3d-mri-brain-tumor-segmentation-using-autoencoder-regularization icon indicating copy to clipboard operation
3d-mri-brain-tumor-segmentation-using-autoencoder-regularization copied to clipboard

Published 20 hours ago • verified publisher icon IAmSuyogJadhav

about group norm size

Open alalbiol opened this issue 5 years ago • 1 comments

Hi I am also implementing this algorithm and I want to check something with you...

I see that in your implementation you set the number of groups to 8: But in the paper myronenko says literally: "GN stands for group normalization (with group size of 8)"

so this can also understood that each group has 8 channels and therefore num_groups = inChans/8

What do you think?

alalbiol avatar Sep 24 '19 20:09 alalbiol

I think you got it right. I was a bit confused when implementing this part as well. Thank you for your valuable suggestion. I am a bit occupied now but will make sure to implement and test this one once I get some free time. Added to the to-do list!

IAmSuyogJadhav avatar Sep 26 '19 17:09 IAmSuyogJadhav