Open feitiandemiaomi opened 4 years ago
Hmm looks like your starting learning rate is too high. My guess is you tried to train with a learning rate of 1e-3
you should set it to 1e-4
. It is totally normal that the printed learning rate increases this is because chainer calculates some crazy things for the Adam optimizer.
@Bartzi I will try, Thanks a lot!
@Bartzi Thanks for your good job When I try to train the fsns according to readme, I find the loss are unusual, which shows as follows: ps: my train dataset is the original fsns test ,val dataset is the original val I do not change code ,so it trains in default ,and I have two gusses,one is the my configuration of the fsns dataset has error ,the final gt shows : Is it right? And the other guess is that the lr is too big, as the number of iterations increases, the lr becomes larger . I will go on training. Looking forward to your reply