pyg-team/pytorch-frame

Tabular Deep Learning Library for PyTorch

71
/ 100
Verified

This project helps data scientists and machine learning engineers build and train advanced deep learning models using diverse tabular data. It takes in raw tabular data, which can include various column types like numbers, text, images, or timestamps, and outputs highly predictive models. It's designed for practitioners who want to leverage deep learning for complex prediction tasks on structured datasets.

773 stars. Used by 1 other package. Actively maintained with 8 commits in the last 30 days. Available on PyPI.

Use this if you need to build deep learning models on tabular data that combines many different data types, including text and images, and want to experiment with state-of-the-art architectures.

Not ideal if your primary need is for traditional tree-based models like GBDT, or if you're not comfortable working with deep learning frameworks and Python.

predictive-modeling data-science machine-learning-engineering deep-learning heterogeneous-data
Maintenance 17 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 18 / 25

How are scores calculated?

Stars

773

Forks

71

Language

Python

License

MIT

Last pushed

Mar 04, 2026

Commits (30d)

8

Dependencies

6

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pyg-team/pytorch-frame"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.