pytorch-tabular/pytorch_tabular

Health v2 · maintenance only

Adoption not part of the score

1677 stars · 177 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

PyTorch Tabular is a Python library providing a unified, high-level interface for deep learning models on tabular data, built on PyTorch and PyTorch Lightning. It bundles standard tabular architectures with automatic GPU/CPU scaling and logging.

Use cases

• train deep learning models on tabular data
• apply neural networks to structured CSV datasets
• use TabNet or FT-Transformer style architectures
• scale tabular model training on GPU with PyTorch Lightning
• replace gradient boosting with deep learning for classification or regression

When to choose

• you want a high-level API for deep learning on tabular data without writing boilerplate
• you want built-in access to multiple tabular architectures under one interface
• you already use PyTorch Lightning and want automatic logging and GPU scaling

When to avoid

• you need a quick baseline on small tabular data, where gradient boosting (XGBoost/LightGBM) is often stronger
• you need custom architectures outside the supported set
• you work with images, text, or audio rather than structured tables

Facets

library · maturity active

machine-learning deep-learning machine-learning data-science python tabular-data pytorch-lightning neural-networks high-level-api

Member repositories

For agents

markdown · JSON · MCP: product_card(name="pytorch-tabular/pytorch_tabular")