-
Notifications
You must be signed in to change notification settings - Fork 4
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
3DPN #5
Comments
implementation wise we ultimately went with predicting volume CT (bone and tissue separately) and Bone mask. the tissue component is refined by the inverse of bone mask. This seemed to produce better results. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hello, author, I read the article xraysyn in the first stage of training output corresponds to Volume CT and Bone Mask, but your code seems to output 3 channels, corresponding to:
bone_mask = vol_pred_temp[:,[0]]
bone_ct = vol_pred_temp[:,[1]]bone_mask
tissue_ct = vol_pred_temp[:,[2]](1-bone_mask)
Is there any difference between vol_pred_temp[:,[1]] and vol_pred_temp[:,[2]]?
The text was updated successfully, but these errors were encountered: