This project using yolov3 to detection license plate in street using repo : https://github.com/ultralytics/yolov3
Python 3.7 or later with the following pip3 install -U -r requirements.txt
packages:
numpy
torch >= 1.0.0
opencv-python
tqdm
- Data training :3600 images (size 1000x2000)
- Data test : 900 images
- Start Training: Run train.py --cfg cfg/yolov3.cfg --img-size 416
-
Run
detect.py
to apply trained weights to an image, such ascar.jpg
from thetest
folder. -
Link weight : https://drive.google.com/file/d/1hTH0Qj-fpxMnqnSzRTq64KPwkrPnGxsJ/view?usp=sharing
- Run
detect.py
withwebcam=True
to show a live webcam feed.
-
- Use
test.py --weights weights/weight.pt
to test YOLOv3 weights.
- Use
- MAP YOLOv3-416 : 97