How should I interpret the Precision curve?

WongKinYiu / yolov7

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

GNU General Public License v3.0

13.4k stars 4.23k forks source link

How should I interpret the Precision curve? #2098

Open seungdae251 opened 1 week ago

seungdae251 commented 1 week ago

P_curve

Hi. I trained a model with 2 classes (person, hardhat) and I got the result like this. Why does the precision score goes low towards confidence score 1.0 but soon raises up high to 1.0 as it gets closer to confidence score 1.0? How should I interpret this graph? Thanks