A Python library that transforms tidy tabular data into synthetic images so you can use computer vision models (CNNs, Vision Transformers) on non-image data.

Which methods are supported?

TINTO, IGTD, REFINED, BarGraph, DistanceMatrix, Combination, SuperTML, FeatureWrap, BIE — each with specific hyperparameters.

Why convert tables into images?

It lets you leverage the advances of modern vision models on tabular problems, sometimes improving accuracy and generalization.

TINTOlib - Python library for transforming tabular data into synthetic images

Name: TINTOlib
Author: Manuel Castillo-Cara

TINTOlib — Tabular Data → Synthetic Images

Open-source Python library to convert tidy tabular data into synthetic images and train CNNs, ViTs, and hybrid architectures.

⭐ GitHub 📘 Documentation

🎉 New Free Course on Udemy! 🎉

We’ve just launched a 100% free course on Udemy about using TINTOlib and developing Hybrid Neural Networks.

Learn how to turn tabular data into synthetic images and apply CNNs, ViTs, and hybrid architectures.

👉 Access the Course on Udemy

🧠 Overview

TINTOlib transforms tidy tabular data into synthetic images, enabling deep learning with CNNs and Vision Transformers (ViTs) for classification and regression. It bridges structured data and image-based learning, and supports hybrid models combining both worlds.

📦 pip install TINTOlib 🖥️ Linux / Windows / macOS 🐍 Python 3.7+ 🧪 CSV / Pandas DataFrame

📺 VideoTutorial Course (English/Spanish)

Prefer not to register on Udemy or looking for the English version? Follow the full bilingual course on GitHub, with videos and practical notebooks covering CNNs, ViTs, and hybrid architectures.

🔧 Features

Input formats: CSV or Pandas DataFrame.
Designed for tidy data (target column at the end).
Output: grayscale images produced by reduction/transformation methods.
Compatible with Linux, Windows, macOS.
Requires Python 3.7+.

🧪 Supported Models

Supported image transformation models include:

Models	Class	Hyperparameters
TINTO	`TINTO()`	`problem` `normalize` `verbose` `pixels` `algorithm` `blur` `submatrix` `amplification` `distance` `steps` `option` `times` `train_m` `zoom` `random_seed`
IGTD	`IGTD()`	`problem` `normalize` `verbose` `scale` `fea_dist_method` `image_dist_method` `error` `max_step` `val_step` `switch_t` `min_gain` `zoom` `random_seed`
REFINED	`REFINED()`	`problem` `normalize` `verbose` `hcIterations` `n_processors` `zoom` `random_seed`
BarGraph	`BarGraph()`	`problem` `normalize` `verbose` `pixel_width` `gap` `zoom`
DistanceMatrix	`DistanceMatrix()`	`problem` `normalize` `verbose` `zoom`
Combination	`Combination()`	`problem` `normalize` `verbose` `zoom`
SuperTML	`SuperTML()`	`problem` `normalize` `verbose` `pixels` `feature_importance` `font_size` `random_seed`
FeatureWrap	`FeatureWrap()`	`problem` `normalize` `verbose` `size` `bins` `zoom`
BIE	`BIE()`	`problem` `normalize` `verbose` `precision` `zoom`

🚀 Getting Started

Install via pip:

pip install TINTOlib

Use requirements.txt for the base environment.
Use requirements-example.txt for full deep learning workflows.

🧩 Example

from TINTOlib.tinto import TINTO

# Create and run TINTO on your tidy DataFrame (target column last)
model = TINTO(problem="supervised", blur=True, pixels=64, random_seed=42)
model.fit_transform(data, folder="outputs")

📚 Additional Resources

📘 Documentation 🚀 GitHub 📹 Crash Course

🧠 Research and Software Publications

📄 Research Articles

Manuel Castillo-Cara et al. MIMO-Based Indoor Localisation with Hybrid Neural Networks. IEEE JSTSP. DOI: 10.1109/JSTSP.2025.3555067
Reewos Talla-Chumpitaz, Manuel Castillo-Cara et al. Blurring Image Techniques for Bluetooth-based Indoor Localisation. Information Fusion. DOI: 10.1016/j.inffus.2022.10.011

💾 Software Articles

Manuel Castillo-Cara et al. TINTO: Converting Tidy Data into Images. SoftwareX. DOI: 10.1016/j.softx.2023.101391

Ph.D. Manuel Castillo-Cara