Pixellib is a library for performing segmentation of images and videos. It supports the two major types of image segmentation:
1.Semantic segmentation
2.Instance segmentation
You can implement both semantic and instance segmentation with few lines of code.
There are two types of Deeplabv3+ models available for performing semantic segmentation with PixelLib:
- Deeplabv3+ model with xception as network backbone trained on Ade20k dataset, a dataset with 150 classes of objects.
- Deeplabv3+ model with xception as network backbone trained on Pascalvoc dataset, a dataset with 20 classes of objects.
Instance segmentation is implemented with PixelLib by using Mask R-CNN model trained on coco dataset.
Note Deeplab and mask r-ccn models are available in the release of this repository.
Install latest version of tensorflow(Tensorflow 2.0+) with:
pip3 install tensorflow
pip3 install pixellib --upgrade
Visit PixelLib's official documentation on readthedocs
Read the following tutorials on performing both semantic and instance segmentation of images and videos with PixelLib.
Learn how to perform state of the art semantic segmentation of 150 classes of objects with Ade20k model using 5 Lines of Code. Perform indoor and outdoor segmentation of scenes with PixelLib by using Ade20k model.
Implement state of the art semantic segmentation of 150 classes objects in video's feeds using Ade20k model with PixelLib using 5 Lines of Code.
Learn how to perform state of the art semantic segmentation of 20 common objects with Pascalvoc model using 5 Lines of Code. Perform segmentation of unique objects with PixelLib by using Pascalvoc model.
Implement state of the art semantic segmentation of 20 unique objects in video's feeds using Pascalvoc model with PixelLib using 5 Lines of Code.
Learn how to implement state of the art instance segmentation of objects with Mask-RCNN with PixelLib using 5 Lines of Code.
Implement state of the art instance segmentation of objects in video's feeds with Mask-RCNN model using 5 Lines of Code.
-
A segmentation api integrated with PixelLib to perform Semantic and Instance Segmentation of images on ios https://github.com/omarmhaimdat/segmentation_api
-
PixelLib is integerated in drone's cameras to perform instance segmentation of live video's feeds https://elbruno.com/2020/05/21/coding4fun-how-to-control-your-drone-with-20-lines-of-code-20-n/?utm_source=twitter&utm_medium=social&utm_campaign=tweepsmap-Default
-
Bonlime, Keras implementation of Deeplab v3+ with pretrained weights https://github.com/bonlime/keras-deeplab-v3-plus
-
Liang-Chieh Chen. et al, Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation https://arxiv.org/abs/1802.02611
-
Matterport, Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow https://github.com/matterport/Mask_RCNN
-
Kaiming He et al, Mask R-CNN https://arxiv.org/abs/1703.06870
-
TensorFlow DeepLab Model Zoo https://github.com/tensorflow/models/blob/master/research/deeplab/g3doc/model_zoo.md
-
Pascalvoc and Ade20k datasets' colormaps https://github.com/tensorflow/models/blob/master/research/deeplab/utils/get_dataset_colormap.py