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.

语言：Jupyter Notebook · GitHub 星标：18 · Fork：6

在 GitHub 上查看原仓库