Computer Vision

From UFRC
Jump to navigation Jump to search

Description

This page describes the collection of Computer Vision software on HiperGator. Computer vision is a crucial field of artificial intelligence that enables computers and systems to derive meaningful information from digital images, videos and other visual inputs. Research Computing AI support will help with building new and finetuning existing advanced models for various tasks including image classification, object detection, semantic segmentation, etc. via support requests or consulting.

Deep Learning Frameworks

There are preinstalled and configured environments on HiPerGator for the most frequently used deep learning frameworks including tensorflow, pytorch, and MxNet. The available deep learning frameworks can be queried using

 module spider [pytorch/tensorflow/mxnet] 

Users can also customize their own conda environment following this tutorial: Managing Python environments and Jupyter kernels

Module environments for Computer Vision

Below are a number of module environments or framework that is configured for training or your deep learning models on HiPerGator-AI.

  • tensorflow or ngc-tensorflow: TensorFlow is a free and open-source software library for machine learning and artificial intelligence. ngc-tensorFlow is the NVIDIA optimized environment container for training on NVIDIA GPUs. Use
 module spider tensorflow

to list the available versions on HiPerGator-AI.

  • pytorch or ngc-pytorch: PyTorch is an open source machine learning framework based on the Torch library. ngc-pytorch is the NVIDIA optimized environment container for training on NVIDIA GPUs. Use
  module spider pytorch

to list the available versions on HiPerGator-AI.

  • Matlab: Matlab provides rich libraries of image processing techniques for image analysis.
  • Detectron2: Detectron2 is Facebook AI Research's next generation library that provides state-of-the-art detection and segmentation algorithms.

Modules for Medical Imaging Applications

  • MONAI core: MONAI Core is a PyTorch-based, open-source framework for deep learning in healthcare imaging, part of PyTorch Ecosystem. Use
 module spider monai 

to list the available versions on HiPerGator-AI. Please see recorded MONAI Core tutorials for details.

  • MONAI label: MONAI Label is an intelligent open source image labeling and learning tool that enables users to create annotated datasets and build AI annotation models. MONAI Label reduces the time and effort of annotating new datasets and enables the adaptation of AI to the task at hand by continuously learning from user interactions and data.

Use the following command to list the available versions on HiPerGator-AI.

 module spider ngc-monailabel

Please see MONAI Label tutorials for details.

Modules for Visualization Toolkit

  • Paraview: ParaView is an open-source multiple-platform application for interactive, scientific visualization. It has a client–server architecture to facilitate remote visualization of datasets, and generates level of detail models to maintain interactive frame rates for large datasets.
  • VisIt: VisIt is an open-source interactive parallel visualization and graphical analysis tool for viewing scientific data. It can be used to visualize scalar and vector fields defined on 2D and 3D structured and unstructured meshes.
  • ITK-SNAP: ITK-SNAP is an interactive software application that allows users to navigate three-dimensional medical images, manually delineate anatomical regions of interest, and perform automatic image segmentation.
  • 3DSlicer: 3D Slicer is a free, open source and multi-platform software package widely used for medical, biomedical, and related imaging research.