Shawnโ€™s Blog
  • ๐Ÿ—‚๏ธ Collections
    • ๐Ÿ–ฅ๏ธ Slides Gallery
    • ๐Ÿ“š Library (Reading Notes)
    • ๐Ÿง‘โ€๐Ÿณ๏ธ Cooking Ideas
    • ๐Ÿฑ Cookbook
    • ๐Ÿ’ฌ Language Learning
    • ๐ŸŽผ Songbook
  • โš™๏ธ Projects
    • โš› Continual Learning Arena
  • ๐Ÿ“„ Papers
    • AdaHAT
  • ๐ŸŽ“ CV
    • CV (English)
    • CV (Mandarin)
  • About
  1. CLArena
  2. Implement Your CL Modules
  • CLArena
    • Welcome Page
    • Get Started
    • Configure Your Experiment
      • Experiment Index Config
      • Configure CL Algorithm
      • Configure CL Dataset
      • Configure Backbone Network
      • Configure Optimizer
      • Configure Learning Rate Scheduler
      • Configure Trainer
      • Configure Lightning Loggers
      • Configure Callbacks
      • Other Configs
    • Implement Your CL Modules
    • API Reference

On this page

  • Implement CL Modules Outside the Package
  • Contributing to CLArena
  1. CLArena
  2. Implement Your CL Modules

Implement Your CL Modules

This section will guide you to implement your own continual learning modules within this package framework.

This package provides bases to implement continual learning modules, including:

  • CLAlgorithm for CL algorithms;
  • CLDataset for CL datasets;
  • CLBackbone for CL backbone networks.

Other parts of the experiment, such as optimizer, trainer, callbacks, are also customisable in the implementation level. I will talk about the logic and practices to implement them in later chapters.

Implement CL Modules Outside the Package

You can implement your custom CL modules anywhere outside the package source code, and specify the _target_ field in your configs for experiment.

Warning

To properly locate your implement module for the config, you need to add the path of your module to the environment variable PYTHONPATH. This should be done in the beginning of every terminal sessions. Either do it once by:

export PYTHONPATH=<path-to-your-module>

or set it every time the commands are executed:

PYTHONPATH=<path-to-your-module> clrun ...

Contributing to CLArena

If youโ€™re interested in contributing to this package with your custom modules, feel free to submit a pull request!

Source Code GitHub Pull Request

Back to top
Other Configs
API Reference
 
 

ยฉ๏ธ 2025 Pengxiang Wang. All rights reserved.