Open mojganaz opened 6 years ago
@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!
It happened sometimes for DCGAN training. I would recommend that you use the latest GAN models as backend such as progressive-gans.
@mojganaz Same problem here , did you find out what was the issue and how did you fix it ?
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 .
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:![gen_00011](https://user-images.githubusercontent.com/5288525/33233290-9d00f692-d1e1-11e7-8f3d-5ec96ecf1acf.png)
Any idea on what the problem could be?