大佬你好,训练的时候出现这个问题了,这是啥情况啊
wangshicr7 opened this issue · comments
wangshicr7 commented
loss_semi_adv_value += loss_semi_adv.data.cpu().numpy()[0]/args.lambda_semi_adv
IndexError: too many indices for array
Wayne Hung commented
This repo was using Pytorch 0.2, which has a different behavior than recent version on single scalar. You could remove the [0] and it should work.
gxwangupc commented
loss_semi_adv_value += loss_semi_adv.data.cpu().numpy()[0]/args.lambda_semi_adv
IndexError: too many indices for array
hahhahahha