Closed hugo-xie closed 2 years ago
any suggestion?
i'm also curious about that...
Mode collapse is still an open problem in GAN training, especially dealing with challenging distribution.
Are you using our default configuration file and training the model using 8 GPUs? Just curious if this has something to do with the batch size.
i have 2 gpus, and costom dataset. but same problem... i will try batch_size 2 and then comment
Maybe lower the learning rate or increase the reconstruction loss?
@mingyuliutw thanks for replying this question.. but still mode collapse happens... i try lr = 3e-5 ~ 1e-5 , reconstruction loss 0.15 ~ 0.3.
i have used this code for funit. (https://github.com/NVlabs/FUNIT) it works well... but funit has unnatural artifact, so i need coco-funit...
any suggestion?
any suggestion?
I collect more data about 10k each category. then mode collapse not happend.
hi, when I trained with coco_funit, In the first few epochs, the results are normal, but mode collapse appears from the 59th epoch. Is this normal? Will it also appear during your training?