^{Back | Next |}^Contents
^{Semantic Segmentation}

# Running Segmentation Models on Jetson To test a custom segmentation network model snapshot on the Jetson, use the command line interface to [`segnet-console`](../examples/segnet-console/segnet-console.cpp) First, for convienience, set the path to your extracted snapshot into a `$NET` variable: ``` bash $ NET=20170421-122956-f7c0_epoch_5.0 $ ./segnet-console drone_0428.png output_0428.png \ --prototxt=$NET/deploy.prototxt \ --model=$NET/snapshot_iter_22610.caffemodel \ --labels=$NET/fpv-labels.txt \ --colors=$NET/fpv-deploy-colors.txt \ --input_blob=data \ --output_blob=score_fr ``` This runs the specified segmentation model on a test image downloaded with the repo. ![Alt text](https://github.com/dusty-nv/jetson-inference/raw/master/docs/images/segmentation-aerial-tensorRT.png) In addition to the aerial model from this tutorial, the repo also includes pre-trained models on other segmentation datasets, including **[Cityscapes](https://www.cityscapes-dataset.com/)**, **[SYNTHIA](http://synthia-dataset.net/)**, and **[Pascal-VOC](http://host.robots.ox.ac.uk/pascal/VOC/)**. ##

Back | FCN-Alexnet Patches for TensorRT