Yolov5s模型build, 设置 pre_compile=True, rknn.init_runtime()报错

模型为Yolov5s来源于官网：https://github.com/ultralytics/yolov5/ matser 分支， 转换的toolkit为rknn-1.7.0

设置 pre-compile=True, 可导出rknn模型文件，但是init_runtime()报错：

I [vnn_CreateRKNN:6025]Virtual tensor initialize

I [vnn_CreateRKNN:6037]Connection initialize

I [vnn_CreateRKNN:6047]graph io initialize

D [setup_node:441]Setup node id[0] uid[0] op[NBG] name[nbg_0]

D [print_tensor:146]in(0) : id[   3] vtl[0] const[0] shape[ 640, 640, 3, 1   ] fmt[f16] qnt[NONE]

D [print_tensor:146]out(0): id[   0] vtl[0] const[0] shape[ 80, 80, 85, 3, 1 ] fmt[u8 ] qnt[ASM zp=210, scale=0.092896]

D [print_tensor:146]out(1): id[   1] vtl[0] const[0] shape[ 40, 40, 85, 3, 1 ] fmt[u8 ] qnt[ASM zp=182, scale=0.086178]

D [print_tensor:146]out(2): id[   2] vtl[0] const[0] shape[ 20, 20, 85, 3, 1 ] fmt[u8 ] qnt[ASM zp=179, scale=0.075776]

D [optimize_node:385]Backward optimize neural network

D [optimize_node:392]Forward optimize neural network

I [compute_node:327]Create vx node

D [compute_node:350]Instance node[0] "NBG" ...

E [compute_node:354]Create node[0] NBG fail

Create rknn graph fail!

Warning: NN VipSram is NULL, but SRAM is enabled!  ##  这是什么警告 ？？

I [remove_client_ops:5508]remove_client_ops num=0

I [remove_client_ops:5519]remove_client_ops finish

Create RKNN model fail, error=-6

E Catch exception when init runtime!

E Traceback (most recent call last):

E   File "rknn/api/rknn_base.py", line 884, in rknn.api.rknn_base.RKNNBase.init_runtime

E   File "rknn/api/rknn_runtime.py", line 341, in rknn.api.rknn_runtime.RKNNRuntime.build_graph

E Exception: RKNN init failed. error code: RKNN_ERR_MODEL_INVALID

Init runtime environment failed

当设置 pre-compile=False，模型load很慢，但结果正确；

我需要设置pre_compile=True， 因为模型load会快很多，哪位大佬知道这个错误是为什么？

这是再PC机器上做的转换

rknn.init_runtime 是必须要在开发板上面进行吗？在PC上只调用init_runtime, 不进行inference是否可行？

自问自答
当 pre_compile=True， 既不能在PC上init_runtime， 也不能 inference.