-
Hi, I am trying to train StyleGAN using a database of `npy` files. When I launch `python train.py PGAN -c maps.json` things run fine, but when instead I use `python train.py StyleGAN -c maps.json` I g…
-
hello, I don't understand what you're result, Input side face map, output positive face map?
-
(fb_gan_zoo) root@f56c103c5607:~/pytorch_GAN_zoo# python train.py StyleGAN -c config_cifar10.json --restart -n cifar10
Setting up a new session...
Running StyleGAN
size 10
50000 images found
AC-G…
-
Would it be a good idea to try to grow a trained network to a larger size than originally configured? I did around 750 000 iterations with a small resolution and the greyscale option. Now I don't real…
-
I can't imagine how hard this was to do. Second, I want to learn more about creating stylegan, to the point that I can create my own from scratch. Do you have any recommendations on resources where …
-
Do you have any saved checkpoints of your model trained on CelebA (or any other face dataset) that you could share? Thanks!
-
Sorry to bother you, I am a college student, I am very interested in your work, your work is great. I would like to cite your paper《Evaluating the Clinical Realism of Synthetic Chest X‑Rays Generated …
-
First of all, thanks for sharing! Very interesting.
I see that you experimented with SpectralNorm as well, can you share your insights on the effect it had on the training ?
-
I am trying to synthesize multi-channel volumes, using 3D progressive GAN, where one or several channels contain the segmentation annotations. I tried this a bit with the old code (2020) but with "nob…
-
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:
![…