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

Enhance maisi notebooks with visualization #1855

Closed
KumoLiu opened this issue Oct 9, 2024 · 3 comments · Fixed by #1860 or #1861
Closed

Enhance maisi notebooks with visualization #1855

KumoLiu opened this issue Oct 9, 2024 · 3 comments · Fixed by #1860 or #1861
Assignees

Comments

@KumoLiu
Copy link
Contributor

KumoLiu commented Oct 9, 2024

  • After running inference in the maisi_diff_unet_training_tutorial.ipynb notebook, the resulting nii.gz file is saved to disk but not displayed within the Jupyter Notebook. We suggest displaying the generated 3D image in at least three views (x, y, z).

  • Similarly, when performing inference in the maisi_train_controlnet_tutorial.ipynb notebook, the resulting nii.gz file is saved but the generated 3D image is not displayed within the Jupyter Notebook.

@KumoLiu
Copy link
Contributor Author

KumoLiu commented Oct 9, 2024

Hi @dongyang0122 and @guopengf, could you please help enhance the tutorial with the feedback from internal test? Thanks.

@dongyang0122
Copy link
Collaborator

The training tutorial uses synthetic data and simplified parameters to effectively demonstrate the entire process. However, it is important to note that the model will not be fully trained and may produce results resembling noise. We provide guidance on saving these results locally, enabling users to monitor the training progress as needed. Given this context, visualizing the “noise” in three different views within the tutorial notebook is not necessary.

@KumoLiu
Copy link
Contributor Author

KumoLiu commented Oct 9, 2024

The training tutorial uses synthetic data and simplified parameters to effectively demonstrate the entire process. However, it is important to note that the model will not be fully trained and may produce results resembling noise.

Oh yes, I forgot that, make sense to me. Thanks for quick reply.

KumoLiu added a commit to KumoLiu/tutorials that referenced this issue Oct 10, 2024
Signed-off-by: YunLiu <55491388+KumoLiu@users.noreply.github.com>
KumoLiu added a commit that referenced this issue Oct 10, 2024
Fixes #1855.

Add image visualization in the diffusion model training tutorial.

### Description
A few sentences describing the changes proposed in this pull request.

### Checks
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [ ] Avoid including large-size files in the PR.
- [ ] Clean up long text outputs from code cells in the notebook.
- [ ] For security purposes, please check the contents and remove any
sensitive info such as user names and private key.
- [ ] Ensure (1) hyperlinks and markdown anchors are working (2) use
relative paths for tutorial repo files (3) put figure and graphs in the
`./figure` folder
- [ ] Notebook runs automatically `./runner.sh -t <path to .ipynb file>`

---------

Signed-off-by: dongyang0122 <don.yang.mech@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: YunLiu <55491388+KumoLiu@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
3 participants