onesixsolutions/torchcast
onesixsolutions/torchcast has 58 GitHub stars and 4 forks. GitHot measured 0 stars in 24 hours and 0 in 7 days. Last checked 2026-11-21 23:26 UTC. Last push 2026-11-21.
Progression mesurée des étoiles
- in 24h
- 0
- in 7 days
- 0
- in 15 days
- Historique en cours
- in 1 month
- Historique en cours
Variations nettes sur des périodes qui se chevauchent, pas des totaux quotidiens. Les mesures absentes restent vides. Les étoiles indiquent l’intérêt, pas la qualité.
À propos
Forecasting with PyTorch
Apprentissage automatiqueREADME.md
Originaltorchcast
torchcast is a Python package for forecasting built on top of PyTorch <http://pytorch.org>_. Its benefits include:
- An API designed around training and forecasting with batches of time-series, rather than training separate models for one time-series at a time.
- Robust support for multivariate time-series, where multiple correlated measures are being forecasted.
- Forecasting models that are hybrids: they are classic state-space models with the twist that every part is differentiable and can take advantage of PyTorch's flexibility. For
example <https://docs.strong.io/torchcast/examples/electricity.html#Training-our-Hybrid-Forecasting-Model>_, we can use arbitrary PyTorchtorch.nn.Modulesto learn seasonal variations across multiple groups, embedding complex seasonality into lower-dimensional space.
This repository is the work of Strong <https://www.strong.io/>_.
.. image:: docs/examples_air_quality_6_2.png
Getting Started
torchcast can be installed with pip:
.. code-block:: bash
pip install git+https://github.com/onesixsolutions/torchcast.git#egg=torchcast
torchcast requires Python >= 3.9 and PyTorch >= 1.12.
See the Quick Start <https://docs.strong.io/torchcast/quick_start.html>_ for a simple example that will get you up to speed, or delve into the examples <https://docs.strong.io/torchcast/examples/examples.html>_ or the API <https://docs.strong.io/torchcast/api/api.html>_.
Explorer des projets similaires
Chargement…