AdvSemiSeg icon indicating copy to clipboard operation
AdvSemiSeg copied to clipboard

Published 20 hours ago • verified publisher icon hfslyc

all losses are NaN

Open aoaoaoaoa opened this issue 4 years ago • 0 comments

why all my losses in experiment are NaN? I used the same code, parameters and dataset. like this "iter = 19998/20000, loss_seg = nan, loss_adv_p = nan, loss_D = nan, loss_semi = nan, loss_semi_adv = nan semi ratio: 1.0000"

aoaoaoaoa avatar Mar 05 '21 00:03 aoaoaoaoa