-
-
Notifications
You must be signed in to change notification settings - Fork 13
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Model training based on pretrained classification model does not work as expected #916
Comments
👋 Hello @curtinmjc, thank you for raising an issue about Ultralytics HUB 🚀! Your contribution helps us improve and address any potential issues. For more insights into the Ultralytics HUB, please explore our comprehensive HUB Docs:
As this seems like a 🐛 Bug Report, we would appreciate it if you could provide a minimum reproducible example (MRE) to help us understand the issue better. This can include a detailed description along with code snippets or configuration files that showcase the problem. On your specific concerns:
We aim to resolve all issues promptly and appreciate your patience. An Ultralytics engineer will follow up with you soon to provide further assistance. Thank you for your understanding! 😊 |
As far as a minimum reproducible example (MRE) is concerned, the first model training used the Official YOLO11n classify architecture with my first custom dataset. The second model training started using the Custom model that I had trained initially with my second custom dataset. I can provide you with the two Classify datasets, but I do not believe there is anything special about them. |
Hello @curtinmjc, Thank you for providing additional context about your training process. It sounds like you're using a well-structured approach with the YOLO11n classify architecture and custom datasets. To address the issue you're experiencing, here are a few steps you can take:
Your feedback is invaluable, and we're here to help you get the most out of Ultralytics HUB. If you have any more details or questions, feel free to share them. 😊 |
Thank you for your response. My answers to your listed steps:
|
Hello @curtinmjc, Thank you for the detailed follow-up! It sounds like you've been thorough in your troubleshooting process. Let's see how we can further assist you:
If the issue continues, consider sharing a minimal reproducible example with the community on GitHub Discussions or Discord. This can provide more insights and allow others to replicate and diagnose the problem. Thank you for your patience and for working with the community to resolve this. If you have any more questions or need further assistance, feel free to reach out. 😊 |
Search before asking
Question
Background:
What I did and learned:
Additional
Questions:
The text was updated successfully, but these errors were encountered: