Skip to content

Mayo-Radiology-Informatics-Lab/ConfusionMatrix_Dice_Recall_with-cupy

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 

Repository files navigation

Confusion matrix, dice, accuracy with cupy

Scikitlearn 'confusion matrix' extraction is very slow for digital pathology images of 30k x 30k pixels. Instead cupy library with matrix multiplication could be used to speed up the calculation.

Need cupy library; check for correct version compatible with your cudatoolkit. https://pypi.org/project/cupy/

Use Metric_withcupy.py to calculate metric and save in new folder.

Use Metric_dicecupy_average.py to take average of all files.

About

Scikitlearn 'confusion matrix' extraction is very slow for digital pathology images of 30k x 30k pixels. Instead cupy library with matrix multiplication could be used to speed up the calculation.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Python 100.0%