This tutorial explains how to convert and optimize the YOLOv8 PyTorch* model with OpenVNO.
This tutorial demonstrates step-by-step instructions on how to run and optimize PyTorch* Yolo V8 with OpenVINO.
The tutorial consists of the following steps:
- Prepare PyTorch model
- Download and prepare dataset
- Validate original model
- Convert PyTorch model to OpenVINO IR
- Validate converted model
- Prepare and run NNCF Postraining optimization pipeline
- Compare accuracy of the FP32 and quantized models
- Compare performance of the FP32 and quantized models
If you have not installed all required dependencies, follow the Installation Guide.