ONNX YOLOv8 Instance Segmentation

Python scripts performing instance segmentation using the YOLOv8 model in ONNX.

Important

The input images are directly resized to match the input size of the model. I skipped adding the pad to the input image (image letterbox), it 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.

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

git clone https://github.com/ibaiGorordo/ONNX-YOLOv8-Instance-Segmentation.git
cd ONNX-YOLOv8-Instance-Segmentation
pip install -r requirements.txt

For Nvidia GPU computers: pip install onnxruntime-gpu

Otherwise: pip install onnxruntime

You can convert the Pytorch model to ONNX using the following Google Colab notebook:

The original YOLOv8 Instance Segmentation model can be found in this repository: YOLOv8 Instance Segmentation

Image inference:
```
python image_instance_segmentation.py
```
Webcam inference:
```
python webcam_instance_segmentation.py
```
Video inference: https://youtu.be/8j-FjTsLctA
```
python video_instance_segmentation.py
```
Original video: https://youtu.be/-bhSSispEcg