style-based-gan-pytorch
style-based-gan-pytorch copied to clipboard
Implementation A Style-Based Generator Architecture for Generative Adversarial Networks in PyTorch
 If you add another layer before the last loop so that the final output is 513 channels, but the last convolution accepts 512 channels, there is an...
The sample.png generated using the generate.py file looks strange. I wonder what factors may cause this. (By the way, this sample.png has an abstract appearance but the effect of style-mixing...
Dear author, thanks for your code. But I have some trouble in the procedure of backward. The error message is: **RuntimeError: one of the variables needed for gradient computation has...
我长期研究和改进GAN,如果对GAN或者深度学习感兴趣的可以联系我,联系方式,wechat: lovedaixiaobaby
Thanks for your code! I first run:python prepare_data.py --out LMDB_PATH --n_worker N_WORKER DATASET_PATH and then I want to train Stylegan with:python train.py --mixing LMDB_PATH, I met the question below: ![2023-07-18...
Thank you for your good job! When I use your code, the function of each python file is still relatively vague. There is no comment in the codes, so I...
I downloaded the source code for stylegan and tried to run it on my machine. but the model cannot be successfully trained. This is my error message My machine is...
Thanks a lot for the code. It really helps. I'm a beginner in this area. I got interrupted when I was training this model. Now in checkpoint I got 040000...
i choose ffhq-dataset's thumbnails128x128. I'm curious about which parameters need to be modified?should the --max_size in train.py be modified? should the number of layers in model.py be modified, such as...