[ONNX] Add dim_param support in export with onnx shape inference #44920
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
facebook-github-bot
added
the
oncall: jit
💊 CI failures summary and remediationsAs of commit 2b54121 (more details on the Dr. CI page):
Extra GitHub checks: 1 failed
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. This comment has been revised 68 times. |
BowenBao
force-pushed
the
onnx_shape_inf_dim_param
branch
from
97a6e9a to
b5b4a0e
Compare
Codecov Report
@@ Coverage Diff @@
## master #44920 +/- ##
==========================================
- Coverage 68.56% 68.56% -0.01%
==========================================
Files 405 405
Lines 51969 51979 +10
==========================================
+ Hits 35634 35639 +5
- Misses 16335 16340 +5
Continue to review full report at Codecov.
|
ailzhang
added
the
triaged
BowenBao
commented
Sep 24, 2020
BowenBao
force-pushed
the
onnx_shape_inf_dim_param
branch
from
768ca81 to
4e5aa2e
Compare
Contributor
facebook-github-bot
left a comment
facebook-github-bot
left a comment
There was a problem hiding this comment.
@bzinodev has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
BowenBao
force-pushed
the
onnx_shape_inf_dim_param
branch
from
4e5aa2e to
b3b7574
Compare
Collaborator
Author
|
rebased to resolve conflict. |
BowenBao
force-pushed
the
onnx_shape_inf_dim_param
branch
from
c2e764a to
0f70a20
Compare
neginraoof
reviewed
Sep 29, 2020
BowenBao
force-pushed
the
onnx_shape_inf_dim_param
branch
from
bcd6bbf to
6372c86
Compare
remove prints remove debug prints clang format fix flake8, remove old outdated code unrelated clang tidy clang-tidy clang-tidy clang format fix windows build merge changes add second pass shape inference to increase coverage clang format update to comments
BowenBao
force-pushed
the
onnx_shape_inf_dim_param
branch
from
6372c86 to
2b54121
Compare
Collaborator
Author
|
@bzinodev This PR has been approved and rebased, please help importing for merge. |
Contributor
facebook-github-bot
left a comment
facebook-github-bot
left a comment
There was a problem hiding this comment.
@bzinodev has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
bzinodev
approved these changes
Sep 30, 2020
Contributor
BowenBao
added a commit
to BowenBao/pytorch
that referenced
this pull request
Oct 2, 2020
…orch#44920) Summary: * Support propagating `dim_param` in ONNX by encoding as `ShapeSymbol` in `SymbolicShape` of outputs. If export is called with `dynamic_axes` provided, shape inference will start with these axes set as dynamic. * Add new test file `test_pytorch_onnx_shape_inference.py`, reusing all test cases from `test_pytorch_onnx_onnxruntime.py`, but focus on validating shape for all nodes in graph. Currently this is not enabled in the CI, since there are still quite some existing issues and corner cases to fix. The test is default to run only at opset 12. * Bug fixes, such as div, _len, and peephole.cpp passes for PackPadded, and LogSoftmaxCrossEntropy. * This PR depends on existing PR such as 44332. Pull Request resolved: pytorch#44920 Reviewed By: eellison Differential Revision: D23958398 Pulled By: bzinodev fbshipit-source-id: 00479d9bd19c867d526769a15ba97ec16d56e51d
This was referenced Oct 2, 2020
soumith
pushed a commit
that referenced
this pull request
Oct 6, 2020
) (#45755) Summary: * Support propagating `dim_param` in ONNX by encoding as `ShapeSymbol` in `SymbolicShape` of outputs. If export is called with `dynamic_axes` provided, shape inference will start with these axes set as dynamic. * Add new test file `test_pytorch_onnx_shape_inference.py`, reusing all test cases from `test_pytorch_onnx_onnxruntime.py`, but focus on validating shape for all nodes in graph. Currently this is not enabled in the CI, since there are still quite some existing issues and corner cases to fix. The test is default to run only at opset 12. * Bug fixes, such as div, _len, and peephole.cpp passes for PackPadded, and LogSoftmaxCrossEntropy. * This PR depends on existing PR such as 44332. Pull Request resolved: #44920 Reviewed By: eellison Differential Revision: D23958398 Pulled By: bzinodev fbshipit-source-id: 00479d9bd19c867d526769a15ba97ec16d56e51d
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
9 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
dim_paramin ONNX by encoding asShapeSymbolinSymbolicShapeof outputs. If export is called withdynamic_axesprovided, shape inference will start with these axes set as dynamic.test_pytorch_onnx_shape_inference.py, reusing all test cases fromtest_pytorch_onnx_onnxruntime.py, but focus on validating shape for all nodes in graph. Currently this is not enabled in the CI, since there are still quite some existing issues and corner cases to fix. The test is default to run only at opset 12.