Add YOLO architecture

[rojberr]

No description provided.

[rojberr]

GIT Conflict ;) Let me know if you want to do it together ^^

[Copilot]

Pull Request Overview

This PR introduces support for the YOLO classifier architecture into the project by updating the model factory, classifier module, main initialization, and configuration files.

• Added YOLO model loading and classifier head replacement in the model factory.
• Updated the classifier module and main script to use the new YOLO model structure.
• Adjusted configuration settings to reflect the new model and hyperparameter values.

Reviewed Changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
src/models/model_factory.py	Added YOLO model loading, dummy input generation, and classifier head replacement.
src/models/classifier_module.py	Updated import and optimizer configuration for YOLO models versus other models.
src/main.py	Modified instantiation and logging to support the new classifier module alias.
src/dataset_functions.py	Removed an extraneous newline to improve code cleanliness.
src/config.yaml	Updated model name and learning rate to match the new YOLO classifier implementation.

Comments suppressed due to low confidence (2)

src/models/model_factory.py:62

• Assigning arbitrary attributes (f, i, type) to new_head may lead to confusion; consider adding inline comments or refactoring this into a dedicated classifier head subclass to clarify its purpose.

new_head.f = -1

src/models/classifier_module.py:82

• [nitpick] Consider using a more explicit check (e.g. if self.name == "YOLO_cls") to avoid potential false positives when matching model names.

if self.name.startswith("YOLO"):

[Copilot]

Consider removing the deprecated commented-out block if it is no longer needed to improve code readability and maintainability.

[rojberr]

@marszy775 ;)