You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I trained a yolo-nas model for an object detection dataset and I noticed something weird. The recall and mAP value of the model were at 98% and 95% respectively however the precision was barely 20%.
This comes off as a surprise to me that how is the mAP and recall high, but the precision so low. Why is that ? Can somebody elaborate ?
The same model when trained with yolov5 gave precision, recall and mAP value of 94%.
Versions
No response
The text was updated successfully, but these errors were encountered:
Hi @HissaanAli .
It sounds like you need to tune the confidence level of the NMS.
In the post prediction callback, pass conf=0.9, for example. And see if the precision-recall tradeoff looks better
💡 Your Question
I trained a
yolo-nas
model for an object detection dataset and I noticed something weird. The recall andmAP
value of the model were at 98% and 95% respectively however the precision was barely 20%.This comes off as a surprise to me that how is the mAP and recall high, but the precision so low. Why is that ? Can somebody elaborate ?
The same model when trained with yolov5 gave precision, recall and mAP value of 94%.
Versions
No response
The text was updated successfully, but these errors were encountered: