tuya
tuya
+1，很早以前就开始闪退了
@jerrykuku 大神，能不能在Lean固件编译里面加入这个主题的设定，每次更新固件还要多装一个ipk，有点强迫症
@zorrose82 你写的是对的，但是这样还得自己装一个luci-app-argon-config_0.9-20210309_all.ipk，我是想知道能不能直接在git环节把这个ipk一起包含了，每次编译就不用再额外装了
@zorrose82 大聪明！！我试试！
@zorrose82 非常感谢 我试试！
@zorrose82 成功了，谢谢！
+1
Labels are shared by Gen and Dis, Gen will use both noise array Z and label to generate fake image, Dis will try to give the correct class label referred...
you almost said it in last sentence. The classifier in Dis will be fed with true dataset and real_label loss will be the difference between the truedata label and predict...
I solve it by using some tricks! Thanks anyway!