Deci-AI / super-gradients

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.
https://www.supergradients.com
Apache License 2.0
4.54k stars 496 forks source link

How to print and save validation metrics results? #1766

Closed rupher3222 closed 8 months ago

rupher3222 commented 8 months ago

💡 Your Question

How can I train a custom dataset like YOLOV8 so that it automatically generates validation metrics results (F1-score, p-r curve, mAP@0.5, mAP@0.5_0.95, Precision, Recall) and also saves the graphs related to them? I have no idea how to modify the code for this. Please help!!

Versions

No response

BloodAxe commented 8 months ago

There is a PR related to this issue https://github.com/Deci-AI/super-gradients/pull/1772