Precision & Recall at Confidence Thresholds
This lesson is part of the course
In this lesson
You keep only the detections above seven confidence thresholds and calculate TP, precision, recall and F1 at each, to see the trade-off a deployment threshold makes.
Buy the course once for $9.99 to unlock every lesson and lab, the final exam and the certificate – lifetime access, no subscription.
Lessons in this course
- Bounding Box Geometry: Corners, Centre & YOLO Format Locked
- Intersection over Union (IoU) with MAX and MIN Locked
- Matching Predictions to Ground Truth: TP, FP & FN at IoU ≥ 0.5 Locked
- Precision & Recall at Confidence Thresholds Locked
- The Precision-Recall Curve, Point by Point Locked
- Average Precision: 11-Point vs All-Point Interpolation Locked
- mAP Across Classes & mAP@[.5:.95] Locked
- Class Confusion & Segmentation Metrics: Dice vs IoU Locked