orcanet 0.12

Runs Neural Networks for usage in the KM3NeT project

OrcaNet is a deep learning framework based on Keras in order to simplify the training process of neural networks for astroparticle physics. It incorporates automated logging, plotting and validating during the training, as well as saving and continuing the training process. Additionally, it features easy management of multiple neural network inputs and the use of training data which is split over multiple files.

In this sense, it tackles many challenges that are usually found in astroparticle physics, like huge datasets.

OrcaNet is a part of the Deep Learning efforts for the neutrino telescope KM3NeT. Find more information about KM3NeT on http://www.km3net.org

OrcaNet is currently being developed at the official KM3NeT gitlab (https://git.km3net.de/ml/OrcaNet).

However, there’s also a github mirror that can be found at https://github.com/ViaFerrata/OrcaNet.

OrcaNet can be installed via pip by running:

pip install orcanet

Tensorflow 1.X

Orcanet per default runs on tensorflow 2, but there is also no longer supperted tf 1 branch, which makes use of the deprecated stand-alone keras package. For the tf 1 version, orcanet will install tensorflow (the cpu version). For training with graphics cards, tensorflow-gpu is required, which needs to be installed manually via:

pip install tensorflow-gpu