Deep Generative Cross-modal On-body Accelerometer Data Synthesis from Videos

Requirements:

Python 3 required (for python build)
Install PyTorch and dependencies from http://pytorch.org
Install required modules (numpy scipy pandas sklearn matplotlib statistics pyyaml).

pip3 install -r requirement.txt

root
├── code
│   ├── baseline
│   ├── checkpoints
│   ├── dataloader
│   └── ...
│
└── data
    ├── ECM
    ├── LabEating
    └── MD2K

git clone https://github.com/HAbitsLab/SensorSynthesis.git
cd SensorSynthesis

Install PyTorch and 0.4+ and other dependencies (e.g., torchvision, visdom and dominate).
- For pip users, please type the command pip install -r requirements.txt.
- For Conda users, we provide a installation script ./scripts/conda_deps.sh. Alternatively, you can create a new Conda environment using conda env create -f environment.yml.
- For Docker users, we provide the pre-built Docker image and Dockerfile. Please refer to our Docker page.

In folder preprocess:

Stanford ECM dataset: python3 run_pwcnet_ecm.py

MD2K Sense2StopSync dataset: use convert2mp4.sh, then python3 run_pwcnet_MD2K.py

I3D Feature Extraction is used:

In folder utils/feature_extraction, run python3 run_i3d_ecm_gpu.py and python3 run_i3d_MD2K_gpu.py.

@inproceedings{dummmy,
}