Attention

As of June 30, 2025, the Isaac ROS Buildfarm for Isaac ROS 2.1 on Ubuntu 20.04 Focal is no longer supported.

Due to an isolated infrastructure event, all ROS 2 Humble Debian packages that were previously built for Ubuntu 20.04 are no longer available in the Isaac Apt Repository. All artifacts for Isaac ROS 3.0 and later are built and maintained with a more robust pipeline.

Users are encouraged to migrate to the latest version of Isaac ROS. The source code for Isaac ROS 2.1 continues to be available on the release-2.1 branches of the Isaac ROS GitHub repositories.

The original documentation for Isaac ROS 2.1 is preserved below.

Using DOPE at Different Image Resolutions

Overview

The DOPE network architecture, as outlined in the original paper, can receive input images of arbitrary size and subsequently produce output belief maps of the corresponding dimensions.

However, the ONNX format used to run this network on Triton or TensorRT is not as flexible, and an ONNX-exported model does NOT support arbitrary image sizes at inference time. Instead, the desired input image dimensions must be explicitly specified when preparing the ONNX file using the dope_converter.py script, as referenced in the quickstart.

Tutorial Walkthrough

  1. Follow steps 1-6 of the main DOPE quickstart.

  2. At step 7, run the dope_converter.py script with the two additional arguments row and col specifying the desired input image size:

    python3 /workspaces/isaac_ros-dev/src/isaac_ros_pose_estimation/isaac_ros_dope/scripts/dope_converter.py --format onnx --input /tmp/models/Ketchup.pth --row 1080 --col 1920
    
  3. Proceed through steps 8-9.

  4. At step 10, launch the ROS 2 launch file with two additional arguments network_image_height and network_image_width specifying the desired input image size:

    ros2 launch isaac_ros_dope isaac_ros_dope_tensor_rt.launch.py model_file_path:=/tmp/models/Ketchup.onnx engine_file_path:=/tmp/models/Ketchup.plan network_image_height:=1080 network_image_width:=1920 input_image_height:=1080 input_image_width:=1920
    
  5. Continue with the rest of the quickstart. You should now be able to detect poses in images of your desired size.