Getting Started

Learn how to use ELEKTRONN.


ELEKTRONN is a Python 2.7 package that can be installed with conda or pip.

Getting Started

How do you use ELEKTRONN for your data analysis task? Read our basic recipe or try out one of the examples.

For an application on 3D image data, head to the Documentation.


ELEKTRONN’s full documentation, including many tips for training, can be found here:

book Documentation

Use Cases

ELEKTRONN can be used for...

  • image segmentation
  • object recognition
  • prediction of income
  • ... much more

Installation extension

Get Started with ELEKTRONN trending_up

For people new to Neural Networks and CNNs we recommend reading the practical introduction in our documentation.

A more theoretical introduction, including formulae and references can be found here.

Your First Training with MNIST school

MNIST is a famous benchmark data set for the task of handwritten digit recognition. To try out the example training:

elektronn-train MNIST_CNN_warp_config.py [--gpu=0]

The first argument to the script is the path to a config file which is within the package’s examples directory. You can alternatively copy the file, edit it and use your modified version. If you have an NVIDIA GPU add the option --gpu=0 which will make the execution significantly faster (make sure you have configured theano when installing ELEKTRONN). Plots of the training progress are saved to ~/CNN_Training/2D/MNIST_example_warp (the destination can be changed in the config file).

This is an example of "img-scalar" training: the input data is image like but the output is a scalar (namely the class prediction) describing the whole image. The main focus of ELEKTRONN lies however on "img-img" traing which is described in the next section.

Basic Recipe for CNN Training with Images format_list_numbered