Improved error messages regarding to issue #274. Classification and Segmentation application now ensure that num_of_classes and number of labels are the same and the user is told to check the histogram_ref file in case there is an issue. Also it throws an error if the number of classes is smaller than 2 as both classification and segmentation do not make sense with only 1 class.
UNet error message: states that input image size must be bigger than 88 and divisible by 8
Types of changes
[ x] Bug fix (non-breaking change which fixes an issue)
[ ] New feature (non-breaking change which adds functionality)
[ ] Breaking change (fix or feature that would cause existing functionality to change)
[x ] My code follows the code style of this project.
[ ] I have added tests to cover my changes.
[ ] All new and existing tests passed.
Todos
[x ] Tests
[ x] Documentation
Impacted Areas in Application
List general components of the application that this PR will affect:
*Segmentation and Classification Application
Status
READY
Description
Improved error messages regarding to issue #274. Classification and Segmentation application now ensure that num_of_classes and number of labels are the same and the user is told to check the histogram_ref file in case there is an issue. Also it throws an error if the number of classes is smaller than 2 as both classification and segmentation do not make sense with only 1 class.
UNet error message: states that input image size must be bigger than 88 and divisible by 8
Types of changes
Todos
Impacted Areas in Application
List general components of the application that this PR will affect: *Segmentation and Classification Application