Open In Github

Python scripts performing object detection using the YOLOv10 model in ONNX.

[!CAUTION] I skipped adding the pad to the input image when resizing, which might affect the accuracy of the model if the input image has a different aspect ratio compared to the input size of the model. Always try to get an input size with a ratio close to the input images you will use.

Requirements

• Check the requirements.txt file.
• For ONNX, if you have a NVIDIA GPU, then install the onnxruntime-gpu, otherwise use the onnxruntime library.

Installation

pip install yolov10-onnx

Or, clone this repository:

git clone https://github.com/ibaiGorordo/ONNX-YOLOv10-Object-Detection.git
cd ONNX-YOLOv10-Object-Detection
pip install -r requirements.txt

ONNX Runtime

For Nvidia GPU computers: pip install onnxruntime-gpu

Otherwise: pip install onnxruntime

ONNX model

• If the model file is not found in the models directory, it will be downloaded automatically from the Official Repo.
• Available models: yolov10n.onnx, yolov10s.onnx, yolov10m.onnx, yolov10b.onnx, yolov10l.onnx, yolov10x.onnx

Original YOLOv10 model

The original YOLOv10 model can be found in this repository: https://github.com/THU-MIG/yolov10

• The License of the models is AGPL-3.0 license: https://github.com/THU-MIG/yolov10/blob/main/LICENSE

Examples

• Image inference:

   python image_object_detection.py
  

• Webcam inference:

   python webcam_object_detection.py
  

• Video inference: https://youtu.be/hz9PYZF4ax4

   python video_object_detection.py
  

  

References:

• YOLOv10 model: https://github.com/THU-MIG/yolov10