https://github.com/kitware/trame-mnist

Simple trame demonstrator using the MNIST dataset with XAITK for saliency analysis
https://github.com/kitware/trame-mnist

trame trame-app

Last synced: about 2 months ago
JSON representation

Simple trame demonstrator using the MNIST dataset with XAITK for saliency analysis

• Host: GitHub
• URL: https://github.com/kitware/trame-mnist
• Owner: Kitware
• License: bsd-3-clause
• Created: 2022-02-12T00:19:08.000Z (almost 3 years ago)
• Default Branch: master
• Last Pushed: 2023-07-12T23:30:43.000Z (over 1 year ago)
• Last Synced: 2024-10-31T19:57:37.077Z (2 months ago)
• Topics: trame, trame-app
• Language: Python
• Homepage:
• Size: 932 KB
• Stars: 1
• Watchers: 4
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.rst
  • License: LICENSE

Awesome Lists containing this project

README

        
================

Trame MNIST

================

Example application using **trame** for exploring MNIST dataset in the context of AI training and XAI thanks to **XAITK**.

* Free software: BSD License

* `XAITK Saliency with MNIST `_

* `XAI Discovery Platform | MNIST Sample Data `_

Installing

----------

For the Python layer it is recommended to use `conda `_ to properly install the various ML packages.

conda setup on macOS

^^^^^^^^^^^^^^^^^^^^^

Go to `conda documentation `_ for your OS

.. code-block:: console

    brew install miniforge

    conda init zsh

venv setup for AI

^^^^^^^^^^^^^^^^^^

.. code-block:: console

    # Needed in order to get py3.9 with lzma

    # PYTHON_CONFIGURE_OPTS="--enable-framework" pyenv install 3.9.9

    conda create --name trame-mnist python=3.9

    conda activate trame-mnist

    # For development when inside repo

    pip install -e .

    # For testing (no need to clone repo)

    pip install trame-mnist

Running the application

------------------------

.. code-block:: console

    conda activate trame-mnist

    trame-mnist

If **cuda** is available, the application will use your GPU, but you can also force the usage of your cpu by adding to your command line the following argument: **--cpu**

|image_1| |image_2| |image_3|

.. |image_1| image:: https://github.com/Kitware/trame-mnist/raw/master/gallery/trame-mnist-02.jpg

  :width: 32%

.. |image_2| image:: https://github.com/Kitware/trame-mnist/raw/master/gallery/trame-mnist-03.jpg

  :width: 32%

.. |image_3| image:: https://github.com/Kitware/trame-mnist/raw/master/gallery/trame-mnist-04.jpg

  :width: 32%

License

--------

**trame-mnist** is distributed under the OSI-approved BSD 3-clause License.