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

Can only obtain probability images and not a single class label image #17

Open
davodogster opened this issue Jun 7, 2019 · 3 comments
Assignees
Labels
enhancement New feature or request

Comments

@davodogster
Copy link

Are you able to program CATS so that when applying a classifier to an image or a folder of images you can select “labels” instead of “probability maps”. This would give a multi-class label image with each pixel assigned to the class with the highest probability. The probability maps are difficult to deal with when there are more than two classes and you have to arbitrarily chose a threshold for each image (and the user might have 20 or 200 classified probability maps for each class of each image)

@tischi
Copy link
Collaborator

tischi commented Jun 7, 2019

will work on it!

@tischi tischi self-assigned this Jun 7, 2019
@tischi tischi added the enhancement New feature or request label Jun 7, 2019
@tischi
Copy link
Collaborator

tischi commented Jun 15, 2019

Hi Sam,
Both within the CATS GUI as well as within the BatchClassification plugin there is now an option to export as label masks.
Let me know how it works for you!

@davodogster
Copy link
Author

Hi Christian, there is no option to export probabilities as one image(label masks) under the "apply classifier to multiple images". It would be a great feature if you could implement this.

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

No branches or pull requests

2 participants