1The following <TARGET_PLATFORM> represents RK356X or RK3588 2# Aarch64 Linux Demo 3## Build 4 5modify `GCC_COMPILER` on `build-linux_<TARGET_PLATFORM>.sh` for target platform, 6 7then execute 8 9``` 10./build-linux_<TARGET_PLATFORM>.sh 11``` 12 13## Install 14 15Copy install/rknn_common_test_Linux to the devices under /userdata/. 16 17- If you use rockchip's evb board, you can use the following way: 18 19Connect device and push the program and rknn model to `/userdata` 20 21``` 22adb push install/rknn_common_test_Linux /userdata/ 23``` 24 25- If your board has sshd service, you can use scp or other methods to copy the program and rknn model to the board. 26 27## Run 28 29``` 30adb shell 31cd /userdata/rknn_common_test_Linux/ 32``` 33 34``` 35export LD_LIBRARY_PATH=./lib 36./rknn_common_test model/<TARGET_PLATFORM>/mobilenet_v1.rknn model/dog_224x224.jpg 37``` 38 39# Android Demo 40## Build 41 42modify `ANDROID_NDK_PATH` on `build-android_<TARGET_PLATFORM>.sh` for target platform, then execute 43 44``` 45./build-android_<TARGET_PLATFORM>.sh 46``` 47 48## Install 49 50connect device and push build output into `/data` 51 52``` 53adb push install/rknn_common_test_Android /data/ 54``` 55 56## Run 57 58``` 59adb shell 60cd /data/rknn_common_test_Android/ 61``` 62 63``` 64export LD_LIBRARY_PATH=./lib 65./rknn_common_test model/<TARGET_PLATFORM>/mobilenet_v1.rknn model/dog_224x224.jpg 66``` 67
