StyleGAN.pytorch
StyleGAN.pytorch copied to clipboard
huangzh13
A PyTorch implementation for StyleGAN with full features.
im continuing my training from checkpoint. the quality of the output samples a bit reduced. Is it normal ? This is last sample i stopped.  This...
Hi, I wonder if you or anybody else implemented the multi-GPU run feature or not? Or can you please instruct me how to add multi-gpu train to this code? Thanks,
Could you give an example for how to train a model under conditional is set as True? Or give some suggestion on it ? Thx!
I'm trying to generate some samples from generator that I already trained. While training, I got ok results like these:  But when I try to generate samples I got...
Hi how do i attain the latent vector to control over my results? in `generate_sample.py` you have give a input param dlatent like this: ``` parser.add_argument("--input", action="store", type=str, default=None, help="the...
Hi! Thanks for your codes. I noticed that you have generated pictures based on ffhq128, I couldn't find this model, so would you like to provide the pre-trained model for...
Hello, @huangzh13, Firstly, great job on the code. It's quite good. I just wanted to point out that there could be a possible mistake in porting the official tensorflow pretrained...
hi, I get the following error even at the lowest resolution. ``` RuntimeError: cuDNN error: CUDNN_STATUS_NOT_SUPPORTED. This error may appear if you passed in a non-contiguous input. ``` It somehow...
First of all, thank you for making this amazing code -- the outputs are very realistic! However, it appears that the generator isn't deterministic with respect to it's input latent...
