Add tolerance args to CheckONNXModel.py #3024
Merged
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Outdated suggestions cannot be applied.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.
Added
--rtol=x
and--atol=y
to CheckONNXModel.py.So for example, if you wanted to check the accuracy of a code running on CPU vs accelerator, you would launch the following command
where
-m
is to give the model name,-r
is the reference compile parameters,-a
is the additional parameters to be tested for the test compilation (you can use the-t
to give an entirely different compiler options), and the last 2 parameters are used to pass the absolute and relative tolerance used to verify the equivalence of the reference-compiled-run vs test-compiled-run.