English | 简体中文

训练策略

This is a road sign recognition project based on YOLOv5, developed with a PyQt5 interface, YOLOv5 trained model, and MySQL database. The project consists of five modules: parameter initialization, sign recognition, database, data analysis, and image processing(Please refer to the Chinese document for details).

• Sign Recognition Module

  

• Image Processing and Data Augmentation Module

  

• Parameter Initialization Module

  

• Database Module

  

• Data Analysis Module

  

• Login Interface

  

Road Sign Recognition System Based on YOLOV5

Run main.py.

• admin 123456
• 1 2
• Modify the main function to enter directly

• pt folder: Contains the model
• main_with folder: login.py (login UI), win.py (main UI)
• dialog folder: RTSP pop-up interface
• apprcc_rc.py: Resource file
• login_ji.py: Interface login logic file
• run-exp52: Road sign recognition model trained for 300 epochs
• tt100k_to_voc-main folder: JSON to YOLO format converter
• Dataset: TT100k : Traffic-Sign Detection and Classification in the Wild

pip install -r requirements.txt

• Converting the TT100K dataset to VOC format and selecting more than 100 images and XMLs for each of the 45 categories using a Python script
• https://github.com/Javacr/PyQt5-YOLOv5