This crash course introduces TINTOlib, a Python library to convert tabular data into synthetic images. The course is hands-on and includes bilingual videos and notebooks to apply deep learning models like CNNs, Vision Transformers (ViTs), and hybrid architectures on tabular datasets.
- 📚 Theory: 3 videos + 1 presentation
- 🧪 Practice: 5 videos + 5 Jupyter notebooks
All videos are available in English and Spanish.
Todos los vídeos están disponibles en inglés y español.
Conceptual overview of TINTOlib and Hybrid Neural Networks (HyNNs).
| Topic | English | Español |
|---|---|---|
| 1. What is TINTOlib? | ▶ Watch | ▶ Ver |
| 1. Introduction to TINTOlib | ▶ Watch | ▶ Ver |
| 2. Tabular to Image Conversion | ▶ Watch | ▶ Ver |
| 3. Hybrid Neural Networks (HyNNs) | ▶ Watch | ▶ Ver |
Each hands-on video corresponds to a Jupyter notebook.
| Practice | English Video | Spanish Video | Notebook |
|---|---|---|---|
| 1. CNN for Tabular Images | ▶ Watch | ▶ Ver | 📓 Regression_CNN.ipynb |
| 2. CNN + MLP Hybrid | ▶ Watch | ▶ Ver | 📓 Binary_CNN+MLP.ipynb |
| 3. Vision Transformer (ViT) | ▶ Watch | ▶ Ver | 📓 Regression_ViT.ipynb |
| 4. ViT + MLP Hybrid | ▶ Watch | ▶ Ver | 📓 Binary_hybrid_vision_transformer.ipynb |
| 5. Summary & Insights | ▶ Watch | ▶ Ver | 📓 Regression_CNN+MLP-Fusion.ipynb |
- Watch the theory videos first.
- Then go through each practice video + notebook.
- Run the notebooks locally or via Google Colab.
- Required datasets in
Datasetsfolder.
To install the required packages:
pip install tensorflow pandas matplotlib scikit-learn tintolib- 📘 Docs: TINTOlib ReadTheDocs
- 📦 PyPI: TINTOlib on PyPI
- 💻 GitHub: TINTOlib Documentation
- Manuel Castillo-Cara – manuelcastillo@dia.uned.es
- Raúl García-Castro – r.garcia@upm.es
- Jiayun Liu – jiayun.liu@upm.es
