Skip to content

Latest commit

 

History

History
36 lines (27 loc) · 1.74 KB

README.md

File metadata and controls

36 lines (27 loc) · 1.74 KB
Raw

Background Removal Demo

Binder Colab

This demo notebook shows image segmentation and removing/adding background with U^2-Net and OpenVINO™.

Image segmentation with U^2-Net and OpenVINO Background removal with U^2-Net and OpenVINO

Notebook Contents

  • Importing Pytorch library and loading U^2-Net model.
  • Converting PyTorch U^2-Net model to OpenVINO IR format.
  • Loading and preprocessing input image.
  • Doing inference on OpenVINO IR model.
  • Visualizing results.

U^2-Net source

@InProceedings{Qin_2020_PR,
title = {U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection},
author = {Qin, Xuebin and Zhang, Zichen and Huang, Chenyang and Dehghan, Masood and Zaiane, Osmar and Jagersand, Martin},
journal = {Pattern Recognition},
volume = {106},
pages = {107404},
year = {2020}
}

Installation Instructions

This is a self-contained example that relies solely on its own code.
We recommend running the notebook in a virtual environment. You only need a Jupyter server to start. For details, please refer to Installation Guide.