Semantic Segmentation with Open3D-ML, PyTorch Backend, and a Custom Dataset

As part of my experimentation with Open3D-ML for Point Clouds, I wrote articles explaining how to install this library with <a href="https://medium.com/@kidargueta/testing-open3d-ml-for-3d-object-detection-and-segmentation-df125e7a8283?sk=ebf7a48cedb1499ddb13e2846e49358f" rel="noopener">Tensorflow</a> and <a href="https://medium.com/@kidargueta/installing-open3d-ml-for-3d-computer-vision-with-pytorch-d640a6862e19?sk=4d899c1dde4126ec011cee7273a106c2" rel="noopener">PyTorch</a> support. To test the installation, I explained how to run a simple Python script to visualize a labeled dataset for Semantic Segmentation called <a href="http://www.semantic-kitti.org/" rel="noopener ugc nofollow" target="_blank">SemanticKITTI</a>. In this article, I go over the steps I followed to do inference on any Point Cloud, including the test portion of SemanticKITTI, as well as on my private dataset. The rest of this article assumes that you have successfully installed and tested Open3D-ML with PyTorch backend by following my previous article. Having done so also means you have downloaded the SemanticKITTI dataset. To run a Semantic Segmentation model on unlabeled data, you need to load an Open3D-ML pipeline. The pipeline will consist of a Semantic Segmentation model, a dataset, and probably other pre/post-processing steps. Open3D-ML comes with modules and configuration files to easily load and run popular pipelines. <a href="https://medium.com/@kidargueta/semantic-segmentation-with-open3d-ml-pytorch-backend-and-a-custom-dataset-b82e324ebe95">Click Here</a>