In order to get things running:
- Clone the repository
git clone https://github.com/mutschcr/tool-tracking.git
cd tool-tracking
- Then you need to download the measurement data from an external host:
wget https://owncloud.fraunhofer.de/index.php/s/MQUpf2vhIghAtke/download -O tool-tracking-data.zip
unzip tool-tracking-data.zip && rm tool-tracking-data.zip
- Setup a virtual python environment (e.g. with conda)
conda create --name tool-tracking_env python=3.7
conda activate tool-tracking_env
pip install -r requirements.txt
- Mark the data-tools and fhg-utils folders as Content roots or add them to your PYTHONPATH
- Get introduced on how to load and work with the data
Start Jupyter and run the both notebook How-to-load-the-data.ipynb and plot_window_sizes.ipynb with:
jupyter notebook
Changelog:
- 2020-08-14: Update dataset with enhanced rivetter labels
- 2020-08-12: Update dataset with twice the amount of labeled data; enhanced labels.
- 2020-07-29: Update data loader and notebooks
Known issues:
- 2020-08-12: Enforcing window lenghts when segmenting rivetter data lets two very short windows (label -1) slip through. These cause problems and need to be filtered out: 'filter_labels(..)'
License:
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
