End-to-end samples

​

Prerequisites

• For more information, see the Evaluate tab on the Scenarios page.
• The host and device can reach each other over the network using the ping command.
• ROS 2 Jazzy is available on both the host and the device with a matching ROS_DOMAIN_ID.
• The device runs qcom-robotics-proprietary-image (Qualcomm Linux) or qirp-sdk or qirp-sdk-desktop (Ubuntu).

​

Run AI samples

• Image classification
• Hand detection

Run sample_resnet101 end-to-end to classify a bundled image with the ResNet-101 model through the Qualcomm® AI Engine Direct SDK (QNN).

​

Pipeline diagram

The following diagram shows the ROS 2 nodes and topics in the pipeline.

​

Run the sample

Follow the OS tab. Both paths launch with the built-in image publisher, which defaults to publishing glasses.jpg at 10 Hz.

• Qualcomm Linux
• Ubuntu

1

Source the runtime environment on the device

Over SSH to the device:

source /usr/share/qirp-setup.sh -m
export ROS_DOMAIN_ID=123

2

Launch the sample with the image publisher

ros2 launch sample_resnet101 launch_with_image_publisher.py

3

Echo the classification topic

In a second SSH session:

ros2 topic echo /resnet101_output

1

Install the sample package

sudo apt install ros-jazzy-sample-resnet101

2

Set up the environment on the device

source /opt/ros/jazzy/setup.bash
export ROS_DOMAIN_ID=123

3

Launch the sample with the image publisher

ros2 launch sample_resnet101 launch_with_image_publisher.py

4

Echo the classification topic

ros2 topic echo /resnet101_output

​

Expected result

The following output shows a steady classification stream on /resnet101_output.

data: 'sunglass'
---
data: 'sunglass'
---
data: 'sunglass'

Pass image_path:=<your image path> to the launch command to change the input image; the label updates accordingly.

Run sample_hand_detection end-to-end to detect palms and hand landmarks with the MediaPipe Hand Landmark Detector through QNN. The two-stage pipeline runs palm detection followed by landmark regression, then annotates the source frame.

​

Pipeline diagram

The following diagram shows the ROS 2 nodes and topics in the two-stage pipeline.

​

Run the sample

Follow the OS tab. Both paths launch with the built-in image publisher, so no camera is required.

• Qualcomm Linux
• Ubuntu

1

Source the runtime environment on the device

Over SSH to the device:

source /usr/share/qirp-setup.sh -m
export ROS_DOMAIN_ID=123
export PYTHONPATH=$PYTHONPATH:/opt/ros/jazzy/lib/python3.14/site-packages/sample_hand_detection

2

Launch the sample with the image publisher

ros2 launch sample_hand_detection launch_with_image_publisher.py model_path:=/opt/model/

3

View the annotated frames on the host

In a host terminal:

export DISPLAY=YOUR_HOST_IP:0
export ROS_DOMAIN_ID=123
rqt

In rqt, select Plugins → Visualization → Image View and choose /handlandmark_result.

1

Install the sample package

sudo apt install ros-jazzy-sample-hand-detection

2

Set up the environment on the device

source /opt/ros/jazzy/setup.bash
export ROS_DOMAIN_ID=123

3

Launch the sample with the image publisher

ros2 launch sample_hand_detection launch_with_image_publisher.py

4

View the annotated frames on the host

On the host, open rqt, select Plugins → Visualization → Image View, and choose /handlandmark_result.

​

Expected result

The following figure shows the annotated frame with the palm bounding box and the 21 landmark markers when a fully open palm image is published.

​

Next steps

• QIR SDK user guide (Qualcomm Linux) — Complete QIR SDK user guide for Qualcomm Dragonwing devices running Qualcomm Linux software, including SDK overview, install, image variants, cross-compile toolchain, overlay mechanism, migration guide, and troubleshooting.
• QIR SDK user guide (Ubuntu) — Complete QIR SDK user guide for Qualcomm Dragonwing devices running Ubuntu, including software architecture, install, and sample applications.
• Try more sample applications
  QIR SDK Sample applications (Linux)

  Samples

  QIR SDK Sample applications (Ubuntu)

  Samples