-
Notifications
You must be signed in to change notification settings - Fork 604
Arm backend: Add test for DeiT Tiny for TOSA BI #10846
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.
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
Conversation
Add test case for the DeiT Tiny model for the TOSA BI profile. At this time the output of the model differs from the reference implementation by a mean absolute error of around 2.5, which is too high. An internal ticket has been raised to resolve this issue. Signed-off-by: Martin Lindström <[email protected]> Change-Id: I9f3223068d35fa6f3e485e0fb12ad49bb8b3d534
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10846
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit bf654f8 with merge base 7993bb2 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
@pytorchbot label "partner: arm" |
@pytorchbot label ciflow/trunk |
@pytorchbot label "topic: not user facing" |
aten_op=[], | ||
exir_op=[], | ||
use_to_edge_transform_and_lower=True, | ||
atol=3.0, # This needs to go down: MLETORCH-956 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is it stable though? As opposed to flaky, else we can mark it as Flaky..
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@digantdesai I believe it is rather stable. Been looping it several times myself and the numerical error looks to be consistent.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
More transformers! Let's go.
Add test case for the DeiT Tiny model for the TOSA BI profile. At this time the output of the model differs from the reference implementation by a mean absolute error of around 2.5, which is too high. An internal ticket has been raised to resolve this issue.
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218