This notebook demonstrates how to do inference on a PyTorch semantic segmentation model, using OpenVINO.
The notebook uses Model Optimizer to convert the open-source Lite-RASPP semantic segmentation model with a MobileNet V3 Large backbone from torchvision, trained on COCO dataset images using 20 categories that are present in the Pascal VOC dataset, to OpenVINO IR. It also shows how to do segmentation inference on an image, using OpenVINO Runtime and compares the results of the PyTorch model with the OpenVINO IR model.
If you have not installed all required dependencies, follow the Installation Guide.