Vitis AI 1.1 release uses container technology to distribute the AI software. The release consists of the following components.
- Tools Container
- Runtime package for MPSoC
- Public Github for Examples (https://github.com/Xilinx/Vitis-AI
- Vitis AI Model Zoo (https://github.com/Xilinx/Vitis-AI/tree/master/AI-Model-Zoo)
Tools Container
The tools container consists of the following:
- Containers distributed via dockerhub: https://hub.docker.com/r/xilinx/vitis-ai/tags
- Unified Compiler flow includes
- Compiler flow for DPUV3 (cloud)
- Compiler flow for DPUV2 (embedded)
- Compiler flow for DPUV1 (cloud)
- Pre-built conda environment to run frameworks:
- conda activate vitis-ai-caffe for Caffe based flows
- conda activate vitis-ai-tensorflow for Tensorflow based flow
- Alveo Runtime tools
Runtime Package for MPSoC Devices
- Container Path URL: https://www.xilinx.com/bin/public/openDownload?filename= vitis_ai_2019.2-r1.1.0.tar.gz
- Contents
- PetaLinux SDK and Cross compiler tool chain
- VAI board packages based on 2019.2 release, including Vitis AI new generation runtime VART.
- Models and overlaybins at https://www.xilinx.com/vitis-ai:
- All public pre-trained models
- All Zynq UltraScale+ MPSoCs overlay bins
- This is not visible to users and it is expected examples requiring pre-trained models have scripts for pulling them.