Hprc banner tamu.png

Difference between revisions of "SW:R-CNN"

From TAMU HPRC
Jump to: navigation, search
Line 1: Line 1:
 
[https://en.wikipedia.org/wiki/Region_Based_Convolutional_Neural_Networks "Region Based Convolutional Neural Networks (R-CNN) are a family of machine learning models for computer vision and specifically object detection."] -- Wikipedia
 
[https://en.wikipedia.org/wiki/Region_Based_Convolutional_Neural_Networks "Region Based Convolutional Neural Networks (R-CNN) are a family of machine learning models for computer vision and specifically object detection."] -- Wikipedia
  
The page above mentions a number of packages available for using R-CNNs.  For now, this page will concentrate on [https://github.com/facebookresearch/detectron2 Detectron2] from [https://ai.facebook.com/ Facebook AI Research].
+
The page above mentions a number of packages available for using R-CNNs.  For now, this page will concentrate on [https://github.com/facebookresearch/detectron2 Detectron2].
 +
 
 +
= Detectron2 =
 +
"Detectron2 is [https://ai.facebook.com/ Facebook AI Research]'s next generation software system that implements state-of-the-art object detection algorithms. It is a ground-up rewrite of the previous version, Detectron, and it originates from maskrcnn-benchmark." --[https://github.com/facebookresearch/detectron2 Detectron2 site]
 +
 
 +
It also includes support for Fast R-CNN, Faster R-CNN and other R-CNNs.
 +
 
 +
See the Directron2 site for using and training.  For now, this page will only cover installation.
 +
 
 +
== Installing Detectron2 in a Python virtual environment on HPRC clusters ==

Revision as of 15:36, 12 August 2020

"Region Based Convolutional Neural Networks (R-CNN) are a family of machine learning models for computer vision and specifically object detection." -- Wikipedia

The page above mentions a number of packages available for using R-CNNs. For now, this page will concentrate on Detectron2.

Detectron2

"Detectron2 is Facebook AI Research's next generation software system that implements state-of-the-art object detection algorithms. It is a ground-up rewrite of the previous version, Detectron, and it originates from maskrcnn-benchmark." --Detectron2 site

It also includes support for Fast R-CNN, Faster R-CNN and other R-CNNs.

See the Directron2 site for using and training. For now, this page will only cover installation.

Installing Detectron2 in a Python virtual environment on HPRC clusters