This section contains information regarding the features and updates of the Vitis AI Library 1.0 release. This release is the successor of last Xilinx AI SDK v2.0 release.
The Vitis AI Library is a set of high-level libraries and APIs built for efficient AI inference with DPU. It provides an easy-to-use and unified interface by encapsulating many efficient and high-quality neural networks.
Key Features And Enhancements
This Vitis AI Library release includes the following key features and enhancements:
- Support for new Vitis AI runtime
- The Vitis AI Library is updated to be based on the new Vitis AI Runtime with unified APIs. It also fully supports XRT 2019.2.
- New DPU support
- Besides DPU for Edge devices, the new AI Library will support new cloud based DPU IPs using the same codes (runtime and models for cloud DPU will not be included in this release).
- New TensorFlow model support
- There are 21 TensorFlow models supported, which are from the official TensorFlow repository. The pre-compiled models for edge devices are included, while original models are in the updated Model Zoo.
- New libraries and demos
- There are two new libraries libdpmultitask and libdptfssd which supports multi-task models and SSD models from official TensorFlow repository. There is an updated classification demo that shows the usage of the unified APIs in Vitis AI Library runtime.
- New Open Source Library
- The libdpbase library is open source in this release, which shows how to use unified APIs in Vitis AI runtime to construct high-level libraries.
- New Installation Method
- The host side environment adopts docker image installation, which simplifies and unifies the installation process.
Vitis AI Library 1.0 has
been tested with the following images.
- For existing Xilinx AI SDK v2.0 users, the library interface remains consistent and the application can be directly ported to the new Vitis AI Library.
The following models are supported by this version of the Vitis AI Library.
|28||ssd_pedestrian_pruned_0_97||ADAS Pedestrian Detection|
|30||ssd_adas_pruned_0_95||ADAS Vehicle Detection|
|35||vpgnet_pruned_0_99||ADAS Lane Detection|
|41||face_landmark||Face Detection and Recognition|
The following platforms and EVBs are supported by the Vitis AI Library 1.0.
|Zynq UltraScale+ MPSoC ZU9EG||Xilinx ZCU102||V1.1|
|Zynq® UltraScale+™ MPSoC ZU7EV||Xilinx ZCU104||V1.0|
Because of the complicated configuration for SSD models from the official TensorFlow repository, there is a new libdptfssd library that is different from the original libdpssd library for Caffe models. These two libraries may be merged in future releases.
The following features are deprecated in Vitis AI Library 1.0:
- Removed demos
- The squeezenet and SSD demos have been removed. Because we highly encourage customers to use high-level APIs from AI Library for applications and solutions, we only provide one classification demo in this release to show how to use the low-level unified APIs in Vitis AI run time.
- Removed pre-compiled models
- Six TensorFlow models have been removed in this release but provided in
the previous Xilinx AI v2.0 release, to
keep sync with the updated Model Zoo. Models that are removed can be
replaced by similar models in updated the Model Zoo which come from
TensorFlow slim models. The models are: