Training SegNet model for multi-class pixel wise classification

 

Source: http://mi.eng.cam.ac.uk/projects/segnet/tutorial.html

This implementation of SegNet [1] is built on top of the Caffe deep learning library. The first step is to download the SegNet source code, which can be found on our GitHub repository here. Our code to support SegNet is licensed for non-commercial use (license summary). To install SegNet, please follow the Caffe installation instructions here. Make sure you also compile Caffe’s python wrapper.

screen-shot-2016-11-16-at-10-08-22-am

Get  SegNet Tutorial –  https://github.com/alexgkendall/SegNet-Tutorial

Your file structure should now look like this:

/SegNet/
    CamVid/
        test/
        testannot/
        train/
        trainannot/
        test.txt
        train.txt
    Models/
        # SegNet and SegNet-Basic model files for training and testing
    Scripts/
        compute_bn_statistics.py
        test_segmentation_camvid.py
    caffe-segnet/
        # caffe implementation

Testing SegNet Live: http://mi.eng.cam.ac.uk/projects/segnet/demo.php#demo

Bayesian SegNet:

This is a tutorial on Bayesian SegNet [4], a probabilistic extension to SegNet. By the end of this tutorial you will be able to train a model which can take an image like the one on the left, and produce a segmentation (center) and a measure of model uncertainty (right).

Source: http://mi.eng.cam.ac.uk/projects/segnet/tutorial.html#bayes_segnet

screen-shot-2016-11-16-at-10-34-52-am

 

Happy machine learning, have fun!!

 

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s