Integrating a Tailored Auto-Encoder Model into Generative Model Application

[dongyang0122]

Fixes #7858.

Description

Integrating a tailored auto-encoder model into the generative model application to improve the production of high-dimensional 3D images, specifically sized at 512 x 512 x 512.

Types of changes

• 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).
• 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.
• In-line docstrings updated.
• Documentation updated, tested make html command in the docs/ folder.

[ericspod]

The requirements for this app aren't being installed by the tests, this is why they are failing. The generative models repo is being integrated into Core by @virginiafdez currently, shall we wait for that to complete and then we can eliminate the requirement here for the external repo? Thanks!

[dongyang0122]

Hi @Nic-Ma @KumoLiu @ericspod @yiheng-wang-nv , the PR is dependent on another monai related project. I am not sure how to pass the some tests without installing the package. Thanks.

[dongyang0122]

Hi @ericspod, we are currently preparing to release a new MONAI feature within the next few days. Initially, we may need to enable this application, followed by integrating the changes once another pull request is ready for incorporation.

[dongyang0122]

I am not sure what the following error (premerge / flake8-py3 (codeformat) (pull_request) Failing after 3m) is from. This is not from my scripts.

tests/test_pad_collation.py:116:12: E721 Use is and is not for type comparisons, or isinstance() for isinstance checks
|
114 | self.assertTrue(len(set(shapes)) > 1) # inverted shapes must be different because of random xforms
115 |
116 | if t_type == dict:
| ^^^^^^^^^^^^^^ E721
117 | batch_inverse = BatchInverseTransform(dataset.transform, loader)
118 | for data in loader:
|

Found 3 errors.
Check failed!
Please run auto style fixes: ./runtests.sh --autofix
Error: Process completed with exit code 1.

[KumoLiu]

I am not sure what the following error (premerge / flake8-py3 (codeformat) (pull_request) Failing after 3m) is from. This is not from my scripts.

tests/test_pad_collation.py:116:12: E721 Use is and is not for type comparisons, or isinstance() for isinstance checks | 114 | self.assertTrue(len(set(shapes)) > 1) # inverted shapes must be different because of random xforms 115 | 116 | if t_type == dict: | ^^^^^^^^^^^^^^ E721 117 | batch_inverse = BatchInverseTransform(dataset.transform, loader) 118 | for data in loader: |

Found 3 errors. Check failed! Please run auto style fixes: ./runtests.sh --autofix Error: Process completed with exit code 1.

Hi @dongyang0122, you can merge dev to solve the error, thanks!

[dongyang0122]

Shall we proceed if no further questions? Thanks. @KumoLiu @mingxin-zheng @ericspod

[ericspod]

Shall we proceed if no further questions? Thanks. @KumoLiu @mingxin-zheng @ericspod

I'm good if others are.

[KumoLiu]

/build

[mingxin-zheng]

I have no other comments now and okay to merge it as long as the tests pass. Thanks!

[KumoLiu]

/build