This is a modified version of Caffe which supports the ENet architecture.
It comes as a fork of Caffe-SegNet-cuDNN5 with a slightly adapted dense-image-data-layer and a new layer: spatial dropout (python layer).
Credit: Alex Kendall for his caffe-segnet repository, which is the basis for this.
Please find a tutorial on how to use it in the ENet repository.
This extension to the Caffe library is released under a creative commons license which allows for personal and research use only. You can view a license summary here: http://creativecommons.org/licenses/by-nc/4.0/