how to print dice of multi class segmentation like nnunet? #4231
-
thanks for brilliant work! |
Beta Was this translation helpful? Give feedback.
Answered by
yiheng-wang-nv
May 5, 2022
Replies: 1 comment 1 reply
-
Hi @jjhhan , you can use |
Beta Was this translation helpful? Give feedback.
1 reply
Answer selected by
jjhhan
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi @jjhhan , you can use
scores = dice_metric_batch.aggregate()
, thenprint(scores)
to see the results for each channel.There is an example which also has multiple classes:
https://github.com/Project-MONAI/tutorials/blob/ff586e0cf24ac164553327b9453edab147cffa9e/3d_segmentation/brats_segmentation_3d.ipynb