- Make sure you have enough data for training the network.
- Try using a different base network. Refer to this link: https://www.mathworks.com/help/vision/ref/trainfasterrcnnobjectdetector.html#bvkk009-1-network
- Make sure the PositiveOverlapRange and NegativeOverlapRange are adjusted according to your data
How to know if the faster R-CNN is trained to a good state according to Mini-Batch loss and accuracy trends
11 views (last 30 days)
Show older comments
jingxue chen on 12 Oct 2020
Answered: Divya Gaddipati on 29 Dec 2020
Hello, I am trying to train a faster R-CNN detector using my dataset, but the result is much worse than yolo V2, which is different from some papers. I think there is something wrong when training faster R-CNN. So I wonder how to know if I should change hyperparameters and when to stop training according to Mini-Batch loss and accuracy trends?
Divya Gaddipati on 29 Dec 2020
You should refer to this example in trainFasterRCNNObjectDetector documentation page to understand the role of various inputs going into trainingOptions function. For one, if you are training your network using adam solver, consider using the other training options associated with it like GradientDecayFactor and SquaredGradientDecayFactor.
You could also try couple of other things:
You can also refer to the answer posted for a similar question to understand how faster R-CNN works:
Find more on Object Detection in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!Start Hunting!