Skip to content

getting-started.rst

Latest commit

 

History

History
74 lines (50 loc) · 2.02 KB

getting-started.rst

File metadata and controls

74 lines (50 loc) · 2.02 KB
Raw

Getting started

PyKale Tutorials are runnable scripts. You read the narrated version, then run the full experiment when you want the real numbers. Here is the shortest path in.

Install PyKale

pip install pykale

Datasets are never bundled — each tutorial downloads what it needs, or points at pykale/data.

Run your first tutorial

The recommended starting point is :doc:`domain adaptation on digit images </_gallery/others/image_classification/digit_domain_adaptation/plot_digit_domain_adaptation>`. It trains a classifier on MNIST and adapts it to USPS without target labels — PyKale's core idea in a few minutes on CPU.

cd others/image_classification/digit_domain_adaptation
pip install -r requirements.txt
python main.py --cfg configs/MN2UP-DANN.yaml --devices 1

Explore a domain

Tutorials are filed by the domain that owns them:

.. grid:: 1 2 3 3
   :gutter: 2

   .. grid-item-card:: Protein
      :link: _pages/protein
      :link-type: doc

      Drug-target binding and polypharmacy side effects.

   .. grid-item-card:: Cancer
      :link: _pages/cancer
      :link-type: doc

      Multiomics integration for cancer classification.

   .. grid-item-card:: Cardiac
      :link: _pages/cardiac
      :link-type: doc

      Cardiac imaging and uncertainty estimation.

   .. grid-item-card:: Others
      :link: _pages/others
      :link-type: doc

      Method demonstrations: recognition, domain adaptation, few-shot learning.

   .. grid-item-card:: Materials
      :link: _pages/materials
      :link-type: doc

      Reserved — tutorials in development.

Adapt an example to your own data

Every tutorial ships its complete main.py and config. Fork the folder, point DATASET.ROOT (or the equivalent config field) at your data, and adjust the model. See :doc:`CONTRIBUTING` for conventions, and :doc:`all-tutorials` to browse everything.