Training DCGAN will result in gray images

[mojganaz]

I am using train_dcgan.py to train the network over outdoor_64 images. However, after about 10 epochs of training, the generated images by the network become gray. Here is an example output file:

Any idea on what the problem could be?

[boluoweifenda]

@mojganaz I have the same question, I think it may be caused by some hyperparameters and generator "learns" to produce gray images to minimize it's loss function. I haven't fix the problem yet, please let me know if you have any idea, thanks!

[junyanz]

It happened sometimes for DCGAN training. I would recommend that you use the latest GAN models as backend such as progressive-gans.

[AbhishekSen]

@mojganaz Same problem here , did you find out what was the issue and how did you fix it ?

[junyanz]

DCGAN is pretty old. If you just need to train a GAN model, you can probably try more recent work such as GAN-stability or style-gan .