# lucidrains/tab-transformer-pytorch

Implementation of TabTransformer, attention network for tabular data, in Pytorch

Repository: https://github.com/lucidrains/tab-transformer-pytorch
Canonical: https://ross.abutalabs.com/products/tab-transformer-pytorch
Language: Python
License: MIT
License Family: permissive
Topics: artificial-intelligence, deep-learning, transformer, attention-mechanism, tabular-data
Last push: 2026-01-08T15:05:23+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 61, release rhythm 65, longevity 100
- inputs: {"age_days": 2088, "days_push": 237, "days_rel": 237, "gap_med": 2.5, "n_releases_24m": 9}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1091, forks 131 (observed 2026-08-28T04:03:33.167693+00:00)

## What it is
A PyTorch implementation of the TabTransformer architecture, an attention-based neural network for tabular data, also including the FT Transformer variant for comparison. It is distributed as a pip-installable library for researchers and practitioners applying deep learning to structured data.

## Use cases
- train a transformer model on tabular data with categorical and continuous features
- compare attention-based models against gradient boosted decision trees on structured datasets
- implement TabTransformer from the paper in PyTorch
- use FT Transformer for embedding continuous numerical features
- predict outcomes like shipping cost from mixed tabular inputs

## When to choose
- you want a ready-made PyTorch implementation of TabTransformer or FT Transformer
- your dataset has many categorical features and you want attention-based modeling
- you are benchmarking deep learning against GBDT on tabular data

## When to avoid
- you need a battle-tested production AutoML solution rather than a research implementation
- your tabular data is small and gradient boosted trees would suffice
- you do not use PyTorch

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, artificial-intelligence
- platform: python
- tags: transformer, tabular-data, attention-mechanism, pytorch, ft-transformer

## Member repositories
- lucidrains/tab-transformer-pytorch (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:33.167693+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 2026-08-30T06:49:09.412143+00:00, confidence not recorded.
  - readme: https://github.com/lucidrains/tab-transformer-pytorch (fetched 2026-08-28T04:03:33.167693+00:00, sha df7ab34491f7)
  - registry_pypi: https://pypi.org/pypi/tab-transformer-pytorch/json (fetched 2026-08-29T12:51:25.690413+00:00, sha 8f807bd69f14)
- Data as of 2026-08-30T08:39:29.467469+00:00.