- Ability to detect a good or bad posture
- Reminders for taking breaks
- Session statistics at the end of each session
- Download the GitHub repository and extract the folder.
- Make sure you have Conda installed.
cd into whereever you cloned the repository and once you're inside Hackathon-Project cd into app.- Once inside
app, run the following command, conda env create -f environment.yml.
- Then run
conda activate app since this is the environment with all the packages.
- Now, inside the same
app folder run streamlit run Home.py.
- This should then boot up the app on localhost and you should be able to access it.
- You will find that the
data folder is empty and this is just because we wanted to maintain privacy of the several images that we had taken of oursevles during the course of the project.
- From our testing the project only builds on Windows and not Mac due to several Windows specific packages.
- If the project isn't building then it may be possible to follow the steps below to try and run it:
- Create a new environment with
conda create -n app and then run conda activate app.
- Make sure you're inside the
app folder of Hackathon-Project and then install the following packages:
- PyTorch
- Mediapipe
- OpenCV
- Strealit
- Pandas
- Numpy
- Once done, you should be able to run
streamlit run Home.py from the app folder and see the app running on localhost.
- Please make sure you're in a well lit environment and your upperbody is visible in order for the model to be able to detect the points.
- Have your speakers on in order to be able to listen to the ringing sound.
- If the app is not running or you're not able to set up the environment for whatever reason please reach out to us via any of the following contact methods:
https://www.youtube.com/watch?v=SVa9-QafC50