Closed gofixyourself closed 2 years ago
Yes, the pipeline is right. Some hyperparameters may also need to be adjusted.
@gofixyourself DO you get the results of 512x512? how does it performance?
Yes, the pipeline is right. Some hyperparameters may also need to be adjusted.
Can you share the command line about how to train 256x256?
Yes, the pipeline is right. Some hyperparameters may also need to be adjusted.
Can you share the command line about how to train 256x256?
Please refer to exp/cips3d/bash/ffhq_exp
.
Hi! You did a great job, thanks for such a great paper and promptly published CIPS-3D code.
I've already gotten good results with your pipeline, but for images with resolution 64x64. Now I'm waiting the results of generating images with a resolution of 128x128. And I will further train for higher resolution images.
I understand correctly, in order to get 512x512 images, I need to convert the original FFHQ dataset once again through your script dataset_tool.py, but specifying the resize for 512 in it? And after I need to run training pipeline with lower values for generator learning rate and discriminator learning rate?
Thanks!