search

odegeasslbc / FastGAN-pytorch

Official implementation of the paper "Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis" in ICLR 2021
GNU General Public License v3.0
600 stars 100 forks source link

Getting Garbage from Generator? #54

Open Hana-Ali opened 1 year ago

Hana-Ali commented 1 year ago

Hello,

I just have a question. Why are the reconstructed images obtained from the discriminator, while only garbage is obtained for me from the generator? I don't know if this is the intended functionality, but when I look at the image created by the gen, all I see is: image

When I look at the outputted reconstruction from the discriminator, however, I see this: image

Shouldnt the generator output the reconstruction, not discriminator?

janspiegel commented 1 year ago

Hi I was slightly confused by this as well - the reconstructed images are probably not a very helpful way of monitoring generator performance - I think training for longer will produce better generator results.