From the course: Deep Learning and Computer Vision: Object Detection with PyTorch
Join today to access over 24,900 courses taught by industry experts.
Evaluating object detection models - PyTorch Tutorial
From the course: Deep Learning and Computer Vision: Object Detection with PyTorch
Evaluating object detection models
- [Instructor] Welcome back. In this video, we learn how to evaluate the performance of object detection models using key metrics such as intersection over union and mAP, which stands for mean average precision. These metrics help us understand how well our model is detecting objects and how accurately it's localizing them. Let's start with intersection over union, which measures the overlap between the predicted bounding box and the ground truth bounding box. Intersection over union is calculated by dividing the area of overlap between the two bounding boxes by the area of union. The formula for intersection over union is straightforward. It's the area of overlap divided by the area of union. A higher intersection over union value means the predicted bonding box aligns well with the ground truth while lower value indicates poor alignment. This function calculates intersection over union by first finding the intersection area and then dividing it by the union area. Intersection over…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.