mode collapse

[hd201708010401]

I have some problems with my training facdes dataset and maps dataset

The translation result on facdes is always the same, and there will be no change

The translation results on the maps dataset are shown in the figure below.

[JunlinHan]

Hello,
Yes, DCLGAN suffers from mode collapses in such datasets (see section 5.3 of the paper for a discussion).

CycleGAN/SimDCL might performs better.

[hd201708010401]

@JunlinHan Can you provide the pre-training model of SimDCL trained facades? My training model still has the phenomenon of model collapse, which cannot reproduce the effect in the article.

[JunlinHan]

@hd201708010401
Hello,
Oh I do not have a copy of this pre-trained model.

Did you use the default training setting? If possible, could you share your training log? Be careful with the number of GPU and batchsize.

[hd201708010401]

邮件已经收到，谢谢。I have received your email. Thank you for your letter.