TorchScript add check if quantized

[z-a-f]

Stack from ghstack:

• TorchScript add check if quantized #32890 TorchScript add check if quantized

Differential Revision: D19673463

[jerryzh168]

Why? could you implement the required method?

[kostmo]

💊 CircleCI build failures summary and remediations

As of commit 7dbd48f:

None of the build failures appear to be your fault.

• 1/3 broken upstream at merge base c917a24 since Feb 10

  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 origin viable/strict
  git rebase --onto viable/strict $(git merge-base origin/master HEAD)
  

  If your commit is older than viable/strict:

  git fetch origin viable/strict
  git rebase viable/strict
  

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

• 2/3 recognized as flaky ❄️

  • Re-run these jobs?

Detailed failure analysis

One may explore the probable reasons each build failed interactively on the Dr. CI website.

❄️ 2 failures recognized as flaky

The following build failures have been detected as flaky and may not be your fault:

caffe2_onnx_py3_6_clang7_ubuntu16_04_test (1/2)

Step: "Test" (full log | pattern match details) ❄️

Feb 10 20:07:20 test/onnx/test_utility_funs.py::TestUtilityFuns::test_constant_fold_reshape Fatal Python error: Segmentation fault

Feb 10 20:07:20 test/onnx/test_utility_funs.py::TestUtilityFuns_opset11::test_constant_fold_transpose_matmul PASSED [ 99%] 
Feb 10 20:07:20 test/onnx/test_utility_funs.py::TestUtilityFuns_opset11::test_constant_fold_unsqueeze PASSED [ 99%] 
Feb 10 20:07:20 test/onnx/test_utility_funs.py::TestUtilityFuns_opset11::test_error_on_data_parallel PASSED [ 99%] 
Feb 10 20:07:20 test/onnx/test_utility_funs.py::TestUtilityFuns_opset11::test_is_in_onnx_export PASSED [ 99%] 
Feb 10 20:07:20 test/onnx/test_utility_funs.py::TestUtilityFuns_opset11::test_strip_doc_string PASSED [ 99%] 
Feb 10 20:07:20 test/onnx/test_utility_funs.py::TestUtilityFuns_opset11::test_validate_dynamic_axes_invalid_input_output_name PASSED [ 99%] 
Feb 10 20:07:20 test/onnx/test_utility_funs.py::TestUtilityFuns::test_constant_fold_concat PASSED [ 99%] 
Feb 10 20:07:20 test/onnx/test_utility_funs.py::TestUtilityFuns::test_constant_fold_div PASSED [ 99%] 
Feb 10 20:07:20 test/onnx/test_utility_funs.py::TestUtilityFuns::test_constant_fold_lstm PASSED [ 99%] 
Feb 10 20:07:20 test/onnx/test_utility_funs.py::TestUtilityFuns::test_constant_fold_mul PASSED [ 99%] 
Feb 10 20:07:20 test/onnx/test_utility_funs.py::TestUtilityFuns::test_constant_fold_reshape Fatal Python error: Segmentation fault 
Feb 10 20:07:20  
Feb 10 20:07:20 Current thread 0x00007fd9a46a7700 (most recent call first): 
Feb 10 20:07:20   File "/usr/local/lib/python3.6/dist-packages/_pytest/_io/saferepr.py", line 43 in repr_instance 
Feb 10 20:07:20   File "/usr/lib/python3.6/reprlib.py", line 65 in repr1 
Feb 10 20:07:20   File "/usr/lib/python3.6/reprlib.py", line 55 in repr 
Feb 10 20:07:20   File "/usr/local/lib/python3.6/dist-packages/_pytest/_io/saferepr.py", line 36 in repr 
Feb 10 20:07:20   File "/usr/local/lib/python3.6/dist-packages/_pytest/_io/saferepr.py", line 67 in saferepr 
Feb 10 20:07:20   File "/usr/local/lib/python3.6/dist-packages/_pytest/_code/code.py", line 655 in repr_args 
Feb 10 20:07:20   File "/usr/local/lib/python3.6/dist-packages/_pytest/_code/code.py", line 736 in repr_traceback_entry 
Feb 10 20:07:20   File "/usr/local/lib/python3.6/dist-packages/_pytest/_code/code.py", line 777 in repr_traceback 

caffe2_onnx_py2_gcc5_ubuntu16_04_test (2/2)

Step: "Test" (full log | pattern match details) ❄️

Feb 10 20:08:06 test/onnx/test_utility_funs.py::TestUtilityFuns::test_constant_fold_reshape /var/lib/jenkins/workspace/scripts/onnx/test.sh: line 57: 2219 Segmentation fault (core dumped) pytest "${args[@]}" --ignore "$top_dir/test/onnx/test_pytorch_onnx_onnxruntime.py" --ignore "$top_dir/test/onnx/test_custom_ops.py" --ignore "$top_dir/test/onnx/test_models_onnxruntime.py" "${test_paths[@]}"

Feb 10 20:08:05 test/onnx/test_utility_funs.py::TestUtilityFuns_opset10::test_constant_fold_transpose_matmul PASSED [ 99%] 
Feb 10 20:08:05 test/onnx/test_utility_funs.py::TestUtilityFuns_opset10::test_constant_fold_unsqueeze PASSED [ 99%] 
Feb 10 20:08:05 test/onnx/test_utility_funs.py::TestUtilityFuns_opset10::test_error_on_data_parallel PASSED [ 99%] 
Feb 10 20:08:05 test/onnx/test_utility_funs.py::TestUtilityFuns_opset10::test_is_in_onnx_export PASSED [ 99%] 
Feb 10 20:08:05 test/onnx/test_utility_funs.py::TestUtilityFuns_opset10::test_strip_doc_string PASSED [ 99%] 
Feb 10 20:08:05 test/onnx/test_utility_funs.py::TestUtilityFuns_opset10::test_validate_dynamic_axes_invalid_input_output_name PASSED [ 99%] 
Feb 10 20:08:05 test/onnx/test_utility_funs.py::TestUtilityFuns::test_constant_fold_concat PASSED [ 99%] 
Feb 10 20:08:05 test/onnx/test_utility_funs.py::TestUtilityFuns::test_constant_fold_div PASSED [ 99%] 
Feb 10 20:08:05 test/onnx/test_utility_funs.py::TestUtilityFuns::test_constant_fold_lstm PASSED [ 99%] 
Feb 10 20:08:05 test/onnx/test_utility_funs.py::TestUtilityFuns::test_constant_fold_mul PASSED [ 99%] 
Feb 10 20:08:06 test/onnx/test_utility_funs.py::TestUtilityFuns::test_constant_fold_reshape /var/lib/jenkins/workspace/scripts/onnx/test.sh: line 57:  2219 Segmentation fault      (core dumped) pytest "${args[@]}" --ignore "$top_dir/test/onnx/test_pytorch_onnx_onnxruntime.py" --ignore "$top_dir/test/onnx/test_custom_ops.py" --ignore "$top_dir/test/onnx/test_models_onnxruntime.py" "${test_paths[@]}" 

🚧 1 upstream failure recognized by patterns:

These builds matched patterns, but were probably caused by upstream breakages:

• pytorch_linux_xenial_py2_7_9_test from Feb 10

---

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.

This comment has been revised 4 times.

[z-a-f]

Why? could you implement the required method?

Do you mean the .double? If so, I could, it's just this seemed to be easier :)

[jerryzh168]

I see, I thought we also want to compare the quantized info. Looks like this is just numeric comparison, then this should be fine.

[facebook-github-bot]

@z-a-f merged this pull request in acd51e1.