Is my average precision good? Yolov4

Hello guys, I trained Yolov4 detector… I copied almost the whole code from MathWorks example of object detection using yolov4, I just loaded my own data, which contains 1865 images and 5 diferent classes… after training which took around 10 hours average precision is 93%… did I do good work or is this info of average precision irelevant? How do I know if i trained my detector good?

Answer 1

[Neha]

Hi Adrian,

I understand that you wish to know if the average precision of your YOLOv4 detector is a relevant metric and if it’s result is good enough. Since average precision represents the accuracy of the detector and is a vector of scores for each object class in the order specified by ground truth data, 93% is a very good result. Apart from average precision there are other metrics like Recall, F1-score and Precision which can be considered. You can refer Evaluate Detection Precision for more information about calculating precision and recall.

The F1-score is the harmonic mean of precision and recall, calculated as:

F1 = 2 * (precision .* recall) ./ (precision + recall); 

Apart from metrics, there are other factors which can determine if the detector has been trained well:

1. Test your YOLOv4 model on a validation dataset that was not used during training. This will give you an indication of how well your model will perform on new data.
2. Check if there are any specific classes that your YOLOv4 model is having trouble detecting accurately. If so, you may need to re-evaluate your annotations, gather more data, or consider using other techniques such as data augmentation or minority oversampling to improve the detection performance on those classes.
3. You may also look into optimizing the hyperparameters using automatic tools like Hyperparameter Optimization in Classification Learner App.

Hope this helps!