isaac_ros_unet

Source code on GitHub.

Quickstart

1. Set up your development environment by following the instructions here.

2. Clone isaac_ros_common and this repository under ${ISAAC_ROS_WS}/src.

   cd ${ISAAC_ROS_WS}/src
   

   git clone https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_common.git
   

   git clone https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_image_segmentation.git
   

3. Pull down a ROS Bag of sample data:

   cd ${ISAAC_ROS_WS}/src/isaac_ros_image_segmentation && \
     git lfs pull -X "" -I "resources/rosbags/"
   

4. Launch the Docker container using the run_dev.sh script:

   cd ${ISAAC_ROS_WS}/src/isaac_ros_common && \
     ./scripts/run_dev.sh
   

5. Install this package’s dependencies.

sudo apt-get install -y ros-humble-isaac-ros-unet ros-humble-isaac-ros-triton ros-humble-isaac-ros-dnn-image-encoder

6. Download the PeopleSemSegNet ShuffleSeg ETLT file and the int8 inference mode cache file:

   mkdir -p /tmp/models/peoplesemsegnet_shuffleseg/1 && \
     cd /tmp/models/peoplesemsegnet_shuffleseg && \
     wget https://api.ngc.nvidia.com/v2/models/nvidia/tao/peoplesemsegnet/versions/deployable_shuffleseg_unet_v1.0/files/peoplesemsegnet_shuffleseg_etlt.etlt && \
     wget https://api.ngc.nvidia.com/v2/models/nvidia/tao/peoplesemsegnet/versions/deployable_shuffleseg_unet_v1.0/files/peoplesemsegnet_shuffleseg_cache.txt
   

7. Convert the ETLT file to a TensorRT plan file:

   /opt/nvidia/tao/tao-converter -k tlt_encode -d 3,544,960 -p input_2:0,1x3x544x960,1x3x544x960,1x3x544x960 -t int8 -c peoplesemsegnet_shuffleseg_cache.txt -e /tmp/models/peoplesemsegnet_shuffleseg/1/model.plan -o argmax_1 peoplesemsegnet_shuffleseg_etlt.etlt
   

8. Create a file called /tmp/models/peoplesemsegnet_shuffleseg/config.pbtxt by copying the sample Triton config file:

   cp /workspaces/isaac_ros-dev/src/isaac_ros_image_segmentation/resources/peoplesemsegnet_shuffleseg_config.pbtxt /tmp/models/peoplesemsegnet_shuffleseg/config.pbtxt
   

9. Run the following launch files to spin up a demo of this package:

   ros2 launch isaac_ros_unet isaac_ros_unet_triton.launch.py model_name:=peoplesemsegnet_shuffleseg model_repository_paths:=['/tmp/models'] input_binding_names:=['input_2:0'] output_binding_names:=['argmax_1'] network_output_type:='argmax' input_image_width:=1200 input_image_height:=632
   

   Then open another terminal, and enter the Docker container again:

   cd ${ISAAC_ROS_WS}/src/isaac_ros_common && \
     ./scripts/run_dev.sh
   

   Then, play the ROS bag:

   ros2 bag play -l src/isaac_ros_image_segmentation/resources/rosbags/unet_sample_data/
   

10. Visualize and validate the output of the package by launching rqt_image_view in another terminal: In a third terminal, enter the Docker container again:

    cd ${ISAAC_ROS_WS}/src/isaac_ros_common && \
      ./scripts/run_dev.sh
    

    Then launch rqt_image_view:

    ros2 run rqt_image_view rqt_image_view
    

    Then inside the rqt_image_view GUI, change the topic to /unet/colored_segmentation_mask to view a colorized segmentation mask.

Note

The raw segmentation mask is also published to /unet/raw_segmentation_mask. However, the raw pixels correspond to the class labels and so the output is unsuitable for human visual inspection.

Try More Examples

To continue your exploration, check out the following suggested examples:

• Tutorial with Isaac Sim
• Tutorial with Nitros Graph

Troubleshooting

Isaac ROS Troubleshooting

For solutions to problems with Isaac ROS, please check here.

Deep Learning Troubleshooting

For solutions to problems with using DNN models, please check here.

API

Usage

Three launch files are provided to use this package. The first launch file launches isaac_ros_tensor_rt, whereas another one uses isaac_ros_triton, along with the necessary components to perform encoding on images and decoding of U-Net’s output. The final launch file launches an Argus-compatible camera with a rectification node, along with the components found in isaac_ros_unet_triton.launch.py. A more comprehensive tutorial featuring the third launch file can be found here.

Warning

For your specific application, these launch files may need to be modified. Please consult the available components to see the configurable parameters.

Launch File	Components Used
isaac_ros_unet_tensor_rt.launch.py	DnnImageEncoderNode, TensorRTNode, UNetDecoderNode
isaac_ros_unet_triton.launch.py	DnnImageEncoderNode, TritonNode, UNetDecoderNode
isaac_ros_argus_unet_triton.launch.py	ArgusMonoNode, RectifyNode, DnnImageEncoderNode, TritonNode, UNetDecoderNode

UNetDecoderNode

ROS Parameters

ROS Parameter	Type	Default	Description
color_segmentation_mask_encoding	string	rgb8	The image encoding of the colored segmentation mask. Supported values: rgb8, bgr8
color_palette	int64_t list	[]	Vector of integers where each element represents the RGB color hex code for the corresponding class label. The number of elements should equal the number of classes. E.g. [0xFF0000, 0x76b900]
network_output_type	string	softmax	The type of output that the network provides. Supported values: softmax, argmax, sigmoid
mask_width	int16_t	960	The width of the segmentation mask.
mask_height	int16_t	544	The height of the segmentation mask.

Warning

• Note: the model output should be NCHW or NHWC. In this context, the C refers to the class.

• Note: For the network_output_type, the softmax and sigmoid option expects a single 32 bit floating point tensor. For the argmax option, a single signed 32 bit integer tensor is expected.

• Note: Models with greater than 255 classes are currently not supported. If a class label greater than 255 is detected, this mask will be downcast to 255 in the raw segmentation.

ROS Topic	Interface	Description
tensor_sub	isaac_ros_tensor_list_interfaces/TensorList	The tensor that contains raw probabilities for every class in each pixel.

Warning

All input images are required to have height and width that are both an even number of pixels.

ROS Topics Published

ROS Topic	Interface	Description
unet/raw_segmentation_mask	sensor_msgs/Image	The raw segmentation mask, encoded in mono8. Each pixel represents a class label.
/unet/colored_segmentation_mask	sensor_msgs/Image	The colored segmentation mask. The color palette is user specified by the color_palette parameter.