API Reference

Complete API documentation for SToG.

• base
• selectors
• models
• datasets
• benchmark
• main

Overview

SToG consists of several modules:

• base.py - Base class for feature selectors

• selectors.py - Feature selection methods (STG, STE, Gumbel, etc.)

• trainer.py - Training utilities

• models.py - Neural network models

• datasets.py - Dataset loading utilities

• benchmark.py - Benchmarking framework

• main.py - Main execution script