Fix pre-commit issues caused by the EfficientAD PR

[samet-akcay]

Description

• This is to fix the pre-commit issues caused by the efficient ad pr

Fixes

• Bug report [Bug]: EfficientAD Decoder image_size class attribute missing #1120

Changes

• Bug fix (non-breaking change which fixes an issue)
• Refactor (non-breaking change which refactors the code base)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

Checklist

• My code follows the pre-commit style and check guidelines of this project.
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing tests pass locally with my changes
• I have added a summary of my changes to the CHANGELOG (not for minor changes, docs and tests).

[djdameln]

Thanks!

[jpcbertoldo]

Could you enjoy the pr and correct another issue?

If you try to run it with an image size smaller than 256 (i guess, i tried 224) it breaks because at some point in the model there will be a convolutional kernel (8x8) size bigger than the feature map resolution (7x7).

I think just an assertion at the init would do (to explicitly let the user know this).