User Guide

This guide follows the typical usage flow: reading a database, wrapping it in a dataset, selecting and configuring a model, training with the library trainer, and evaluating with official metrics.

• Reading databases
• Preprocessing and augmentation
• Models and configurations
• Training
• Evaluation and metrics

Every code block in this guide is either executed as part of the test suite or taken from the examples (the benchmarks/ directory), which double as continuously-tested reference usage.