Aaron Siegel
Results
3
issues of
Aaron Siegel
ESRGAN was trained with a RaGAN but Real-ESRGAN was trained with a vanilla GAN. As far as I can tell there was no mention in the Real-ESRGAN paper as to...
RestoreFormer sets the number of attention heads to 8 here https://github.com/wzhouxiff/RestoreFormer/blob/f31d8e9a200a6200368d6fc27596d20499e0e991/configs/RestoreFormer.yaml#L30 but the HQ_Dictionary model leaves it as default, ie 1. Is this a bug or was it done on...