Skip to content

[v1.4.0] Fix unflatten when dim is a negative integer (#31208) #31432

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
mingbowan merged 1 commit into from
Dec 20, 2019
Merged

[v1.4.0] Fix unflatten when dim is a negative integer (#31208) #31432

mingbowan merged 1 commit into from
Dec 20, 2019

Conversation

@vishwakftw
Copy link
Contributor

@vishwakftw vishwakftw commented Dec 18, 2019

Summary:
Changelog:

Test Plan:

  • Updated tests in test_namedtensor.py

Fixes #31184

Differential Revision: D19036569

Pulled By: zou3519

fbshipit-source-id: 86e01e20988dee7c4b6c73232f66282d687f9a2c

@vishwakftw
Fix unflatten when dim is a negative integer (pytorch#31208)
397d57a 
Summary:
Changelog:
- Wrap dim to be a positive integer when dim is negative
Pull Request resolved: pytorch#31208

Test Plan:
- Updated tests in test_namedtensor.py

Fixes pytorch#31184

Differential Revision: D19036569

Pulled By: zou3519

fbshipit-source-id: 86e01e20988dee7c4b6c73232f66282d687f9a2c
@vishwakftw vishwakftw requested a review from zou3519 December 18, 2019 19:42
@vishwakftw vishwakftw mentioned this pull request Dec 18, 2019
Closed
@kostmo
Copy link
Member

kostmo commented Dec 18, 2019 •
edited
Loading

💊 CircleCI build failures summary and remediations

As of commit 397d57a:

  • 4/4 failures introduced in this PR

Detailed failure analysis

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

🕵️ 4 new failures recognized by patterns

The following build failures don't appear to be due to upstream breakage:

See CircleCI build pytorch_linux_xenial_py3_6_gcc5_4_build (1/4)

Step: "Build" (full log | pattern match details)

Automatic merge failed; fix conflicts and then commit the result. 
CONFLICT (add/add): Merge conflict in .circleci/docker/common/install_cache.sh 
Auto-merging .circleci/docker/common/install_cache.sh 
CONFLICT (add/add): Merge conflict in .circleci/docker/common/install_android.sh 
Auto-merging .circleci/docker/common/install_android.sh 
CONFLICT (add/add): Merge conflict in .circleci/docker/build.sh 
Auto-merging .circleci/docker/build.sh 
CONFLICT (add/add): Merge conflict in .circleci/config.yml 
Auto-merging .circleci/config.yml 
CONFLICT (add/add): Merge conflict in .circleci/cimodel/data/binary_build_definitions.py 
Auto-merging .circleci/cimodel/data/binary_build_definitions.py 
Automatic merge failed; fix conflicts and then commit the result.

See CircleCI build pytorch_xla_linux_xenial_py3_6_clang7_build (2/4)

Step: "Build" (full log | pattern match details)

Dec 18 20:03:44 Failed to run '['/var/lib/jenkins/workspace/xla/scripts/generate_code.sh']' 
Dec 18 20:03:44 AtenXlaType function missed override: Tensor upsample_bilinear2d_backward(const Tensor& grad_output, IntArrayRef output_size, IntArrayRef input_size, bool align_corners, double scales_1, double scales_2); // upsample_bilinear2d_backward(Tensor,IntArrayRef,IntArrayRef,bool,double,double)->Tensor 
Dec 18 20:03:44 AtenXlaType function missed override: Tensor upsample_nearest2d(const Tensor& self, IntArrayRef output_size, double scales_1, double scales_2); // upsample_nearest2d(Tensor,IntArrayRef,double,double)->Tensor 
Dec 18 20:03:44 AtenXlaType function missed override: Tensor upsample_nearest2d_backward(const Tensor& grad_output, IntArrayRef output_size, IntArrayRef input_size, double scales_1, double scales_2); // upsample_nearest2d_backward(Tensor,IntArrayRef,IntArrayRef,double,double)->Tensor 
Dec 18 20:03:44 Traceback (most recent call last): 
Dec 18 20:03:44   File "/var/lib/jenkins/workspace/xla/scripts/gen.py", line 1052, in <module> 
Dec 18 20:03:44     generate(args) 
Dec 18 20:03:44   File "/var/lib/jenkins/workspace/xla/scripts/gen.py", line 1022, in generate 
Dec 18 20:03:44     assert check_overrides(overrides, overridden) 
Dec 18 20:03:44 AssertionError 
Dec 18 20:03:44 Building torch_xla version: 0.8 
Dec 18 20:03:44 Failed to run '['/var/lib/jenkins/workspace/xla/scripts/generate_code.sh']' 
Dec 18 20:03:44 + cleanup 
Dec 18 20:03:44 + retcode=1 
Dec 18 20:03:44 + set +x 
Dec 18 20:03:44 =================== sccache compilation log =================== 
Dec 18 20:03:44 =========== If your build fails, please take a look at the log above for possible reasons =========== 
Dec 18 20:03:44 Compile requests              2493 
Dec 18 20:03:44 Compile requests executed     2238 
Dec 18 20:03:44 Cache hits                    2212 
Dec 18 20:03:44 Cache misses                    13 
Dec 18 20:03:44 Cache timeouts                   0

See CircleCI build caffe2_onnx_py3_6_clang7_ubuntu16_04_test (3/4)

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

Dec 18 20:06:03 ../.local/lib/python3.6/site-packages/caffe2/python/allcompare_test.py::TestAllCompare::test_allcompare FAILED [ 0%] 
Dec 18 20:05:55 ============================= test session starts ============================== 
Dec 18 20:05:55 platform linux -- Python 3.6.9, pytest-5.2.2, py-1.8.0, pluggy-0.13.0 -- /usr/bin/python3.6 
Dec 18 20:05:55 cachedir: .pytest_cache 
Dec 18 20:05:55 rootdir: /var/lib/jenkins 
Dec 18 20:05:55 plugins: hypothesis-3.59.0, sugar-0.9.2 
Dec 18 20:05:55 collecting ... WARNING:root:This caffe2 python run does not have GPU support. Will run in CPU only mode. 
Dec 18 20:05:55 INFO:caffe2.python.net_drawer:Cannot import pydot, which is required for drawing a network. This can usually be installed in python with "pip install pydot". Also, pydot requires graphviz to convert dot files to pdf: in ubuntu, this can usually be installed with "sudo apt-get install graphviz". 
Dec 18 20:06:03 net_drawer will not run correctly. Please install the correct dependencies. 
Dec 18 20:06:03 collected 2900 items / 1 skipped / 2899 selected 
Dec 18 20:06:03  
Dec 18 20:06:03 ../.local/lib/python3.6/site-packages/caffe2/python/allcompare_test.py::TestAllCompare::test_allcompare FAILED [  0%] 
Dec 18 20:06:03  
Dec 18 20:06:03 =================================== FAILURES =================================== 
Dec 18 20:06:03 ________________________ TestAllCompare.test_allcompare ________________________ 
Dec 18 20:06:03  
Dec 18 20:06:03 self = <caffe2.python.allcompare_test.TestAllCompare testMethod=test_allcompare> 
Dec 18 20:06:03  
Dec 18 20:06:03     @given( 
Dec 18 20:06:03 >       d=st.integers(1, 5), n=st.integers(2, 11), num_procs=st.integers(1, 8) 
Dec 18 20:06:03     ) 
Dec 18 20:06:03     def test_allcompare(self, d, n, num_procs):

See CircleCI build caffe2_onnx_py2_gcc5_ubuntu16_04_test (4/4)

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

Dec 18 20:17:42 ../.local/lib/python2.7/site-packages/caffe2/python/allcompare_test.py::TestAllCompare::test_allcompare FAILED [ 0%] 
Dec 18 20:17:35 ============================= test session starts ============================== 
Dec 18 20:17:35 platform linux2 -- Python 2.7.12, pytest-4.6.6, py-1.8.0, pluggy-0.13.0 -- /usr/bin/python2 
Dec 18 20:17:35 cachedir: .pytest_cache 
Dec 18 20:17:35 rootdir: /var/lib/jenkins 
Dec 18 20:17:35 plugins: hypothesis-3.59.0, sugar-0.9.2 
Dec 18 20:17:35 collecting ... WARNING:root:This caffe2 python run does not have GPU support. Will run in CPU only mode. 
Dec 18 20:17:35 INFO:caffe2.python.net_drawer:Cannot import pydot, which is required for drawing a network. This can usually be installed in python with "pip install pydot". Also, pydot requires graphviz to convert dot files to pdf: in ubuntu, this can usually be installed with "sudo apt-get install graphviz". 
Dec 18 20:17:42 net_drawer will not run correctly. Please install the correct dependencies. 
Dec 18 20:17:42 collected 2900 items / 1 skipped / 2899 selected 
Dec 18 20:17:42  
Dec 18 20:17:42 ../.local/lib/python2.7/site-packages/caffe2/python/allcompare_test.py::TestAllCompare::test_allcompare FAILED [  0%] 
Dec 18 20:17:42  
Dec 18 20:17:42 =================================== FAILURES =================================== 
Dec 18 20:17:42 ________________________ TestAllCompare.test_allcompare ________________________ 
Dec 18 20:17:42  
Dec 18 20:17:42 self = <caffe2.python.allcompare_test.TestAllCompare testMethod=test_allcompare> 
Dec 18 20:17:42  
Dec 18 20:17:42     @given( 
Dec 18 20:17:42 >       d=st.integers(1, 5), n=st.integers(2, 11), num_procs=st.integers(1, 8) 
Dec 18 20:17:42     ) 
Dec 18 20:17:42     def test_allcompare(self, d, n, num_procs):
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 2 times.

@mingbowan mingbowan merged commit 0541546 into pytorch:v1.4.0 Dec 20, 2019
@vishwakftw vishwakftw deleted the v1.4.0-unflatten-namedtensor-fix branch December 20, 2019 19:25
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@gchanan gchanan gchanan approved these changes

@zou3519 zou3519 zou3519 approved these changes

Assignees

No one assigned

Labels

open source

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

5 participants

@vishwakftw @kostmo @gchanan @zou3519 @mingbowan