pytorch-MNIST-CelebA-GAN-DCGAN icon indicating copy to clipboard operation
pytorch-MNIST-CelebA-GAN-DCGAN copied to clipboard

Published 20 hours ago • verified publisher icon znxlwm

Why the loss of D quickly go down to zero?

Open Lycheezx opened this issue 3 years ago • 4 comments

Hello I ran your code of DCGAN implementation on dataset of MNIST but the quality of the generated images were poor. I have already tried to reduce the learning rate but it didn't work and the result was a far cry from yours. I am new to GAN and feel really confused. Did you change your parameter settings or do some other adjustments? Hope to get some advice from you, thank you very much!

Lycheezx avatar Sep 18 '20 06:09 Lycheezx

Same to you~

yuchenlichuck avatar Nov 07 '20 14:11 yuchenlichuck

Me too. I guess another repo https://github.com/eriklindernoren/PyTorch-GAN makes life much easier :)

Newbeeer avatar Apr 08 '21 10:04 Newbeeer

The results are really poor. I recommend this repo too.

Me too. I guess another repo https://github.com/eriklindernoren/PyTorch-GAN makes life much easier :)

omid-ghozatlou avatar Nov 28 '22 16:11 omid-ghozatlou

The MNIST result of DCGAN is very poor, I thought it was a problem with my environment. This is too bad.

Tang-08080103 avatar Jun 27 '23 07:06 Tang-08080103