- Copy the compiled model to the work
place
[Docker]$ cp compiled/resnet50_tf.xmodel ~
- Download the vitis_ai_runtime_r2.5.0_image_video.tar.gzpackage and unzip it in
the docker
container.
[Docker]# cd /workspace/examples [Docker]# wget https://www.xilinx.com/bin/public/openDownload?filename=vitis_ai_runtime_r2.5.0_image_video.tar.gz -O vitis_ai_runtime_r2.5.0_image_video.tar.gz [Docker]# tar -xzvf vitis_ai_runtime_r2.5.0_image_video.tar.gz -C VART
- Environment variable setup in docker
container.
source /workspace/setup/alveo/setup.sh DPUCAHX8H
- Build and Run the resnet50
example.
[Docker] cd /workspace/examples/VART/resnet50 [Docker] bash -x build.sh [Docker] ./resnet50 ~/resnet50_tf.xmodel
The result is shown below.
Note: To improve the user experience, the pre-built models
are already available in Model Zoo. For more information, see Quick Start For Cloud.