confusion matrix explanation

[Yousef-Alhattab]

Search before asking

• [X] I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

we trained 300 epochs with correct labeling and everything is fine! this dataset has 6 classes and the training was fine on them then we rename all the classes with a same single name for all and 0 refers to their labeling, for example: 2 0.982969 0.501103 0.026657 0.021774 3 0.375260 0.478689 0.076369 0.081972 1 0.801413 0.492778 0.055476 0.058918 into 0 0.982969 0.501103 0.026657 0.021774 0 0.375260 0.478689 0.076369 0.081972 0 0.801413 0.492778 0.055476 0.058918

now I am just asking how to get the misdetection and omission. as you can see that I can not break the matrix down cuz in my case I just have a class? any help please!

Additional

No response

[glenn-jocher]

@urbansound8K confusion matrices don't apply to single-class datasets.

[Yousef-Alhattab]

is there any way to get the misdetection and omission for a single-class dataset, please?

another question, please! if I have two datasets with the same name of a class, what should I use for val.py?

is the following command correct?

python path/to/val.py --weights dataset1bestorlast.pt --data dataset2.yaml --img sameasusedfortrain

my thought on it is that what is the difference now? the YAML file for both of the datasets is same with the number of classes and the name too?? it is just one class!

Thanks a lot

[github-actions[bot]]

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

• Wiki – https://github.com/ultralytics/yolov5/wiki
• Tutorials – https://docs.ultralytics.com/yolov5
• Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

• Ultralytics HUB – https://ultralytics.com/hub
• Vision API – https://ultralytics.com/yolov5
• About Us – https://ultralytics.com/about
• Join Our Team – https://ultralytics.com/work
• Contact Us – https://ultralytics.com/contact

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 YOLOv5 🚀 and Vision AI ⭐!

[glenn-jocher]

@urbansound8K For single-class datasets, you can use precision, recall, and mAP (mean average precision) metrics for evaluation. As for your validation question, when using the same class names and number of classes in different datasets, you can use the same validation command as the one you mentioned. The YAML file should be identical in this case. Good luck!