How to train on a customized dataset?

[duynn912]

Hi @Ze-Yang,

I successfully re-produce your result with your readme. And I now want to train on my customized dataset which have the format similar to PASCAL. The dataset have 150 base classes and 50 novel classes. When I train base classes, it is ok. However, when transferring to novel classes, the loss is just nan!

I also change the classes in voc0712.py and some line in RFB_NET_vgg.py to be suitable to 150 base classes and 50 novel classes:

So Could you help me out why it is in the case or there is any lines in some files that I have to change?

[Ze-Yang]

Nan loss may originate from various reasons, e.g., lr, initialization, etc. Our code does not support for customized dataset and you need to get around it by yourself. Thanks.