Issues
- 0
- 2
change input data
#9 opened by sakh251 - 1
Relation with bad GANs
#8 opened by sakh251 - 2
hello. When the loss_unsupervised is nearly equal with 0, the loss_supervised is still pretty large, how should I do to get better result?
#6 opened by fishishappyandfree - 12
hello, the question about the accuracy on the test data by using default configs
#5 opened by fishishappyandfree - 6
i don't understand code: torch.mean(F.softplus(logz_unlabel) why add F.softplus activation?
#4 opened by daixiangzi - 2
- 1
- 1