Closed ashwinvaidya17 closed 1 month ago
Check out this pull request on
See visual diffs & provide feedback on Jupyter Notebooks.
Powered by ReviewNB
Attention: Patch coverage is 96.59091%
with 3 lines
in your changes are missing coverage. Please review.
Project coverage is 81.22%. Comparing base (
e95dbe8
) to head (b283e78
). Report is 1 commits behind head on main.
Files | Patch % | Lines |
---|---|---|
...rc/anomalib/models/components/base/export_mixin.py | 96.20% | 3 Missing :warning: |
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.
Hi @ashwinvaidya17 @samet-akcay
One question, perhaps is a Pytorch general doubt, when you model.to_onnx
(or to_torch for example), the model you are exporting does use the best weights or the last ones? And when in Anomalib we use the export
method of the Engine
class, what happens? If the last ones, how should we act to export the best weights taking advantage of the Anomalib's methods?
Thank you so much.
@CarlosNacher can you create a discussion for this (https://github.com/openvinotoolkit/anomalib/discussions) so that it does not get lost in the PRs.
@ashwinvaidya17 got it, thank you!
Dicussion: https://github.com/openvinotoolkit/anomalib/discussions/2110
๐ Description
โจ Changes
Select what type of change your PR is:
โ Checklist
Before you submit your pull request, please make sure you have completed the following steps:
For more information about code review checklists, see the Code Review Checklist.