Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

cant reproduce results on images having sky/lighter back ground #40

Open
farazBhatti opened this issue Jul 24, 2019 · 2 comments
Open

Comments

@farazBhatti
Copy link

farazBhatti commented Jul 24, 2019

@MathiasGruber Hi, I've used your code to get pretty decent results but when ever there is a lighter background in image such as sky , some noise is added as a result. But your deployed model on www.fixmyphoto.ai works fine. is there something missing in this code base ?

Screenshot from 2019-07-24 10-25-26
for reference..

@ghost
Copy link

ghost commented Aug 20, 2019

My private opinion
Would you check your model load pytorch_vgg16.h5 at each phase?
This is important because pre-trained vgg16 net is required for perceptual loss and style loss.
It not, it might give you blurriness or unexpected results.

Best regards,

@nywang2019
Copy link

@farazBhatti see there are some white blocks at the upper edge of your result, and a black block at the upper right corner. did you resolve this problem? my result images also have a white area at the upper left corner,and a black rect block at the upper right corner. why??? anyone can tell me? @Ferruginous-Hawk0215

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants