72、结合无人机进行rk3588oak-lite跟踪目标物体进行识别、跟踪、保持距离

基本思想：

搭建仿真转换模型环境，主要python版本和我下载的rknn2的版本

(rk3588) ubuntu@ubuntu:~/Downloads/rknn-toolkit2-1.5.0/packages$ python3
Python 3.8.0 (default, Nov  6 2019, 21:49:08) 
[GCC 7.3.0] :: Anaconda, Inc. on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import rknn
>>> exit()

截取shape节点，输出模型

其中安装的whl版本

from rknn.api import RKNNONNX_MODEL = '/home/ubuntu/yolov7/runs/train/exp3/weights/best.onnx'
RKNN_MODEL = '/home/ubuntu/yolov7/runs/train/exp3/weights/best.rknn'if __name__ == '__main__':# Create RKNN objectrknn = RKNN(verbose=True)# pre-process configprint('--> config model')rknn.config(mean_values=[[0, 0, 0]], std_values=[[255, 255, 255]],target_platform='rk3588',quantized_dtype='asymmetric_quantized-8')print('done')print('--> Loading model')ret = rknn.load_onnx(model=ONNX_MODEL, outputs=["/model.77/Reshape_2_output_0", "/model.77/Reshape_1_output_0","/model.77/Reshape_output_0"])if ret != 0:print('Load model  failed!')exit(ret)print('done')# Build modelprint('--> Building model')ret = rknn.build(do_quantization=True, dataset='dataset.txt')  # ,pre_compile=Trueif ret != 0:print('Build yolov5s failed!')exit(ret)print('done')# Export rknn modelprint('--> Export RKNN model')ret = rknn.export_rknn(RKNN_MODEL)if ret != 0:print('Export yolov5s.rknn failed!')exit(ret)print('done')rknn.release()

so库也要对应转模型的whl

连接开发板

neardi 用户密码：lindikeji 或 neardi

ubuntu@ubuntu:~$ ssh neardi@192.168.2.29
neardi@192.168.2.29's password: 
Welcome to Ubuntu 20.04.5 LTS (GNU/Linux 5.10.110 aarch64)* Documentation:  https://help.ubuntu.com* Management:     https://landscape.canonical.com* Support:        https://ubuntu.com/advantageThe programs included with the Ubuntu system are free software;
the exact distribution terms for each program are described in the
individual files in /usr/share/doc/*/copyright.Ubuntu comes with ABSOLUTELY NO WARRANTY, to the extent permitted by
applicable law.neardi@LPA3588:~$ sudo apt-get install cmake gcc g++ ffmpeg

测试一下代码

cmakelists.txt

mian.cpp

参考

Ubuntu新手入门 — Neardi Linux 用户手册 v1.1.2 documentation