🚀 PET project, featuring:
- 📸 YOLO (nano/small) models for detecting fruits and vegetables (YOLOv8)
- 🖥️ Qt application (simulation of smart scales for automatic product detection)
- 🗄️ Database (PostgreSQL in a Docker container)
👉 Repository with the container: fruits-vegetables-cv-docker
python -m venv venv
source venv/bin/activate # Linux/macOS
venv\Scripts\activate # Windows
pip install -r requirements.txt
Create a .env
file and add the following parameters:
Variable | Example Value | Description |
---|---|---|
DEBUG |
TRUE or FALSE |
Debug mode |
MODEL |
NANO or SMALL |
YOLO version |
DATABASE_DBNAME |
smart_scales_db |
Database name |
DATABASE_USERNAME |
smart_scales_user |
Database user |
DATABASE_PASSWORD |
your_password |
Database password |
DATABASE_HOST |
localhost or IP |
Database host |
DATABASE_PORT |
5432 (or 5433 ) |
Database port |
🔹 Note:
The parameters DBNAME
, USERNAME
, and PASSWORD
are set in the PostgreSQL container. Details can be found in the repository fruits-vegetables-cv-docker.
Simply execute the following command:
python main.py
📖 More details about our models and the problem-solving approach can be found in our article:
📝 elibrary.ru/item.asp?id=80257050 (in Russian)
📂 Training logs and model weights 1-YOLOv8 (small), 2-YOLOv8 (nano), 3-YOLOv11 (nano), 4-YOLOv11 (small):
📎 Google Drive
📧 Email: timoshin_aleksey02@mail.ru
🐙 GitHub: AlekseyScorpi