Hackernoon logoPixelLib: Image and Video Segmentation [Maybe just a Quick One] by@inquiringnomad

PixelLib: Image and Video Segmentation [Maybe just a Quick One]

PixelLib is a library created by Ayoola Olafenwa that provides easy out-of-the-box solutions to perform object segmentation with just a few lines of code. PixelLib supports two deeplabv3+ models, Keras and TensorFlow. The Tensorflow model performs better than the Keras model extracted from its checkpoint. In this article, we will go through some of the tasks that PixelLib can accomplish. The “Maybe just a quick one” series title is inspired by my most common reply to “Fancy a drink?”
image
Akis Loumpourdis Hacker Noon profile picture

Akis Loumpourdis

Inquiring Nomad. Reluctant geek.

Tags

Join Hacker Noon

Create your free account to unlock your custom reading experience.