MVP: Implement ML model trainer for threat detection based on YOLO
ChatSam opened this issue · comments
Tasks
- Decide the YOLO version
- Finalize the data annotation format.
- Create a training dataset
- Implement the model trainer
- YoloV8 was selected as the final model.
- Ultralytics YOLO format was finalized as the data annotation format.
- The following 2 datasets are used for initial model
a. Gun Detection V1 dataset (~300 datapoints)
b. Weapon 2 dataset (~ 3900 datapoints)