Intent to configure a modulatory method to build and train variational autoencoders based on custom architectures and losses.
Continuation of work from Antoine Marot on "Interpreting atypical conditions in systems with deep conditional Autoencoders: the case of electrical consumption" submitted at ECML-PKDD 2019 https://github.com/marota/Autoencoder_Embedding_Expert_Caracteristion_
Main features:
- Choices of architectures for encoder or decoder blocks
- Various losses combination available
- Metrics of disentanglement
- Callback on the analysis of leanrt information in hidden layers of the model
Copyright 2020 RTE(France)
RTE: http://www.rte-france.com
This Source Code is subject to the terms of the GNU Lesser General Public License v3.0. If a copy of the LGPL-v3 was not distributed with this file, You can obtain one at https://www.gnu.org/licenses/lgpl-3.0.fr.html.