TorchDyn reference documentation

(New release 0.2.0 is finally out!)

End-to-end Pytorch suite for continuous neural architectures featuring several models, training methods and visualization tools for research, industry and amateurs.

git clone

cd torchdyn

python install

Please visit our GitHub page.


  • This library is developed and maintained by Michael Poli & Stefano Massaroli.
  • The work has been supported by Prof. Jinkyoo Park (KAIST), Prof. Atsushi Yamashita (The University of Tokyo) and Prof. Hajime Asama (The University of Tokyo).

API documentation


Indices and tables