Gatekeeper: License plate detection using YOLOv5

Steps to run:

python -m venv venv .\venv\Scripts\Activate.ps1

Check if CUDA is available on your machine:

python -c "import torch; print(torch.cuda.is_available(), torch.cuda.get_device_name(0))"

YOLO uses CUDA automatically

Model used: YoloV5, https://github.com/ultralytics/yolov5.git Dataset used for finetuning: https://www.kaggle.com/datasets/saisirishan/indian-vehicle-dataset

Fine tuned model is stored as best.pt

Car numberplate video: https://www.kaggle.com/datasets/nimishshandilya/car-number-plate-video

python live_pipeline.py