tsai and pytorch-forecasting

These are complements rather than direct competitors: tsai provides a general-purpose deep learning library for time series tasks built on fastai, while pytorch-forecasting specializes in PyTorch-native forecasting models and can be used alongside tsai for domain-specific forecasting workflows.

tsai
80
Verified
pytorch-forecasting
70
Verified
Maintenance 13/25
Adoption 21/25
Maturity 25/25
Community 21/25
Maintenance 20/25
Adoption 10/25
Maturity 16/25
Community 24/25
Stars: 6,010
Forks: 717
Downloads: 14,647
Commits (30d): 0
Language: Jupyter Notebook
License: Apache-2.0
Stars: 4,827
Forks: 832
Downloads:
Commits (30d): 13
Language: Python
License: MIT
No risk flags
No Package No Dependents

About tsai

timeseriesAI/tsai

Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai

Provides sklearn-compatible preprocessing pipelines, walk-forward cross-validation for time series, and specialized architectures like PatchTST and attention-based RNNs optimized for sequential data. Leverages fastai's training loop abstractions and PyTorch 2.0 support while offering 128+ pre-downloaded benchmark datasets across classification, forecasting, and regression tasks. Supports univariate/multivariate sequences with reduced memory footprint through modular soft dependencies.

About pytorch-forecasting

sktime/pytorch-forecasting

Time series forecasting with PyTorch

Scores updated daily from GitHub, PyPI, and npm data. How scores work