pytorch tabular provides a unified framework for deep learning models on tabular data.
Open source
24 alternativesPyTorch Frame
PyTorch Frame provides a library for applying deep learning models to tabular data.
About PyTorch Frame
PyTorch Frame is an open-source Python library that extends PyTorch for deep learning on heterogeneous tabular data. It handles numerical, categorical, multicategorical, timestamp, text, image and embedding columns, and converts pandas DataFrames into TensorFrame objects for training.
It uses a modular structure of FeatureEncoder, TableConv and Decoder to model column interactions and produce row-level predictions. It includes deep tabular models alongside XGBoost, CatBoost and LightGBM with hyper-parameter tuning, and provides mini-batch loaders, benchmark datasets and support for custom datasets. It can combine with other PyTorch libraries and external text embedding models.
Key features
- Supports numerical, categorical, multicategorical, timestamp, text, image and embedding columns
- Converts pandas DataFrames into TensorFrame for PyTorch training
- Modular FeatureEncoder, TableConv and Decoder model structure
- Includes deep tabular models and XGBoost, CatBoost, LightGBM with tuning
- Provides ready-to-use benchmark datasets and custom dataset support
- Integrates with other PyTorch libraries and external text embedding models
Best for: Existing PyTorch users building neural network models on heterogeneous tabular data.
Good for
- Handles diverse column types within one PyTorch-based workflow
- Includes benchmark datasets and comparison of deep models with GBDTs
- Supports end-to-end training with other PyTorch libraries
PyTorch Frame at a glance
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
PyTorch Frame alternatives
Tools and sites you could use instead, ranked by how closely they match.
This TabGAN repository reviews research on applying GANs to generate tabular data.
Open source
24 alternatives
Captum explains model behavior and supports interpretability analysis for PyTorch systems.
Open source
24 alternatives
Disco’s discovery engine finds statistically validated patterns in tabular data, including feature interactions and subgroup effects.
Open source
24 alternatives
A Python package to assess and improve fairness of machine learning models.
Open source
24 alternatives
This repository implements YOLOv3 variants in PyTorch for real time object detection, training, validation, inference, and export.
Open source
24 alternativesPopular in AI Data & Analytics
Well-known listings from the same topic.
Dotgetdot.aiForvioforvio.comFluidAI Medicalfluidai.mdApache Zeppelinzeppelin.apache.orgSola Securitysola.securityQuadraticquadratichq.com
PyTorch Frame FAQ
What column types can PyTorch Frame process?
Numerical, categorical, multicategorical, text_embedded, text_tokenized, timestamp, image_embedded, and embedding.
Can text columns use external embedding models?
Yes, text data can be encoded with a downloaded model or embedding API endpoint, with examples for OpenAI, Cohere, Hugging Face, and Voyage AI.
Does it integrate with other PyTorch libraries?
Yes, it can train end-to-end with downstream PyTorch models, including PyG for learning over relational databases.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.