surejm/yolov10_testing_mcu_detection

MCU Board Detection with YOLOv10

This repository contains the code and dataset for detecting multiple MCU boards using YOLOv10. This project is a simple experimentation to understand the detection capabilities of YOLOv10.

Table of Contents

• Dataset Creation
• Data Annotation
• Model Training
• Model Inference
• Results
• Contributing
• License

Dataset Creation

The dataset was created using a USB camera connected to a computer. We captured images at a rate of 4 photos per second using a Python script.

Dataset Creation Script

Data Annotation

Data annotation was performed using Roboflow. The process included:

• Data augmentation
• Dataset splitting into train, validation, and test sets
• Checking data proportions

Dataset link

Model Training

The model was trained using YOLOv10 on Google Colab. The training script is available in the repository.

Training Script

Model Inference

The trained model was downloaded and used for inference on a local computer with a USB camera.

Inference Script

Video Demonstration

You can watch the video demonstration of the model in action on YouTube:

Watch the video

Contributing

Contributions are welcome! Please open an issue or submit a pull request.

License

This project is licensed under the MIT License.