Validate that method inputs have the expected dim order #9757
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
Summary: Currently, there is no check for the correct dim order when setting method inputs. If the input tensor has a different dim order than was used in export, it will silently give garbage outputs by treating the input tensor as having a different dim order than it does. To catch this case, I've added an additional check in `method.set_input` to enforce that the dim order matches. I've also added a `dim_order_to_c_string` utility method in "dim_order_util.h" to aid in printing usable error messages. Differential Revision: D72106471
GregoryComer
requested review from
JacobSzwejbka,
lucylq and
swolchok
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/9757
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit faa7591 with merge base 7d35c68 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D72106471 |
This PR needs a
|
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Outdated suggestions cannot be applied.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.
Summary:
Currently, there is no check for the correct dim order when setting method inputs. If the input tensor has a different dim order than was used in export, it will silently give garbage outputs by treating the input tensor as having a different dim order than it does. To catch this case, I've added an additional check in
method.set_inputto enforce that the dim order matches.I've also added a
dim_order_to_c_stringutility method in "dim_order_util.h" to aid in printing usable error messages.Differential Revision: D72106471