# Classify images with `sample_resnet101`
`sample_resnet101` uses Python to performs image classification, in which process it uses Qualcomm® AI Engine Direct SDK (QNN) for model inference.
`resnet101` is a machine learning model that can classify images from the Imagenet dataset. It also serves as the basis for building more advanced models tailored to specific use cases.
Note
For more information, see [sample_resnet101](https://github.com/qualcomm-qrb-ros/qrb_ros_samples/tree/main/ai_vision/sample_resnet101) on GitHub.
## Pipeline flow for `image classification`
## ROS nodes used in the `image classification` pipeline
| ROS Node | Description |
| --- | --- |
| `qrb_ros_resnet101` | `qrb_ros_resnet101` is a python-based ROS2 Jazzy package that implements image classification. It uses QNN HTP as the model backend. The ROS node receives an image topic and publishes the classification result topic. |
| `image_publisher` | `image_publisher` is a ROS2 Jazzy package that publishes the image ROS topic with the local path. For more information, see [image_publisher](https://github.com/ros-perception/image_pipeline). |
## ROS topics used in the `image classification` pipeline
| ROS topic | Message Type | Published/Subscribed By | Description |
| --- | --- | --- | --- |
| `/image_raw` | `sensor_msgs.msg.Image` | Subscribe to images from other nodes | The image to be processed. |
| `/resnet101_output` | `sensor_msgs.msg.String` | Published by `qrb_ros_resnet101` | Publishes the image classification result. |
## Prerequisites
You have completed the settings in [Set up the environment for running sample applications](https://docs.qualcomm.com/doc/80-70023-265/topic/quick_start.html#setup-demo-qs).
## Run out-of-the-box `image classification`
1. On the development kit, run the following commands:
# setup runtime environment
(ssh) source /usr/share/qirp-setup.sh -m
# Set the ROS_DOMAIN_ID
(ssh) export ROS_DOMAIN_ID=123
(ssh) ros2 launch sample_resnet101 launch_with_qrb_ros_camera.py
Copy to clipboard
2. In the Docker environment of the host computer, run the following commands:
Start a terminal and run the following command to check the image classification result.
(ssh) export ROS_DOMAIN_ID=123
(ssh) ros2 topic echo /resnet101_output
Copy to clipboard
## Build and run `image classification`
1. In a terminal of the host computer, run the following commands:
1. Build the sample application project.
tar -zxvf qirp-sdk_2.5.0.tar.gz && cd qirp-sdk
source setup.sh
# build sample
cd /qirp-samples/ai_vision/sample_resnet101
colcon build
Copy to clipboard
2. Package and push the sample application to the device.
# package and push build result of sample
cd /qirp-samples/ai_vision/sample_resnet101/install/sample_resnet101
tar -czvf sample_resnet101.tar.gz lib share
scp sample_resnet101.tar.gz root@[ip-addr]:/opt/
Copy to clipboard
2. On the development kit, run the following commands:
1. Install the sample application.
# Remount the /usr directory with read-write permissions
(ssh) mount -o remount rw /usr
# Install sample package
(ssh) tar --no-overwrite-dir --no-same-owner -zxf /opt/sample_resnet101.tar.gz -C /usr/
Copy to clipboard
2. Run the sample application with the steps in [Run out-of-the-box image classification](https://docs.qualcomm.com/doc/80-70023-265/topic/image_classification.html#run-resnet101q).
Last Published: Dec 29, 2025
[Previous Topic
Detect hands with](https://docs.qualcomm.com/bundle/publicresource/80-70023-265/topics/hand_detection.md) [Next Topic
Estimate image depth values with](https://docs.qualcomm.com/bundle/publicresource/80-70023-265/topics/sample_depth_estimation.md)