torch.nn.modules.module.ModuleAttributeError: 'StaticUnconditionalGAN' object has no attribute '_next_scale_int' #448
-
Dear authors, Attached is the config file. |
Beta Was this translation helpful? Give feedback.
Replies: 4 comments
-
Hey @aloreggia, thanks for your interest in our project. |
Beta Was this translation helpful? Give feedback.
-
Besides misusing |
Beta Was this translation helpful? Give feedback.
-
Thank you for your swift reply, now it is working. Sorry, for the silly questions, I'm pretty new with GANs for data augmentation. Do you have any tips for better using your framework for this purpose? Thanks, |
Beta Was this translation helpful? Give feedback.
-
This is not a silly question at all 😄 . You can try to fine-tune a well-trained GAN with your data. |
Beta Was this translation helpful? Give feedback.
Besides misusing
PGGANFetchDataHook
,scale
inResize
augmentation in the data pipeline should be the same asout_size
of theStyleGANv2Generator
. In your config,scale
andout_size
are 256 and 128 respectively.