Validate that method inputs have the expected dim order #9757
Conversation
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
|
|
Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as |
|
Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as |
2 participants
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