For U50 Cloud (DPUv3E) - 1.1 English

Vitis AI User Guide (UG1414)

Document ID
Release Date
1.1 English

Before running the samples on the cloud, make sure that the U50 card is installed on the server and the docker system is loaded and running

  1. Download the Vitis™ AI Development Kit..
    $git clone

    Then you will find the Vitis AI Runtime samples under /workspace/vitis_ai/vart/samples in the docker system.

  2. Download the vitis_ai_runtime_r1.1_image_video.tar.gz package and unzip it.
    $tar -xzvf vitis_ai_runtime_r1.1_image_video.tar.gz -C vitis-ai/vart
  3. Compile the sample, assuming resnet50 as an example.
    $cd /workspace/vitis_ai/vart/samples/resnet50
    $bash –x

    When the compilation is complete, the executable resnet50 is generated in the current directory.

  4. Run the sample.
    $./resnet50 model_dir_for_U50

The following table shows the run commands for all the Vitis AI samples in the cloud.

Table 1. Launching Commands for Vitis AI Samples on U50
ID Example Name Command
1 resnet50 ./resnet50 model_dir_for_U50
2 resnet50_mt_py /usr/bin/python3 1 model_dir_for_U50
3 inception_v1_mt_py

/usr/bin/python3 1 model_dir_for_U50

4 pose_detection ./pose_detection video/pose.mp4 model_dir_for_U50
5 video_analysis ./video_analysis video/structure.mp4 model_dir_for_U50
6 adas_detection ./adas_detection video/adas.avi model_dir_for_U50
7 segmentation ./segmentation video/traffic.mp4 model_dir_for_U50