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

3D segmentation Demo Activation Maps Visualisation #19

Open
KristoferLintonReid opened this issue Nov 24, 2021 · 1 comment
Open

3D segmentation Demo Activation Maps Visualisation #19

KristoferLintonReid opened this issue Nov 24, 2021 · 1 comment

Comments

@KristoferLintonReid
Copy link

Hi,

I have worked through the 3D segmentation demo on using nnUNet. Can you please add some code to visualize the activation maps like what you have added in the table column 3?

I may be misunderstanding is what looks like segmentation masks in the .nii.gz files in the inference_results folder the attention maps? Otherwise, can you add some example code to visualize maps from the .pkl file?

Thanks

@Karol-G
Copy link
Collaborator

Karol-G commented Nov 25, 2021

Hi,

I have worked through the 3D segmentation demo on using nnUNet. Can you please add some code to visualize the activation maps like what you have added in the table column 3?

I am not aware that there are python libraries to visualize 3D data / 3D attenion maps in python. You need to download the attention_map.nii.gz files and open them with an nii.gz viewer like ITK-Snap or MITK.

I may be misunderstanding is what looks like segmentation masks in the .nii.gz files in the inference_results folder the attention maps? Otherwise, can you add some example code to visualize maps from the .pkl file?

In the nnU-Net demo the attention maps are saved in the folder attention_maps. The folder inference_results is probably a folder used by the nnU-Net.

Best
Karol

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