-
Notifications
You must be signed in to change notification settings - Fork 1.1k
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
6676 port generative inferers #7379
6676 port generative inferers #7379
Conversation
…nels to channels to remain consistent with other networks added Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
I, Mark Graham <[email protected]>, hereby add my Signed-off-by to this commit: 495758f I, Mark Graham <[email protected]>, hereby add my Signed-off-by to this commit: 3ebaf9f Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for the PR.
Looks like we introduce one inferer for one model, can we refactor them such as make DiffusionInferer
more general if comes into other model. Perhaps accept pre-process or post-process or same thing others.
Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
Co-authored-by: YunLiu <[email protected]> Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@ericspod, could you please also help review this PR?
Thanks!
Co-authored-by: YunLiu <[email protected]> Signed-off-by: Mark Graham <[email protected]>
Co-authored-by: YunLiu <[email protected]> Signed-off-by: Mark Graham <[email protected]>
Co-authored-by: YunLiu <[email protected]> Signed-off-by: Mark Graham <[email protected]>
Co-authored-by: YunLiu <[email protected]> Signed-off-by: Mark Graham <[email protected]>
Co-authored-by: YunLiu <[email protected]> Signed-off-by: Mark Graham <[email protected]>
Co-authored-by: YunLiu <[email protected]> Signed-off-by: Mark Graham <[email protected]>
Co-authored-by: YunLiu <[email protected]> Signed-off-by: Mark Graham <[email protected]>
Co-authored-by: YunLiu <[email protected]> Signed-off-by: Mark Graham <[email protected]>
Co-authored-by: YunLiu <[email protected]> Signed-off-by: Mark Graham <[email protected]>
Co-authored-by: YunLiu <[email protected]> Signed-off-by: Mark Graham <[email protected]>
Co-authored-by: YunLiu <[email protected]> Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
I, Mark Graham <[email protected]>, hereby add my Signed-off-by to this commit: 553c94b Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
/build |
Hi @marksgraham, could you please check-pick the commit here after it merged which caused a CI error and could not merge? |
/build |
Hi, |
I think the error is caused by the update from flake8-bugbear instead of test_ordering. But anyway it is also not related to the PR, you could pin the version to avoid the error first, I will try to create a PR to fix it in the dev branch. |
Signed-off-by: Mark Graham <[email protected]>
Signed-off-by: Mark Graham <[email protected]>
/build |
Hi @marksgraham, now the error seems related to the
Line 318 in 25f1901
|
Signed-off-by: Mark Graham <[email protected]>
hi @KumoLiu I have removed the test. As far as I can tell, the test does not make sense and does not seem to be usefully testing any part of the ordering code. |
/build |
Part of Project-MONAI#6676 . ### Description Adds Inferers to assist with training and sampling from diffusion models and controllers. Also takes the opportunity to make two changes which slipped through the previous PRs: - rename the `num_channels` arg in the spade diffusion unet to `channels` to be consistent with all the other models added from Generative - this slipped through in the networks PR. - add the `Ordering` class to `__init__.py` for easier import ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. --------- Signed-off-by: Mark Graham <[email protected]> Co-authored-by: YunLiu <[email protected]> Signed-off-by: Mark Graham <[email protected]>
Part of #6676 .
Description
Adds Inferers to assist with training and sampling from diffusion models and controllers.
Also takes the opportunity to make two changes which slipped through the previous PRs:
num_channels
arg in the spade diffusion unet tochannels
to be consistent with all the other models added from Generative - this slipped through in the networks PR.Ordering
class to__init__.py
for easier importTypes of changes
./runtests.sh -f -u --net --coverage
../runtests.sh --quick --unittests --disttests
.make html
command in thedocs/
folder.