YOLOmatic is a comprehensive open-source tool designed to automate and streamline YOLO model training through an intuitive Terminal UI. Supporting multiple YOLO versions, including YOLOv8, YOLOv9, YOLOv10, and YOLOv11, it offers a professional and efficient approach to training object detection models on custom COCO datasets. The software’s seamless integration with ClearML provides robust experiment tracking, model versioning, and performance monitoring capabilities, making it effortless to manage and compare different training runs. YOLOmatic’s automated configuration process and real-time feedback system transform the complex YOLO training workflow into an accessible and efficient process.

Key Features

• Comprehensive YOLO Support: Compatible with YOLOv8, YOLOv9, YOLOv10, and YOLOv11
• Interactive Terminal UI: User-friendly command-line interface for model and dataset selection
• ClearML Integration: Built-in experiment tracking and management
• Automated Workflow: Streamlined configuration and training process
• Custom Dataset Support: Optimized for COCO format datasets
• Professional UI: Enhanced headers and table styling for better user experience
• Flexible Configuration: YAML-based parameter management
• ONNX Export: Built-in model export capabilities with optimization options

Perfect for researchers, developers, and computer vision enthusiasts who need a reliable and efficient tool for training YOLO models on custom datasets. YOLOmatic simplifies the entire process while maintaining professional-grade tracking and management capabilities.

Getting Started (Install)

To begin, try to clone and install the repo with the following commands:

git clone https://github.com/shahabahreini/YOLOmatic.git
cd YOLOmatic
pip install -r requirements.txt

After that, organize your dataset as follows (notably, I recommend RoboFlow to prepare the dataset):

datasets/
└── your_dataset_name/
    ├── train/
    │   ├── images/
    │   └── labels/
    ├── valid/
    │   ├── images/
    │   └── labels/
    └── test/
        ├── images/
        └── labels/

Run and Train YOLO

1- Launch the interface:

python3 run.py

2- Select your YOLO version and model variant

3- Configure your dataset and training parameters.

4- Start training:

python3 Yolov_trainer.py