Document the usage of timm as backbone provider

[jpcbertoldo]

Description

Add some text in the documentation to make it clearer that timm is used to fetch pre-trained models.

• Fixes Backbone/model weights source should be more obvious to figure out. #543

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
• Documentation improvement

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
• N/A

[ashwinvaidya17]

Thanks for updating the documentation! I have a minor comment.

[jpcbertoldo]

requested changes done

[ashwinvaidya17]

@jpcbertoldo can you have a look at the issues raised by codacy?

[jpcbertoldo]

I'll try if i have time today.
Btw tests were failing in my local env.
I think it was in the other branch but it wasn't related to my changes.
I was wondering if we could arrange a call so i can get a hand with that.

[ashwinvaidya17]

I'll try if i have time today. Btw tests were failing in my local env. I think it was in the other branch but it wasn't related to my changes. I was wondering if we could arrange a call so i can get a hand with that.

Sure take your time. I just ran the CI and I can see that it fails for linting checks but we can have a call in case tox is not working on your machine. Maybe we might have to update the documentation. Let's continue that discussion in an email thread.

[jpcbertoldo]

this was integrated in #576

[watertianyi]

I used convnextv2_huge.fcmae_ft_in22k_in1k_512 to replace the pre-trained network wide_resnet50_2 in patchcore, and used layers=['stages.1', 'stages.2'] for classification. The indicator effect is far worse than wide_resnet50_2. Isn't convnextv2 better than wide_resnet50_2? Why Would it be so bad?