Skip to content
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

Porting of MedNIST DDPM model-zoo from MONAI Generative #721

Open
wants to merge 7 commits into
base: dev
Choose a base branch
from

Conversation

virginiafdez
Copy link

Description

Initial porting from the Generative model-zoo of the mednist-ddpm model (https://github.com/Project-MONAI/GenerativeModels/tree/main/model-zoo/models/mednist_ddpm/bundle).

The bundle files are tested within the docs/2d_ddpm_bundle_tutorial.ipynb

Status

Ready

Please ensure all the checkboxes:

  • Update version and changelog in metadata.json if changing an existing bundle.
  • Please ensure the naming rules in config files meet our requirements (please refer to: CONTRIBUTING.md).
  • Ensure versions of packages such as monai, pytorch and numpy are correct in metadata.json.
  • Avoid using path that contains personal information within config files (such as use /home/your_name/ for "bundle_root").

virginia and others added 5 commits January 12, 2025 14:39
…erify_bundle to pass the check for model.pt, since the requirement for two models (autoencoder and diffusion_model) makes sense for them to keep their specific names.

Modification of inference.json to add dummy attributes to pass the ConfigWorkflow check.
Modification of large_files.yml so that models are .pt and not .pth.
@virginiafdez virginiafdez changed the title Mednist ddpm Porting of MedNIST DDPM model-zoo from MONAI Generative Jan 13, 2025
val_mean_abs_error:
_target_: MeanAbsoluteError
output_transform: $monai.handlers.from_engine([@pred, @label])
metric_cmp_fn: '$scripts.inv_metric_cmp_fn'
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If you wanted to add operator to your imports you could do metric_cmp_fn: '$operator.lt' and eliminate the code definition. I think this will work just fine but needs checking.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants