jrzaurin/pytorch-widedeep

A flexible package for multimodal-deep-learning to combine tabular data with text and images using Wide and Deep models in Pytorch

59
/ 100
Established

This project helps data scientists and machine learning engineers build more accurate predictive models by combining different types of data. It takes in structured tabular data (like spreadsheets), unstructured text (like product descriptions), and images (like product photos) to produce a single, powerful prediction. This is ideal for tasks requiring a holistic view, like predicting customer behavior or classifying complex items.

1,404 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to make predictions or classifications using datasets that include a mix of tabular information, text, and images.

Not ideal if your data consists only of one type, such as purely tabular data or only text, as simpler tools might suffice.

predictive-modeling customer-analytics image-classification text-analytics multimodal-data
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 22 / 25

How are scores calculated?

Stars

1,404

Forks

198

Language

Python

License

Apache-2.0

Last pushed

Sep 27, 2025

Commits (30d)

0

Dependencies

18

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jrzaurin/pytorch-widedeep"

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