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)
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?

Answers (1)

Divya Gaddipati
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:

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!