Using the AI Library's Post-Processing Library - 3.5 English

Each neural network has different post-processing methods. The xnnpp post-processing library is provided in the Vitis AI Library to facilitate user calls. It supports the following neural network post-processing.

• Classification
• Face detection
• Face landmark detection
• SSD detection
• Pose detection
• Semantic segmentation
• Road line detection
• YOLOv3 detection
• YOLOv2 detection
• Openpose detection
• RefineDet detection
• ReID detection
• Multi-task
• Multi-task V3
• Face recognition
• Plate detection
• Plate recognition
• Medical segmentation
• Medical detection
• Face quality
• Hourglass
• Retinaface
• Centerpoint
• Multitaskv3
• Pointpillars_nuscenes
• Rcan
• vehicleclassification
• ofa_yolo
• efficientdet_d2
• ocr
• textmountain
• YOLOx detection
• YOLOv6 detection

There are two ways to call xnnpp:

• Using an automatic call through vitis::ai::<model>::create to create the task such as vitis::ai::YOLOv3::create("yolov3_bdd", true). After the <model> run is complete, xnnpp is automatically processed. You can modify the parameters through the model configuration file.
• Using a manual call through vitis::ai::DpuTask::create to create the task. Then, create the object of the post-process and run the post-process. Use the following steps. SSD post-processing is used as an example here.
  1. Create a configuration and set the correlating data to control post-process.

     using DPU_conf = vitis::ai::proto::DpuModelParam;
     DPU_conf config;

  2. If it is a Caffe model, set the "is_tf" as FALSE.

     config.set_is_tf(false);

  3. Fill the other parameters.

     fillconfig(config);

  4. Create an object of SSDPostProcess.

     auto input_tensor = task->getInputTensor();
     auto output_tensor = task->getOutputTensor();
     auto ssd = vitis::ai::SSDPostProcess::create(input_tensor, output_tensor,config);

  5. Run the post-process.

     auto results = ssd->ssd_post_process();