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

About code execution issues in the psad.py file #1

Open
xgzng opened this issue May 20, 2024 · 4 comments
Open

About code execution issues in the psad.py file #1

xgzng opened this issue May 20, 2024 · 4 comments

Comments

@xgzng
Copy link

xgzng commented May 20, 2024

Hello, I want to skip the first four steps and directly perform the anomaly detection step, but when processing the test data, the code reported an error as shown in the following figure. Is it because the segmentation diagram of the test data is needed? If so, could you share the segmentation diagram of the test data
image
image

@oopil
Copy link
Owner

oopil commented May 27, 2024

You can download the mask using the google drive link. line 141-142 is for making one-hot segmentation label from single channel label. Please check the dimension of the label image, It should be [512, 512] and the shape of the one hot label will be [num_cls, 512, 512].

@xgzng
Copy link
Author

xgzng commented May 28, 2024

Hello, I downloaded the segmentation maps through the google drive link, but there is only the segmentation maps of normal data. Could you share the segmentation maps of the test data?

1 similar comment
@lhlhappy
Copy link

lhlhappy commented Jul 3, 2024

Hello, I downloaded the segmentation maps through the google drive link, but there is only the segmentation maps of normal data. Could you share the segmentation maps of the test data?

@oopil
Copy link
Owner

oopil commented Jul 4, 2024

Sorry for the late reply. I uploaded the segmentation maps of train/val/test data. Please try the link on the segmentation map again.

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