问题描述

在rk3588板子上调用官方例子rknn_toolkit_lite2/examples/inference_with_lite/test.py的时候出现如下报错：

--> Load RKNN model
done
--> Init runtime environment
I RKNN: [11:11:11.738] RKNN Runtime Information: librknnrt version: 1.4.0 (a10f100eb@2022-09-09T09:07:14)
I RKNN: [11:11:11.738] RKNN Driver Information: version: 0.8.2
E RKNN: [11:11:11.739] 6, 1
E RKNN: [11:11:11.739] Invalid RKNN model version 6
E RKNN: [11:11:11.739] rknn_init, load model failed!
E Catch exception when init runtime!
E Traceback (most recent call last):
  File "/home/coolpi/miniconda3/envs/rknnlite38/lib/python3.8/site-packages/rknnlite/api/rknn_lite.py", line 148, in init_runtime
    self.rknn_runtime.build_graph(self.rknn_data, self.load_model_in_npu)
  File "rknnlite/api/rknn_runtime.py", line 875, in rknnlite.api.rknn_runtime.RKNNRuntime.build_graph
Exception: RKNN init failed. error code: RKNN_ERR_FAIL

解决方案

下载rknpu2

git clone https://github.com/rockchip-linux/rknpu2

将下面的so文件复制到/usr/lib/下

sudo cp rknpu2/runtime/RK3588/Linux/librknn_api/librknnrt.so /usr/lib/librknnrt.so

此时运行python test.py可以正常运行