Increase accuracy of yolov9 algorithm #14168
Replies: 1 comment 2 replies
-
Hi @Abhinav28112003, Thank you for reaching out! Achieving high accuracy on a small set of test images can be challenging, but here are a few tips that might help you improve your YOLOv9 model's performance:
If you could provide a minimum reproducible example of your current setup, it would be easier to give more specific advice. You can find guidelines on how to create one here: Minimum Reproducible Example. Lastly, ensure you are using the latest version of the Ultralytics packages to benefit from the latest improvements and bug fixes. I hope these tips help you achieve your target accuracy! If you have any further questions, feel free to ask. 😊 |
Beta Was this translation helpful? Give feedback.
-
@glenn-jocher Hi I have a query on increasing the accuracy of my model on test-images. So basically I have 5 test images I have trained a Yolov9 algorithm model. I have around 181 train images and 20 Label images. I have achieved almost 0.973 mAP on the PR curve on training data. I have been given a task to get 98%+ accuracy on the test images. Currently I am getting 89,90,76 etc as the accuracy. I have used the same colab notebook given the ultralytics Youtube video and I have used the same yaml files consisting of hyper parameters . Please help me with any tips for achieving 98% for all the 5 test images. Please let me know any changes that could get me my test accuracy.
Thank you.
Beta Was this translation helpful? Give feedback.
All reactions