lindsayshuo Goto Github PK

ax-pipeline

The Pipeline example based on AXear-Pi (AX620A) , AXera-Pi Pro (AX650N) and AXera-Pi Zero (AX620Q) shows the software development skills of ISP, Image Processing, NPU, Encoding, and Display modules, which is helpful for users to develop their own multimedia applications.

csd-rknn

CSD-RkNN: Conic Section Discriminances for Large Scale Reverse k Nearest Neighbors Queries

drawrectangles

DrawRectangles by PyQt5

dtln_rknn

face_landmarks_tensorrtx

Tensorrt implementation of face key points

fatigue_driving_detection

挑战杯rk板端代码，gstreamer mpp硬解码，以及推理模型的rknn部署

fatiguedetectrknn

fatigue detect rknn/onnx model deploy in rk3568 npu（ROCK 3A）

ff-rknn

ff-rknn - Real-time Object Detection with NPU (Rockchip)

hrnet_tensorrt

imageio-binaries

Repo to place the (relatively small) binary libraries

infer_pic

infer_pic

kiwi-rknn

rknn inference

lighttrack-rknn

RKNN version demo of [CVPR21] LightTrack: Finding Lightweight Neural Network for Object Tracking via One-Shot Architecture Search

madnet_rknn

monodepth2_rknn

my_code

open_model_zoo

Pre-trained Deep Learning models and demos (high quality and extremely fast)

opencv-rtsp-motion-detection

Uses OpenCV to access an RTSP H.264 video stream from an IP video camera and performs real-time motion detection and object tracking

paddleocr2rknn

Convert the official paddleocr model to a deployable model on RK1126

plr_rknn

Deploy the plr work on rk3588

rknn-cpp-multithreading

A simple demo of yolov5s running on rk3588/3588s using c++ (about 142 frames). / 一个使用c++在rk3588/3588s上运行的yolov5s简单demo(142帧/s)。

rknn-toolkit2

rknn_face_landmarks_deploy

基于rknn的官方Android项目rknn_yolov5_android_apk_demo进行修改，部署人脸检测模型retinaface和106人脸关键点检测模型，支持实时人脸检测。支持rk356x和rk3588设备npu推理。

rknn_facenet

Demo about facenet in rknn

rknn_model_zoo

rknn_yolov5_3588_bytetrack

rkv2_super

参考董立建代码编写的运行superpoint_rknn的代码

rv1126_rknn_blazeface

A demo show how to inference blazeface model on Rockchip RV1126.

sc-depthv3_rknn

self_models

pt and wts