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

Local hints render area too small #74

Open
leochli opened this issue May 11, 2020 · 4 comments
Open

Local hints render area too small #74

leochli opened this issue May 11, 2020 · 4 comments

Comments

@leochli
Copy link

leochli commented May 11, 2020

Hi,

Your repo is amazing and I have been playing around with it. I am wondering is this normal?

I have given a lot of user guided points already. But the colorization seems not working, only a small portion is rendered.

Btw, I am running a GTX 2080 Ti gpu, yet the latency is still very high. Is there anything I was missing?

image

@leochli
Copy link
Author

leochli commented May 11, 2020

PyTorch model seems not working so well?

FYI, I am using PyTorch backend and your pretrained model. Here's the output of your own test image:
image

@richzhang
Copy link
Collaborator

Hi, are you using the caffe weights converted into PyTorch?

@leochli
Copy link
Author

leochli commented May 12, 2020

Hi Richard,

I was using the pytorch_trained.pth fetched from fetch_models.sh

@polymesh
Copy link

polymesh commented Aug 14, 2020

I'm having the same issue. I provide a hint and the affected area is so small I can barely see anything change. If I cluster up a ton of hints, it looks a little more splotchy with color. Almost seems like this is manual coloring - nothing like what we see in the video showing what it can do.

I'm using the PyTorch model on a GTX 980 Ti on Windows 10. Followed the installation instructions. Using Python 3.7 since that's the latest python that supports Qt4.

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

3 participants