Reader small image

You're reading from  Hands-On Computer Vision with Detectron2

Product typeBook
Published inApr 2023
Reading LevelBeginner
PublisherPackt
ISBN-139781800561625
Edition1st Edition
Languages
Tools
Right arrow
Author (1)
Van Vung Pham
Van Vung Pham
author image
Van Vung Pham

Van Vung Pham is a passionate research scientist in machine learning, deep learning, data science, and data visualization. He has years of experience and numerous publications in these areas. He is currently working on projects that use deep learning to predict road damage from pictures or videos taken from roads. One of the projects uses Detectron2 and Faster R-CNN to predict and classify road damage and achieve state-of-the-art results for this task. Dr. Pham obtained his PhD from the Computer Science Department, at Texas Tech University, Lubbock, Texas, USA. He is currently an assistant professor at the Computer Science Department, Sam Houston State University, Huntsville, Texas, USA.
Read more about Van Vung Pham

Right arrow

Detectron2’s image augmentation system

Detectron2’s image augmentation system has three main groups of classes: Transformation, Augmentation, and AugInput. These components help augment images and their related annotations (for example, bounding boxes, segment masks, and key points). Additionally, this system allows you to apply a sequence of declarative augmentation statements and enables augmenting custom data types and custom operations. Figure 8.4 shows a simplified class diagram of Detectron2’s augmentation system:

Figure 8.4: Simplified class diagram of Detectron2’s augmentation system

Figure 8.4: Simplified class diagram of Detectron2’s augmentation system

The Transform and Augmentation classes are the bases for all the classes in their respective groups. Notably, the data format for boxes is in XYXY_ABS mode, which dictates the boxes to be in (x_min, y_min, x_max, y_max), specified in absolute pixels. Generally, subclasses of the Transform base class perform the deterministic changes of the...

lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Hands-On Computer Vision with Detectron2
Published in: Apr 2023Publisher: PacktISBN-13: 9781800561625

Author (1)

author image
Van Vung Pham

Van Vung Pham is a passionate research scientist in machine learning, deep learning, data science, and data visualization. He has years of experience and numerous publications in these areas. He is currently working on projects that use deep learning to predict road damage from pictures or videos taken from roads. One of the projects uses Detectron2 and Faster R-CNN to predict and classify road damage and achieve state-of-the-art results for this task. Dr. Pham obtained his PhD from the Computer Science Department, at Texas Tech University, Lubbock, Texas, USA. He is currently an assistant professor at the Computer Science Department, Sam Houston State University, Huntsville, Texas, USA.
Read more about Van Vung Pham