I meet RKNN_ERR_MODEL_INVALID

[复制链接] · 发表于 2020-2-25 12:44:07

本帖最后由 mellon 于 2020-2-26 10:48 编辑

hello,

I convert Deeplab v3+ algorithm to rknn. rknn Build success, but in the rknn init process, I meet this error:

I [vnn_CreateRKNN:5249]Norm tensor initialize
I [vnn_CreateRKNN:5264]Const tensor initialize
I [vnn_CreateRKNN:5279]Virtual tensor initialize
I [vnn_CreateRKNN:5291]Connection initialize
I [vnn_CreateRKNN:5301]graph io initialize
D [setup_node:368]Setup node id[0] uid[100] op[VARIABLE]
D [print_tensor:136]in(0) : id[ 2] vtl[0] const[1] shape[ 1, 1, 1, 1    ] fmt[f16] qnt[NONE]
D [print_tensor:136]out(0): id[ 299] vtl[1] const[0] shape[ 1, 1, 1, 1    ] fmt[f16] qnt[NONE]
D [setup_node:368]Setup node id[1] uid[105] op[VARIABLE]
D [print_tensor:136]in(0) : id[ 3] vtl[0] const[1] shape[ 1, 1, 1, 1    ] fmt[f16] qnt[NONE]
D [print_tensor:136]out(0): id[ 300] vtl[1] const[0] shape[ 1, 1, 1, 1    ] fmt[f16] qnt[NONE]
D [setup_node:368]Setup node id[2] uid[111] op[VARIABLE]
D [print_tensor:136]in(0) : id[ 4] vtl[0] const[1] shape[ 1, 1, 3       ] fmt[f16] qnt[NONE]
D [print_tensor:136]out(0): id[ 301] vtl[1] const[0] shape[ 1, 1, 3       ] fmt[f16] qnt[NONE]
D [setup_node:368]Setup node id[3] uid[14] op[PERMUTE]
D [print_tensor:136]in(0) : id[ 1] vtl[0] const[0] shape[ 3, 224, 224, 1 ] fmt[f16] qnt[NONE]
D [print_tensor:136]out(0): id[ 302] vtl[1] const[0] shape[ 224, 224, 3, 1 ] fmt[f16] qnt[NONE]
D [setup_node:368]Setup node id[4] uid[11] op[PERMUTE]
D [print_tensor:136]in(0) : id[ 302] vtl[1] const[0] shape[ 224, 224, 3, 1 ] fmt[f16] qnt[NONE]
D [print_tensor:136]out(0): id[ 303] vtl[1] const[0] shape[ 3, 224, 224, 1 ] fmt[f16] qnt[NONE]
D [setup_node:368]Setup node id[5] uid[120] op[RESHAPE]
D [print_tensor:136]in(0) : id[ 303] vtl[1] const[0] shape[ 3, 224, 224, 1 ] fmt[f16] qnt[NONE]
D [print_tensor:136]out(0): id[ 304] vtl[1] const[0] shape[ 3, 224, 224    ] fmt[f16] qnt[NONE]
D [setup_node:368]Setup node id[6] uid[116] op[SUBTRACT]
E [op_check:98]Invalid broadcast for inputs[1] size[3]
E [setup_node:383]Check node[6] SUBTRACT fail
I [remove_client_ops:4942]remove_client_ops num=0
I [remove_client_ops:4953]remove_client_ops finish
Create RKNN model fail!
E Catch exception when init runtime!
E Traceback (most recent call last):
E File "rknn/api/rknn_base.py", line 988, in rknn.api.rknn_base.RKNNBase.init_runtime
E File "rknn/api/rknn_runtime.py", line 320, in rknn.api.rknn_runtime.RKNNRuntime.build_graph
E Exception: RKNN init failed. error code: RKNN_ERR_MODEL_INVALID
Init runtime environment failed

How can i slove this problem? I used rknn-toolkit version 1.3.0, and tensorflow version is 1.14.0. python version is 3.6.

I convert this model. (https://github.com/tensorflow/mo ... /g3doc/model_zoo.md, xception65_coco_voc_trainval)

By any chance, rknn does not support sub operations?

Thank you.

只看该作者 · 发表于 2020-2-26 08:34:59

Thanks for your report. I have sent it to NPU team.
If there is any process, I will inform you in time.

Sub op in tensorflow will be packaged in other sub graph, it is hard to identity the problem without NPU team.
You may take a try about customize op function which was described in document.

只看该作者 · 发表于 2020-2-27 11:01:46

jefferyzhang 发表于 2020-2-26 08:34
Thanks for your report. I have sent it to NPU team.
If there is any process, I will inform you in ti ...

Ok. i will do my best. plz Send me reply as soon as possible.

只看该作者 · 发表于 2020-2-28 16:43:12

本帖最后由 jefferyzhang 于 2020-2-28 17:42 编辑

NPU team need some infomations as below:
Where did you running this model, simulator or device?
If in device, please check NPU driver version.

只看该作者 · 发表于 2020-4-15 23:26:33

本帖最后由 wali 于 2020-4-15 23:28 编辑

D [print_tensor:136]out(0): id[ 195] vtl[1] const[0] shape[ 32, 32, 256, 1   ] fmt[u8 ] qnt[ASM zp=114, scale=0.014985]

D [setup_node:368]Setup node id[58] uid[156] op[RELU]

D [print_tensor:136]in(0) : id[ 193] vtl[1] const[0] shape[ 32, 32, 256, 1   ] fmt[u8 ] qnt[ASM zp=  0, scale=0.007946]

D [print_tensor:136]out(0): id[ 196] vtl[1] const[0] shape[ 32, 32, 256, 1   ] fmt[u8 ] qnt[ASM zp=  0, scale=0.007946]

D [setup_node:368]Setup node id[59] uid[108] op[DECONVOLUTION]

D [print_tensor:136]in(0) : id[ 194] vtl[1] const[0] shape[ 64, 64, 64, 1    ] fmt[u8 ] qnt[ASM zp=  0, scale=0.007091]

D [print_tensor:136]in(1) : id[  50] vtl[0] const[1] shape[ 5, 5, 64, 64     ] fmt[u8 ] qnt[ASM zp=111, scale=0.009331]

D [print_tensor:136]in(2) : id[  51] vtl[0] const[1] shape[ 64               ] fmt[i32] qnt[ASM zp=  0, scale=0.000066]

D [print_tensor:136]out(0): id[ 197] vtl[1] const[0] shape[ 131, 131, 64, 1  ] fmt[u8 ] qnt[ASM zp= 62, scale=0.055957]

D [setup_node:368]Setup node id[60] uid[145] op[CONV2D]

D [print_tensor:136]in(0) : id[ 196] vtl[1] const[0] shape[ 32, 32, 256, 1   ] fmt[u8 ] qnt[ASM zp=  0, scale=0.007946]

D [print_tensor:136]in(1) : id[  52] vtl[0] const[1] shape[ 3, 3, 256, 256   ] fmt[u8 ] qnt[ASM zp=151, scale=0.002047]

D [print_tensor:136]in(2) : id[  53] vtl[0] const[1] shape[ 256              ] fmt[i32] qnt[ASM zp=  0, scale=0.000016]

D [print_tensor:136]out(0): id[ 198] vtl[1] const[0] shape[ 32, 32, 256, 1   ] fmt[u8 ] qnt[ASM zp=143, scale=0.019981]

D [setup_node:368]Setup node id[61] uid[109] op[SLICE]

D [print_tensor:136]in(0) : id[ 197] vtl[1] const[0] shape[ 131, 131, 64, 1  ] fmt[u8 ] qnt[ASM zp= 62, scale=0.055957]

D [print_tensor:136]out(0): id[ 199] vtl[1] const[0] shape[ 64, 128, 128, 4  ] fmt[u8 ] qnt[ASM zp= 62, scale=0.055957]

D [setup_node:368]Setup node id[62] uid[120] op[ADD]

D [print_tensor:136]in(0) : id[ 198] vtl[1] const[0] shape[ 32, 32, 256, 1   ] fmt[u8 ] qnt[ASM zp=143, scale=0.019981]

D [print_tensor:136]in(1) : id[ 195] vtl[1] const[0] shape[ 32, 32, 256, 1   ] fmt[u8 ] qnt[ASM zp=114, scale=0.014985]

D [print_tensor:136]out(0): id[ 200] vtl[1] const[0] shape[ 32, 32, 256, 1   ] fmt[u8 ] qnt[ASM zp=144, scale=0.024428]

D [setup_node:368]Setup node id[63] uid[97] op[ADD]

E [op_check:103]Invalid broadcast for inputs[0] size[64]

E [setup_node:383]Check node[63] ADD fail

Segmentation fault (core dumped)
复制代码

API Version：1.3.0Driver Version ： 1.3.1
在PC上运行遇到了相同的问题，在混合量化自己模型的时候！不混合量化是没问题的！
在RKPro上报以下错误：

I NPUTransfer: Starting NPU Transfer Client, Transfe

r version 1.9.8 (cab3961@2019-12-12T09:54:26)

D NPUTransfer: Transfer spec = local:transfer_proxy

D NPUTransfer: Transfer interface successfully opene

d, fd = 9

E RKNNAPI: rknn_init,  msg_load_ack fail, ack = 1(ACK_FAIL), expect 0(ACK_SUCC)!

E RKNNAPI: ==============================================

E RKNNAPI: RKNN VERSION:

E RKNNAPI:   API: 1.3.0 (c5654ea build: 2019-12-25 12:40:55)

E RKNNAPI:   DRV: 1.3.1 (6ebb4d7 build: 2020-01-02 09:37:58)

E RKNNAPI: ==============================================

D NPUTransfer: Transfer client closed, fd = 9

E Catch exception when init runtime!

E Traceback (most recent call last):

E   File "rknn/api/rknn_base.py", line 988, in rknn.api.rknn_base.RKNNBase.init_runtime

E   File "rknn/api/rknn_runtime.py", line 320, in rknn.api.rknn_runtime.RKNNRuntime.build_graph

E Exception: RKNN init failed. error code: RKNN_ERR_MODEL_INVALID

Init runtime environment failed!
复制代码

只看该作者 · 发表于 2020-7-1 15:07:32

wali 发表于 2020-4-15 23:26
API Version：1.3.0Driver Version ： 1.3.1
在PC上运行遇到了相同的问题，在混合量化自己模型的时候！不 ...

你好，请问你的问题解决了吗？how?

只看该作者 · 发表于 2021-1-6 10:41:45

mellon 发表于 2020-2-27 11:01
Ok. i will do my best. plz Send me reply as soon as possible.

If you have any process,plz inform me of it.It's a great honor to get your help.