rknpu
rknpu copied to clipboard
rockchip-linux
我的板子是RK3399Pro debian系统 1、更新https://github.com/rockchip-linux/rknpu 替换rk3399pro代码仓库下的npu/external/rknpu，然后编译替换之前的npu固件 2、rk3399pro开发板上安装rknn_toolkit-1.7.1-cp37-cp37m-linux_aarch64.whl 3、adb push rknn-toolkit/platform-tools/ntp/linux-aarch64/npu_transfer_proxy 到debian下的/usr/bin 替换旧的 4、运行mobilenet_v1，报一下错误。 done --> Export RKNN model done --> Init runtime environment E Catch exception when init runtime! E Traceback (most...
1. 参考[rknn-toolkit](https://github.com/rockchip-linux/rknn-toolkit/tree/master/platform-tools/update_rk_usb_rule/linux) 并以`sudo`权限执行`update_rk1808_usb_rule.sh`脚本以获取`USB`设备的读写权限，并重启宿主机系统 2. 执行`adb devides`脚本获取rk1808计算棒设备id ```text List of devices attached TM018083200400203 device ``` 3. 执行`ls -ltr /dev/bus/usb/003/001`查看rk1808计算棒设备权限 ```text crw-rw-r-- 1 root root 189, 256 2月 14 10:10 /dev/bus/usb/003/001 ```...
升级1.7.1驱动，并重启开发板后，运行原来的c++代码失败，报 “open librknn_runtime.so fail path=/usr/lib32/librknn_runtime.so”
因为之前在开发板上运行代码出现过推理消耗20s左右时间，看了官方的trouble shoting  想着升级驱动试试看 按照readme进行手动升级，push完成后，重启开发板 发现运行原来的代码，会报错  然后百度发现有人遇到类似的情况 https://blog.csdn.net/u013171226/article/details/121104880 登录开发板，发现现象一致，是libOpenVX.so.1 ibOpenVX.so的软连接失效了，重新建立软连接后，再运行代码正常 ··· ln -snf libOpenVX.so.1.2 libOpenVX.so.1 ln -snf libOpenVX.so.1 libOpenVX.so ···
ret = rknn_outputs_get(ctx, 2, outputs, nullptr) this API need too much time, the same rknn model ,Python need 9ms one imgs ,but C++ API need 20ms C++ API do not...
hi guys. as you may know there is a big difference between yolov3 and yolov5 post process function. I'm looking for an example written for using rknn and **yolov3** ....
`rknn_query`从模型获得的信息： ``` input tensors: index=0 name=x.1_0 n_dims=4 dims=[1 3 640 640] n_elems=1228800 size=1228800 fmt=0 type=3 qnt_type=2 fl=0 zp=0 scale=1.000000 output tensors: index=0 name=permute_at_1747_221_out0_223 n_dims=5 dims=[3 80 80 11] n_elems=211200 size=211200...
宿主机ubuntu18.04系统登录rk1808计算棒后，通过如下指令对固件进行升级 ```shell sudo apt update -y sudo apt upgrade -y sudo reboot ``` rk1808重启后的npu驱动是1.7.0，这个时候宿主机还可以通过ssh远程登录计算棒，同时也可以实现与宿主机实现网络共享。 然后通过如下指令升级计算棒npu驱动 ```shell adb push drivers/linux-aarch64/usr / adb push drivers/npu_ko/galcore.ko /lib/modules/galcore.ko ``` rk1808重启后的npu驱动是1.7.1，但发现宿主机无法通过ssh远程登录计算棒，指示灯也不亮了， 请教一下是什么原因导致的？如何解决？谢谢。
在：postprocess.cc中nms错误： **源代码：** static int nms(int validCount, std::vector &outputLocations, std::vector classIds, std::vector &order, int filterId, float threshold) { for (int i = 0; i < validCount; ++i) { if (order[i] ==...
I tried to run rknpu/rknn/rknn_api/examples/rknn_yolov5_demo on RK3399Pro (Tinker Edge R) with rknpu driver 1.7.1 installed from this repo. However, as noted on README.md, I got following error messages: Failed to...
