-
This repository is created for differentiating people who are wearing a mask, not wearing a mask and wearing a mask incorrectly.
-
The model was trained based on SSD Inception V2 architecture by Tensorflow 1.
-
On RTX3080, it can run up to 45 FPS (Python)
-
On i7-8550u, it can run up to 10 FPS (Python) and 15 FPS (C++)
-
On Nvidia-Jetson NX, it can run up to 7-9 FPS (Python)
-
The dataset used for training this model is from (https://www.kaggle.com/andrewmvd/face-mask-detection)
- Please run the following command to use your webcam as a detection camera.
python video_nms.pyxhost +local:docker # To allow xhost for docker container
docker compose up --build
