# 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

Repository: https://github.com/jrzaurin/pytorch-widedeep
Canonical: https://ross.abutalabs.com/products/pytorch-widedeep
Language: Python
License: Apache-2.0
License Family: permissive
Topics: pytorch, tabular-data, text, images, multimodal-deep-learning, pytorch-tabular-data, pytorch-nlp, pytorch-cv, pytorch-transformers, deep-learning, model-hub, python
Last push: 2026-04-30T14:04:48+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 80, release rhythm 17, longevity 100
- inputs: {"age_days": 3238, "days_push": 125, "days_rel": 340, "gap_med": 183.5, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1416, forks 197 (observed 2026-08-28T04:04:39.907709+00:00)

## What it is
A PyTorch library for multimodal deep learning that combines tabular data with text and images using Wide and Deep model architectures. It provides flexible components for building deep learning models on mixed-modality datasets.

## Use cases
- train deep learning models on tabular data with pytorch
- combine tabular features with text and images in one model
- build wide and deep recommendation models
- use transformers for text columns alongside tabular data
- benchmark tabular deep learning against lightgbm
- multimodal classification with mixed data types

## When to choose
- your dataset mixes tabular, text, and image inputs
- you want Wide and Deep architectures in PyTorch
- you need flexible deep tabular modeling with pretrained text/image encoders

## When to avoid
- you only need gradient-boosted trees like LightGBM/XGBoost
- you need a general-purpose deep learning framework rather than tabular-focused tooling
- you work outside Python/PyTorch

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, nlp, image-processing, data-science
- domain: machine-learning, deep-learning, data-science, computer-vision
- platform: python, cross-platform
- tags: pytorch, tabular-data, wide-and-deep, multimodal, transformers, model-hub, natural-language-processing

## Member repositories
- jrzaurin/pytorch-widedeep (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:39.907709+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:38:05.855666+00:00, confidence not recorded.
  - readme: https://github.com/jrzaurin/pytorch-widedeep (fetched 2026-08-28T04:04:39.907709+00:00, sha 3269ab0a9a72)
  - registry_pypi: https://pypi.org/pypi/pytorch-widedeep/json (fetched 2026-08-29T11:50:47.113316+00:00, sha c07701d4572d)
- Data as of 2026-08-30T08:39:29.467469+00:00.