github: ⚠️ YOLOv3 is out of date by 2882 commits. Use 'git pull ultralytics master'

[abdulkarimatrash]

hello everyone,

I am using yolov3 to train on a custom data, while training, I received this warning:

"github: ⚠️ YOLOv3 is out of date by 2882 commits. Use 'git pull ultralytics master"

I am wondering the reasons behind this warning.

I switched to the main ultralytics repo (https://github.com/ultralytics/ultralytics/tree/main), cloned it, and trained yolov3 on the same dataset using the same configuration, but got different (worse) results. I check the default.yaml presented here to look for differences, I noticed the absence of any anchor handling technique.

https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/default.yaml

I am a bit confused, should I be relying on this repo for training yolov3 due to the presence of anchor-related functionality, or should I switch to the newest ultralytics one?

Thanks, Karim,

[UltralyticsAssistant]

👋 Hello @random-guest, thank you for submitting a ultralytics/yolov3 🚀 Issue. To help us address your concern efficiently, please provide the following information:

1. For bug reports:

   • A clear and concise description of the bug or warning you're encountering
   • A minimum reproducible example MRE demonstrating the issue
   • Your environment details (e.g., OS, Python version, package versions)
   • Steps to reproduce the behavior
   • Any error messages or logs related to the issue

2. For feature requests:

   • A clear description of the feature or enhancement you'd like to see
   • The problem this feature would solve
   • Any alternative solutions you've considered

3. For general questions or clarifications:

   • Provide as much context as possible about your question
   • Include any specific references, such as which parts of the documentation you've looked at
   • Mention any differences you've observed with examples or detailed comparisons

Regarding the warning message "YOLOv3 is out of date by 2882 commits" ⚠️, this typically occurs when your codebase is behind the latest updates on the repository. You can resolve this by running the suggested command:

git pull ultralytics master

As YOLOv3 functionality differs between this repository and the new ultralytics repository, it’s important to note that the new repository integrates additional features and functionalities that are distinct and may impact results. The absence of anchors in the default YAML file within the new repo might be due to architectural updates or optimizations.

To assist you better:

• Could you clarify how you're configuring your custom training (anchors, hyperparameters)?
• What specific performance differences are you observing between the two repos? Providing numerical results or plots would be helpful!

This is an automated response to help gather necessary details more quickly, and an Ultralytics engineer will follow up with further assistance soon 😊. Thank you for contributing to improving our project!

[pderrenger]

@random-guest the warning indicates your local YOLOv3 repo is outdated. For YOLOv3 specifically, we recommend using the original ultralytics/yolov3 repo which contains the legacy anchor implementation. The newer ultralytics/ultralytics repo focuses on YOLOv5/v8+ with updated architectures. If you require YOLOv3's original anchor handling, stick with the dedicated yolov3 repo, though it's now deprecated in favor of newer YOLO versions.

[github-actions[bot]]

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐