Skip to content

Latest commit

 

History

History
35 lines (27 loc) · 2.96 KB

rknpu2.md

File metadata and controls

35 lines (27 loc) · 2.96 KB

English | 中文

RKNPU2 Model Deployment

Installation Environment

RKNPU2 model export is only supported on x86 Linux platform, please refer to RKNPU2 Model Export Environment Configuration.

Convert ONNX to RKNN

Since the ONNX model cannot directly calculate by calling the NPU, it is necessary to convert the ONNX model to RKNN model. For detailed information, please refer to RKNPU2 Conversion Document.

Models supported for RKNPU2

The following tests are at end-to-end speed, and the test environment is as follows:

  • Device Model: RK3588
  • ARM CPU is tested on ONNX
  • with single-core NPU
Mission Scenario Model Model Version(tested version) ARM CPU/RKNN speed(ms)
Detection Picodet Picodet-s 162/112
Detection RKYOLOV5 YOLOV5-S-Relu(int8) -/57
Detection RKYOLOX - -/-
Detection RKYOLOV7 - -/-
Segmentation Unet Unet-cityscapes -/-
Segmentation PP-HumanSegV2Lite portrait(int8) 133/43
Segmentation PP-HumanSegV2Lite human(int8) 133/43
Face Detection SCRFD SCRFD-2.5G-kps-640(int8) 108/42
Face FaceRecognition InsightFace ms1mv3_arcface_r18(int8) 81/12
Classification ResNet ResNet50_vd -/33

Download Pre-trained library

For convenience, here we provide the 1.0.2 version of FastDeploy.