To evaluate object detection models like R-CNN and YOLO, the mean average precision (mAP) is used. The mAP compares the ground-truth bounding box to the detected box and returns a score. The higher the score, the more accurate the model is in its detections.
Usually, the object detection models are evaluated with different IoU thresholds where each threshold may give different predictions from the other thresholds. Assume that the model is fed by an image that has 10 objects distributed across 2 classes. How to calculate the mAP?
To calculate the mAP, start by calculating the AP for each class. The mean of the APs for all classes is the mAP.
#MeanAveragePrecision #AL #ML #Probyto #ProbytoAI
Subscribe and follow us for latest news in Data Science, Machine learning, technology and stay updated!