【RK3588】NPU图像识别例程

例程下载

rk3588例程可以参考firefly
RK3588 NPU Demo

将demo放进RK3588开发板中

使用adb push

```adb push  .\dataDir    /storage/files （在windows的vscode）

#: adb push rknn_ssd_demo /data/local/tmp
rknn_ssd_demo: 1 file pushed, 0 skipped. 162.6 MB/s (35812272 bytes in 0.210s)```

当想往安卓设备端push文件时显示没权限，应执行以下指令：
adb root
adb remount

进入开发板的linux （通过 adb shell）

:/rknn_ssd_demo_Android # chmod 777 rknn_ssd_demo
rk3588_s:/data/local/tmp # ls -l
WARNING: linker: Warning: unable to normalize "./lib" (ignoring)
total 35012
-rwxrwxrwx 1 shell shell 35812272 2022-05-19 06:18 rknn_ssd_demo   查看权限是否已经被修改了，必须为可读可执行

:/rknn_ssd_demo_Android # export LD_LIBRARY_PATH=./lib
:/data/rknn_ssd_demo_Android # ./rknn_ssd_demo model/RK3588/ssd_inception_v2.rknn model/road.bmp

这个在model文件夹中的图片是bus.jpg
所以最后一句需要修改为:/data/rknn_ssd_demo_Android # ./rknn_ssd_demo model/RK3588/ssd_inception_v2.rknn model/bus.jpg根据自己的路径酌情修改

输出结果

rknn_init ...
model input num: 1, output num: 2input tensors:
  index=0, name=Preprocessor/sub:0, n_dims=4, dims=[1, 300, 300, 3], n_elems=270000, size=270000, fmt=NHWC, type=INT8, qnt_type=AFFINE, zp=0, scale=0.007812
output tensors:
  index=0, name=concat:0, n_dims=4, dims=[1, 1917, 1, 4], n_elems=7668, size=7668, fmt=NCHW, type=INT8, qnt_type=AFFINE, zp=53, scale=0.089455
  index=1, name=concat_1:0, n_dims=4, dims=[1, 1917, 91, 1], n_elems=174447, size=174447, fmt=NCHW, type=INT8, qnt_type=AFFINE, zp=53, scale=0.143593
rknn_run
loadLabelName
ssd - loadLabelName ./model/coco_labels_list.txt
loadBoxPriors
person @ (1212460209)0.982374
person @ (110119153195)0.973138
bicycle @ (172163277233)0.973138
person @ (207113258218)0.969119
car @ (148133215170)0.953267
person @ (8313492158)0.639771
person @ (4913358156)0.606060
person @ (96134105162)0.428693

将输出的照片复制到windows上

adb pull ./data/rknn_ssd_demo_Android/out.jpg ./