DRN_CVPR2020
DRN_CVPR2020 copied to clipboard
the number of train epoch
thank you for your excellent work! I am using you FSM in my object. I have a question that whether your method need more epoch to fit data. As you mentioned in your article, in DOTA and HRSC2016, your need 140 epochs to train. thank for your reply
@sunpeng96 Thanks for your interest in our work. The training time(epoch) before and after adding the FSM is the same. The baseline method is also trained for 140 epochs. We did not conduct experiments to compare the performance when training different epochs.