Skip to content

Latest commit

 

History

History
47 lines (27 loc) · 1.64 KB

File metadata and controls

47 lines (27 loc) · 1.64 KB

Damaged-Car-parts-prediction-using-YOLOv8

Training

pip install ultralytics

  • Collect dataset of damaged cars
  • Annotate them
  • in this case there are 8 classes namely : damaged door, damaged window, damaged headlight, damaged mirror, dent, damaged hood, damaged bumper, damaged windshield
  • convert the annotations into YOLO 1.1 format
  • run main.py
  • in this particular case i ran for 5000 epochs

Screenshot from 2023-03-18 19-50-29

Results

F1_curve P_curve PR_curve R_curve

Prediction

val_batch0_pred val_batch1_pred val_batch2_pred

Deployment

Screenshot from 2023-03-20 06-11-43

Usage

  • Clone the repo
  • cd to my_fastapi_app
  • run python main.py

Test with images Done!