Can someone suggest what changes should I do to the training scripts to use multiscale discriminator instead of projected discriminator?
I have tried training with projected discriminator, but the ID is not very well pasted on the target face. I have trained till 250k epochs with batch size 40.
Some tips about training can also help.
Can someone suggest what changes should I do to the training scripts to use multiscale discriminator instead of projected discriminator?
I have tried training with projected discriminator, but the ID is not very well pasted on the target face. I have trained till 250k epochs with batch size 40.
Some tips about training can also help.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Can someone suggest what changes should I do to the training scripts to use multiscale discriminator instead of projected discriminator?
I have tried training with projected discriminator, but the ID is not very well pasted on the target face. I have trained till 250k epochs with batch size 40.
Some tips about training can also help.