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

Incorrecct segmentation results #2

Open
rocker12121 opened this issue Nov 3, 2022 · 2 comments
Open

Incorrecct segmentation results #2

rocker12121 opened this issue Nov 3, 2022 · 2 comments

Comments

@rocker12121
Copy link

Hello,

I have successfully generated the semantic segmentation results by setting up the environment and running the command:
chmod +x demo_test.sh
./demo_test.sh

But I don't get the correct results. The resulting segmented image is all green with a bit of a brown color. Can you guide me regarding this? Any help is appreciated.

@kukby
Copy link
Owner

kukby commented Nov 5, 2022

Hello,
Thank you very much for your interest in my project.
The situation you described may be caused by the training time being too short. The project required three days of training to achieve the described effect when using Resnet18 as a backbone network.

@rocker12121
Copy link
Author

But I am using your pre-trained model and just trying it on an image for semantic segmentation.

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