Skip to content

AUTOSELFDRIVING2022/TrafficLight_Detection_Inference

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

TrafficLight Classification module with YoloV7 detector

This source is only includes inference code. Our detector has a seven different classes:

  • Person, Bike, Car, Bus, Truck, Traffic Sign, Traffic Light, Emergency Car Our traffic light classification supports a 12 traffic light types.
  • green, green_left, off, other, pedestrain, red, red_left, red_yellow, yellow, yellow21, yellow_green4, yellow_other (South Korea).
base code of YoloV7

A PyTorch implementation of YOLOv7.

TrafficLight Classification trainer code

Our traffic light classification code (Link: https://github.com/AUTOSELFDRIVING2022/TrafficLight_Classification_Trainer)

0. Weight Download

1. Inference

  • Load pretrained yolov7 modle weights.
  • Inference Traffic Light Classification:
python inference_YOLOv4_TL_Classification_TRACK.py --det_weight {weight_file_of_detector} --tl_weights {tl_classification_weight} --ec_weights {ec_classification_weight} --source {input_file_directory} --save_result_image {save_result_true_false} 

About

TrafficLight Detection Module

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages