PyTorch to ONNX and OpenVINO IR Tutorial

This notebook demonstrates how to perform inference on a PyTorch semantic segmentation model using OpenVINO.

Notebook Contents

The notebook uses OpenVINO Model Optimizer to convert the open source fastseg semantic segmentation model, trained on the CityScapes dataset, to OpenVINO IR. It also shows how to perform segmentation inference on an image using OpenVINO Inference Engine and compares the results of the PyTorch model with the IR model.

Installation Instructions

If you have not done so already, please follow the Installation Guide to install all required dependencies.