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:
CLAlgorithmfor CL algorithms;CLDatasetfor CL datasets;CLBackbonefor 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.
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 you’re interested in contributing to this package with your custom modules, feel free to submit a pull request!