DeepLabV3+ Semantic Segmentation with Keras
Semantic segmentation is the process of segmenting an image into classes - effectively, performing pixel-level classification. Color edges don't necessarily have to be the boundaries of an object, and pixel-level classification only works when you take the surrounding pixels and their context into consideration.
In this Guided Project, you'll learn how to build an end-to-end image segmentation model, based on the DeepLabV3+ architecture, using Python and Keras/TensorFlow.
Besides Mark R-CNNs which have good performance, and U-Net-like models which don't perform as well - DeepLabV3+ performs the state of the art of image segmentation. Besides being implemented within cutting-edge platforms like Detectron2, DeepLabV3+ is the architecture powering most modern segmentation applications, particularly in medical and aerial imagery.
With high-level libraries like Keras - transferring ideas into code is easier than ever before, and we'll be converting high-level concepts into a functional model, implementing both U-Net and DeepLabV3+. This is also the perfect opportunity to introduce the Albumentations library for performant, effective data augmentation. By the end of the project - you'll have the know-how of creating highly performant image segmentation models with as little as 300 training images:
Note: This Guided Project is part of our in-depth course on Practical Deep Learning for Computer Vision and assumes that you've read the previous lessons or have that prerequisite knowledge from before.
What is a Guided Project?
Turn Theory Into Practice
All great learning resources, books and courses teach you the holistic basics, or even intermediate concepts, and advise you to practice after that. As soon as you boot up your own project - the environment suddenly isn't as pristine as in the courses and books! Things go wrong, and it's oftentimes hard to pinpoint even why they do go wrong.
StackAbuse Guided Projects are there to bridge the gap between theory and actual work. We'll respect your knowledge and intelligence, and assume you know the theory. Time to put it into practice.
When applicable, Guided Projects come with downloadable, reusable scripts that you can refer back to whenever required in your new day-to-day work.