About detecting many extra boxes
pengjizhi opened this issue · 7 comments
Hello author, thank you for your hard work!
Drawing on your ideas, I am developing my own single-stage object detection network, but there are a lot of extra boxes in the visualization results.
Since my network structure is deep, I guess it may be caused by the disappearance of the gradient or the explosion of the gradient, but why do these two situations lead to the appearance of a large number of abnormal boxes, can you give any suggestions?
In addition, I don't think this is the cause of nms. In fact, such results are already the results after nms.
How about your training loss ? @pengjizhi I think the value of your training loss may be very large.
@yqyao
Hello!
I also feel very strange about this, because in my display, the value of loss has been falling normally, so I didn't realize that this happened, and it wasn't until I tested it that I found a lot of exception boxes.
What dataset you use for training ? @pengjizhi
Have you solved this problem?I've met the same issue. The false positive rate was very high. @pengjizhi
@yin19961202
Hello, I haven't found the main cause of this problem at present, I guess it may be because the model is too complicated, and it caused gradient explosion or gradient disappearance during training.
Currently I can solve this problem by reducing the learning rate.