) Dr. CI Users group.

This comment has been revised 21 times.

[BowenBao]

Thanks @fatcat-z, could you check the failed onnx_ort_test1/onnx_ort_test2 CI tests and fix if related?

[fatcat-z]

Thanks @fatcat-z, could you check the failed onnx_ort_test1/onnx_ort_test2 CI tests and fix if related?

It has been fixed by updating expect file.