srvcodes / continual-learning-for-har Goto Github PK

This project forked from chameleontk/continual-learning-for-har

A continual model for human activity recognition (called HAR-GAN). It is based on a technique called `generative replay` which two models (classifier and generator) are trainined in the same time to keep learning a new task but also retrain previously learned knwoledge.

License: MIT License