nirtiac / vulcan

A high level deep learning framework for quickly prototyping networks with added tools in data visualisation, model interpretability and performance metrics

Vulcan

Deep Learning Framework

Vulcan is a high-level framework built on top of Theano and Lasagne using added functionality from Scikit-learn to provide all of the tools needed for:

• visualizing high-dimensional data
• data preprocessing
• creating modular neural networks
• model evaluation

This framework was designed with both modularity and ease of use in mind so prototyping architectures is very simple and using them across many machines is even easier. Moreover, it comes with state of the art activations, ensemble methods and network interpretability techniques that all take part in finding the right model for a set of data.

For a more detailed runthrough on how to use the tools, please look at the wiki

Installation

It can be installed using PyPI:

<sudo> pip install vulcanai