PIXELLIB’S OFFICIAL DOCUMENTATION¶
PixelLib is a library created for performing image and video segmentation using few lines of code. It is a flexible library created to allow easy integration of image and video segmentation into software solutions.
PixelLib requires python’s version 3.5-3.7, Download python
It requires pip’s version >= 19.0
Install pip with:
pip3 install pip
Install PixelLib and its dependencies:
Install the latest version of tensorflow(Tensorflow 2.0+) with:
pip3 install tensorflow
Install PixelLib with:
pip3 install pixellib --upgrade
PixelLib supports the two major types of segmentation:
1 Semantic segmentation: Objects in an image with the same pixel values are segmented with the same colormaps.
2 Instance segmentation: Instances of the same object are segmented with different color maps.
- Semantic segmentation of images with PixelLib using Ade20k model
- Semantic segmentation of videos with PixelLib using Ade20k model
- Segmentation of live camera with Ade20k model
- Semantic segmentation of images with PixelLib using Pascalvoc model
- Semantic Segmentation of videos with PixelLib using Pascalvoc model
- Segmentation of live camera with pascalvoc model
- Instance segmentation of images with PixelLib
- Instance segmentation of videos with PixelLib
- Instance Segmentation of Live Camera with Mask R-cnn.