The Result

[YunShen66666]

Hi I try to run this code but got bad results. I also try to use vgg loss followed by lpips loss ,however the result is not as good as the demo. Could release a complete code ?

[zaidbhat1234]

Make sure you sure the VGG and LPIPS on the correct resolution. I mean the trained model works best when the losses are calculated on downsampled 256x256 image. The images in the results represent the results I got with the code. I hope you are using the correct weights for the backbone SG2

On 20-Dec-2020, at 5:09 PM, Bestyunshen [email protected] wrote:

Hi I try to run this code but got bad results. I also try to use vgg loss followed by lpips loss ,however the result is not as good as the demo. Could release a complete code ? https://user-images.githubusercontent.com/57790585/102712297-069b5600-42fb-11eb-9d78-116871053dd0.png https://user-images.githubusercontent.com/57790585/102712300-08fdb000-42fb-11eb-9789-4cfbfadb0968.png — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/zaidbhat1234/StyleGAN2-ADA/issues/1, or unsubscribe https://github.com/notifications/unsubscribe-auth/AH6R5MPJDHKRKZXEDUK3XQLSVXO7JANCNFSM4VDAWUWA.