Mask Mistakes Detection
Detect the mistakes people make while wearing masks. Using YOLO model with Darknet Framework for Multiclass Object Detection. Labels were inspired from this article:
Dataset Preparation
Scraping Images from Google Images using Download All Images Extension.
Search Queries
wrong mask wearing, mask mistakes, 鼻出しLabels
"The Escape Hatch"
"The Earring"
"The Sniffer"
"The Stache"
"The Nose Plug"
"The Neckbeard"
Labelling and Annotation
🖍️LabelImg is a graphical image annotation tool and label object bounding boxes in images
Training
The files maskmis.data and maskmis.names should go in the /data folder of darknet.
Don't forget to create the train.txt and test.txt that maskmis.data calls.
Finally, start training using the following command:
$ ./darknet -i 0 detector train data/maskmis.data cfg/yolov3_maskmis.cfg darknet53.conv.74
Contributing
Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.
Make a Pull requests for any changes. For major changes, please open an issue first to discuss what you would like to change.
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/NewFeature) - Commit your Changes (
git commit -m 'Add some NewFeature') - Push to the Branch (
git push origin feature/NewFeature) - Open a Pull Request
Demos
To-Do
References
YOLO: Real-Time Object Detection