faster R-CNN training loss was small but performance very poor

4 次查看（过去 30 天）

jingxue chen 2020-10-14

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/613796-faster-r-cnn-training-loss-was-small-but-performance-very-poor

评论： Madhav Thakker 2020-11-23

Hi, I am training an faster R-CNN detector on my own dataset, the training loss can below 0.1 when training come to an end. But APs on test dataset are about 0.5, and them seems to be worser when I add epoch. I am wondering what's wrong? And when should I stop training? The training dataset has 3500 images and 5 classes.

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Madhav Thakker 2020-11-23

Do the images in test set follow the same distribution in training set? It is unlikely that the model trained on some images would work well on different distribution of images.

If the images are of similar distribution, check that you are not overfitting to the training set.

请先登录，再进行评论。

请先登录，再回答此问题。