2D semantic segmentation

2D semantic segmentation trained on the Vaihingen dataset

Model | Trainable | Inference | Pre-trained

Published by DEEP-Hybrid-DataCloud Consortium
Created: - Updated:

Model Description

Build Status

Example application for ISPRS 2D Semantic Labeling Contest [1]:

2D semantic segmentation (Vaihingen dataset [2]) that assigns labels to multiple object categories.

Vaihingen dataset

  • 33 patches of different sizes with 9 cm spatial resolution
  • Manually classified into six land cover classes:
  • Impervious surfaces, Building, Low vegetation, Tree, Clutter/background
  • The groundtruth is provided for only 16 patches
  • For the remaining scenes it is unreleased and used for evaluation of submitted results

N.B.: pre-trained weights can be found here (unzip before use!)


[1] http://www2.isprs.org/commissions/comm3/wg4/semantic-labeling.html

[2] M. Cramer: The DGPF-Test on Digital Airborne Camera Evaluation Overview and Test Design, PFG Photogrammetrie, Fernerkundung, Geoinformation, vol. 2010, no. 2, pp. 73-82, 2010.

Test this module

You can test and execute this module in various ways.

Excecute locally on your computer using Docker

You can run this module directly on your computer, assuming that you have Docker installed, by following these steps:

$ docker pull deephdc/deep-oc-semseg_vaihingen
$ docker run -ti -p 5000:5000 deephdc/deep-oc-semseg_vaihingen

Execute on your computer using udocker

If you do not have Docker available or you do not want to install it, you can use udocker within a Python virtualenv:

$ virtualenv udocker
$ source udocker/bin/activate
$ git clone https://github.com/indigo-dc/udocker
$ cd udocker
$ pip install .
$ udocker pull deephdc/deep-oc-semseg_vaihingen
$ udocker create deephdc/deep-oc-semseg_vaihingen
$ udocker run -p 5000:5000  deephdc/deep-oc-semseg_vaihingen

In either case, once the module is running, point your browser to and you will see the API documentation, where you can test the module functionality, as well as perform other actions (such as training).

For more information, refer to the user documentation.

Train this module

You can train this model using the DEEP framework. In order to execute this module in our pilot e-Infrastructure you would need to be registered in the DEEP IAM.

Once you are registedered, you can go to our training dashboard to configure and train it.

For more information, refer to the user documentation.


tensorflow, semantic segmentation, cnn, trainable, inference, pre-trained, api-v2


License: MIT

Configure and train

Get the code

Github Docker Hub

Get the data