In this post we will look at some of the top open source deep learning for time series forecasting frameworks. In particular we will look at PyTorch time series forecasting frameworks.
- Gluon This framework by Amazon remains one of the top DL based time series forecasting frameworks on GitHub. However, there are some down sides including lock-in to MXNet (a rather obscure architecture). The repository also doesn’t seem to be quick at adding new research.
- Flow Forecast: This is an upcoming PyTorch based deep learning for time series forecasting framework. The repository features a lot of recent models out of research conferences along with an easy to use deployment API. The repository is one of the few repositories to have new research models, coverage tests, and interpretability metrics.
- sktime dl This is another time series forecasting repository. Unfortunately it looks like particularly recent activity has diminished on it. On the main page it looks
- PyTorch-TS Another framework, written in PyTorch, this repository focuses more on probabilistic models. The repository isn’t that active (last commit was in November). However, the group behind it appears active in the research community and adds newer models to it.
These seem to be the major time series forecasting framework out there at moment. Interestingly at present there doesn’t seem to be a time series forecasting built exclusively in Tensorflow/Keras. However there are several tutorials out there.