Deep Trainer / SegNet


Emimal Jabason

The implemented architecture is taken from the work in [1]. The number of classes used in this specific model is 2. It can be modified by changing the number of filters in the last convolutional layer based on your needs.
[1] Vijay Badrinarayanan, Alex Kendall, and Roberto Cipolla. SegNet: A deep convolutional encoderdecoder architecture for image segmentation. arxiv:1511.00561, 2015.

Segnet segmentation

Installing extensions requires ORS Dragonfly 3.1 or later.