Tutorials

This folder collects hands‑on, runnable examples that demonstrate how to use iMML for common multi‑modal learning workflows, including exploring datasets, simulating missing modalities, classifying and clustering with incomplete data, among others. Each script is self‑contained and designed to be easy to adapt to your own data. You can find the tutorials in:

• Online documentation: https://imml.readthedocs.io/stable/auto_tutorials/index.html. The online gallery renders these scripts as rich, formatted pages with figures.

• In-repo: https://github.com/ocbe-uio/imml/tree/main/tutorials. As Python scripts, run any file directly. Most scripts will print intermediate results and pop up figures.

Questions or feedback?

• Open an issue: https://github.com/ocbe-uio/imml/issues

• Contributions are welcome: https://imml.readthedocs.io/stable/development/contributing.html.

Statistics and interaction structure of a multi-modal dataset

Statistics and interaction structure of a multi-modal dataset

Modality-wise missing data simulation (Amputation)

Modality-wise missing data simulation (Amputation)

Clustering a multi-modal dataset

Clustering a multi-modal dataset

Retrieval on a vision–language dataset (flickr30k)

Retrieval on a vision–language dataset (flickr30k)

Impute modality- and feature-wise incomplete multi-modal data

Impute modality- and feature-wise incomplete multi-modal data

Classify an incomplete vision–language dataset (Oxford‑IIIT Pets) with deep learning

Classify an incomplete vision–language dataset (Oxford‑IIIT Pets) with deep learning

Dimensionality reduction: Feature extraction and feature selection

Dimensionality reduction: Feature extraction and feature selection