search

dome272 / VQGAN-pytorch

Pytorch implementation of VQGAN (Taming Transformers for High-Resolution Image Synthesis) (https://arxiv.org/pdf/2012.09841.pdf)
MIT License
443 stars 73 forks source link

Black border #1

Closed gogobd closed 2 years ago

gogobd commented 2 years ago

Hi! Thank you for sharing this project and for the video tutorial on writing it! I have a question: why do the generated images all have a black border? Can this be fixed? I tried to add "reflect" to all Conv2d layers but that didn't fix it.

gogobd commented 2 years ago

I was looking into this and I think the border was from the way the images had been concatenated, i counted 256 pixels of image data, then 2 pixels on each side of the images i got from the decoder, so there's no actual issue here. Closing this.