search

znxlwm / pytorch-MNIST-CelebA-GAN-DCGAN

Pytorch implementation of Generative Adversarial Networks (GAN) and Deep Convolutional Generative Adversarial Networks (DCGAN) for MNIST and CelebA datasets
507 stars 145 forks source link

Why the loss of D quickly go down to zero? #12

Open Lycheezx opened 3 years ago

Lycheezx commented 3 years ago

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!

yuchenlichuck commented 3 years ago

Same to you~

Newbeeer commented 3 years ago

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

omid-ghozatlou commented 1 year ago

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 :)

Tang-08080103 commented 1 year ago

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