[ONNX] Make the ONNX Importer More Static #7429
Merged
Conversation
This file contains 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
mbrookhart
force-pushed
the
more_static_onnx_importer
branch
from
9303222
to
52f09ee
Compare
mbrookhart
force-pushed
the
more_static_onnx_importer
branch
from
70894a1
to
6e7b71c
Compare
electriclilies
approved these changes
Feb 11, 2021
added 5 commits
February 12, 2021 11:03
mbrookhart
force-pushed
the
more_static_onnx_importer
branch
from
6e7b71c
to
9c2c5a6
Compare
mbrookhart
changed the title
mbrookhart
changed the title
mbrookhart
changed the title
|
@masahi @jwfromm @tmoreau89 I think this is ready for review |
junrushao
approved these changes
Feb 12, 2021
|
Thank you @mbrookhart @electriclilies @junrushao1994 the PR has been merged |
Lokiiiiii
pushed a commit
to Lokiiiiii/tvm
that referenced
this pull request
Mar 2, 2021
* Construct static Ops if inputs are Constant * Expose FoldConstant as a function in addition to the pass * refactor onnx importer to do more static imports by constant folding fix pylint * fix test regressions * fix style, two bugs * pipe freeze_params through sub_graphs when importing loops and control flow
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Mar 2, 2021
* Construct static Ops if inputs are Constant * Expose FoldConstant as a function in addition to the pass * refactor onnx importer to do more static imports by constant folding fix pylint * fix test regressions * fix style, two bugs * pipe freeze_params through sub_graphs when importing loops and control flow
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
We've been hitting a lot of issues in more complicated ONNX models where results of something like dynamic strided slice feed into an op like dynamic reshape, causing dynamic ranks to appear and crash the importer. To fix this, I decided it might be good to try to progagate constant information through the importer during import instead of trying to retroactively remove dynamic ops in a pass. To do that, I changed the freeze_params behavior of the importer to create constants before import, and made the importer fold constants through the importer as they are seen. Additionally, I edited the ops to only construct dynamic ops if the inputs are not constant.
In sum, this ends up creating many fewer dynamic ops in the ONNX importer, and so we see many fewer dynamic rank issues when importing models.
cc @masahi @jwfromm @electriclilies
@tmoreau89 found a serious performance regression on #7368, this change takes the import + dynamic_to_static of ONNX Bert Large from 20+ minutes to < 30s.