dog-qiuqiu / simple-rknn2
The rknn2 API uses the secondary encapsulation of the process, which is easy for everyone to call. It is applicable to rk356x rk3588
☆44Updated 2 years ago
Alternatives and similar repositories for simple-rknn2:
Users that are interested in simple-rknn2 are comparing it to the libraries listed below
- ☆22Updated last year
- linux bsp app & sample for axpi (ax620a)☆34Updated last year
- 在瑞芯微rockchip的AI芯片rv1109上,利用rknn和opencv库,修改了官方yolov3后处理部分代码Bug,交叉编译yolov3-demo示例后可成功上板部署运行。☆33Updated 3 years ago
- 使用NCNN推理框架和ByteTrack目标跟踪框架,对网络、文件流URL进行实时性视频推理,而UI界面则由Qt框架实现☆21Updated 4 months ago
- ffmpeg->rockchip mpp decoding->rknpu rknn->opencv opengl rendering☆37Updated 2 years ago
- 学习yolo算法和rknn框架☆34Updated 3 years ago
- ☆73Updated 10 months ago
- A collection of pre-compiled, state-of-the-art models in the AXera‘s format☆22Updated last year
- ☆63Updated 2 years ago
- yolov10 瑞芯微 rknn 板端 C++部署,使用平台 rk3588。☆64Updated 6 months ago
- yolov9 瑞芯微 rknn 板端 C++部署。☆11Updated 9 months ago
- ☆74Updated 6 months ago
- rknn inference☆44Updated 2 years ago
- Android hand detect and pose estimation by ncnn☆95Updated 3 years ago
- 基于hisi3559a的yolov5☆35Updated 3 years ago
- 使用OpenCV部署低光照图像增强,包 含C++和Python两个版本的程序☆19Updated last year
- yolov8 旋转目标检测部署,瑞芯微RKNN芯片部署、地平线Horizon芯片部署、TensorRT部署☆25Updated 8 months ago
- 🍅 YOLO5Face 2021 with MNN/NCNN/TNN/ONNXRuntime☆55Updated last year
- c++ version of yolov5 segmentation with ncnn☆81Updated 2 years ago
- RKNN模型推理部署模板☆21Updated last year
- gstreamer rtsp client support rockchip and jetson nx for C/C++ Python☆58Updated last year
- 启动多线程, relu激活, 3588的yolo部署, 帧率150以上.☆18Updated last year
- 华为海思hi系列芯片使用的NNIE推理框架教程☆60Updated 9 months ago
- c++ version of yolov7-mask with ncnn☆58Updated 2 years ago
- ☆16Updated 3 years ago
- Lightweight Mat and imread()/imwrite()/imshow()☆82Updated 7 months ago
- ☆77Updated last year
- toybrick rknn multithread c demo frame work☆20Updated 4 years ago
- PyTorch-->ONNX-->RKNN☆118Updated 2 years ago
- yolov5训练转onnx转caffe工程 直接可用☆23Updated 3 years ago