Merantix Picasso Save

:art: A CNN visualizer

Project README

=============================== Picasso

.. image:: :target:

.. image:: :target:

.. image:: :target: :alt: Documentation Status

.. image::

A CNN model visualizer

See the Medium post_ for an introduction to Picasso.

If you use Picasso in your research, please cite our paper_:

.. code::

    Henderson, R. & Rothe, R., (2017). Picasso: A Modular Framework for Visualizing the Learning Process of Neural Network Image Classifiers. Journal of Open Research Software. 5(1), p.22. 


Picasso uses Python 3.5+ so use a virtual environment if necessary (e.g. virtualenv env --python=python3) and activate it!

#. Install with pip or from source.

With pip:

.. code::

    pip install picasso-viz

From the repository:

.. code::

    git clone [email protected]:merantix/picasso.git
    cd picasso
    pip install -e .

Note: you'll need the Tensorflow backend for Keras for these examples to work. Make sure your ~/.keras/keras.json file looks like:

.. code::

        "backend": "tensorflow",
        "image_dim_ordering": "tf",
        "floatx": "float32",
        "epsilon": 1e-07

#. Start the Flask server

.. code::

    export FLASK_APP=picasso
    flask run

Point your browser to and you should see the landing page! When you're done, Ctrl+C in the terminal to kill your Flask server.

Building the docs

The documentation is much more extensive than this README, and includes instructions on getting the Keras VGG16 and Tensorflow NMIST models working, as well as guides on building your own visualizations and using custom models. This assumes you've cloned the repository. First install the required packages:

.. code::

pip install -e .[docs]

Then build them:

.. code::

cd docs/
make html

Then you can open _build/html/index.html in your browser of choice.


#. Models generated on Keras using the Theano backend should in principle be supported. The only difference is the array ordering of convolutions. I haven't tried this yet though, so an extra config parameter may be needed.


  • Elias_ and Filippo_ for early code contributions and finding bugs and issues.
  • John_, Josh_, Rasmus_, and Stefan_ for their careful code review and feedback.
  • The favicon is a modification of this photograph_ of the painting "Les Demoiselles d'Avignon_", 1907 by Pablo Picasso. Photograph by Max Braun.
  • This package was created with Cookiecutter_ and the audreyr/cookiecutter-pypackage_ project template.

.. _Cookiecutter: .. _audreyr/cookiecutter-pypackage: .. _photograph: .. _Les Demoiselles d'Avignon: .. _Elias: .. _Filippo: .. _John: .. _Josh: .. _Rasmus: .. _Stefan: .. _Medium post: .. _please cite our paper:

Open Source Agenda is not affiliated with "Merantix Picasso" Project. README Source: merantix/picasso

Open Source Agenda Badge

Open Source Agenda Rating