Libraries and Samples

The Vitis™ AI Library contains the following types of neural network libraries based on Caffe framework:

  • Classification
  • Face detection
  • SSD detection
  • Pose detection
  • Semantic segmentation
  • Road line detection
  • YOLOV3 detection
  • YOLOV2 detection
  • Openpose detection
  • RefineDet detection
  • ReID detection
  • Multitask
  • face recognition
  • plate detection
  • plate recognition
  • medical segmentation

Also, the Vitis AI Library contains the following types of neural network libraries based on Tensorflow framework:

  • Classification
  • SSD detection
  • YOLOv3 detection

And, the Vitis AI Library supports the following type of neural network libraries based on Pytorch framework

  • Classification (resnet50, squeezenet and inception_v3)

The related libraries are open source and can be modified as needed. The open source codes are available on the github. You can find them in https://github.com/Xilinx/Vitis-AI.

The Vitis AI Library provides image test samples and video test samples for all the above networks. In addition, the kit provides the corresponding performance test program. For video based testing, we recommend to use raw video for evaluation. Because decoding by software libraries on Arm® CPU may have inconsistent decoding time, which may affect the accuracy of evaluation.

Note: For edge, all the sample programs can only run on the target side, but all the sample programs can be cross compiled on the host side or compiled on the target side.