Har Joint Model Save
AROMA: A Deep Multi-Task Learning Based Simple and Complex Human Activity Recognition Method Using Wearable Sensors
Project README
AROMA: A Deep Multi-Task Learning Based Simple and Complex Human Activity Recognition Method Using Wearable Sensors
This is the implementation of our paper "AROMA: A Deep Multi-Task Learning Based Simple and Complex Human Activity Recognition Method Using Wearable Sensors". This work has been accepted by Ubicomp 2018.
The structure of the project
You can run main.py -h to get the args:
python main.py -h
Three args would be listed:
optional arguments:
-h, --help show this help message and exit
--test TEST select the test day. Max num is 6
--version VERSION model version
--gpu GPU assign task to selected gpu
For leave-one-out cross-validation, the "test" option should be assigned to test one day data in the dataset. Therefore, for example, you can run:
python main.py --test 0 --version har-model --gpu 0
Open Source Agenda is not affiliated with "Har Joint Model" Project. README Source: drewanye/har-joint-model
Stars
27
Open Issues
2
Last Commit
6 years ago
Repository
Open Source Agenda Badge
