🗺️ Overview

The framework adopts a modular design overall, which is reflected in two key aspects:

• 🛠️ Functionally: The framework independently incorporates dedicated modules for supervised training, out-of-distribution detection, novel class discovery, and incremental learning.
• ⚙️ Procedurally：The framework divides its operational workflow into distinct stages, including data processing, model construction, training and evaluation, and visualization.

From an implementation perspective, the framework is built upon foundational deep learning, data processing, and visualization libraries such as PyTorch, NumPy, Matplotlib, and Pandas, leveraging their extensive built-in functionalities.

This comprehensive framework provides researchers with a robust foundation for tackling open world learning challenges, from initial model training through continuous adaptation to novel scenarios.