Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.

[Error 17] Toolkit Error

idata
Employee
1,107 Views

I want to compile my caffe model based on CNN, however I got following error, I can't keep going more.

 

If you have any solution or you know why mvNCCompile give me following error message, please help me.

 

my environment

 

     

  • host: ubuntu16.04
  •  

  • NCSDK V2
  •  

  • mvNCCompile version: mvNCCompile v02.00, Copyright @ Intel Corporation 2017
  •  

  • NCSDK example(AlexNet and GoogleNet) compile and run: SUCCESS
  •  

 

error message

 

mvNCCompile deploy.prototxt -w model.caffemodel -s 12

 

/usr/local/bin/ncsdk/Controllers/Parsers/TensorFlowParser/Convolution.py:46: SyntaxWarning: assertion is always true, perhaps remove parentheses?

 

assert(False, "Layer type not supported by Convolution: " + obj.type)

 

/usr/local/bin/ncsdk/Controllers/Parsers/Phases.py:322: SyntaxWarning: assertion is always true, perhaps remove parentheses?

 

assert(len(pred) == 1, "Slice not supported to have >1 predecessors")

 

mvNCCompile v02.00, Copyright @ Intel Corporation 2017

 

Eltwise Eltwise1 does not have coefficient. Use the default one

 

Eltwise Eltwise2 does not have coefficient. Use the default one

 

Eltwise Eltwise3 does not have coefficient. Use the default one

 

Eltwise Eltwise4 does not have coefficient. Use the default one

 

Eltwise Eltwise5 does not have coefficient. Use the default one

 

Eltwise Eltwise6 does not have coefficient. Use the default one

 

Eltwise Eltwise7 does not have coefficient. Use the default one

 

Eltwise Eltwise8 does not have coefficient. Use the default one

 

Eltwise Eltwise9 does not have coefficient. Use the default one

 

Fusing Pad and Convolution2D

 

Fusing BatchNorm and Scale after Convolution

 

Replacing BN with Bias&Scale

 

Fusing Permute and Flatten

 

Fusing Eltwise and Relu

 

[Error 17] Toolkit Error: Internal Error: Could not build graph. Missing link: Fusing into a layer with multiple successors is not supported: (Output#140)
0 Kudos
13 Replies
idata
Employee
802 Views

@jongseong.kim Can you provide a link to your model? I'd like to take a closer look at the network. Thanks.

0 Kudos
idata
Employee
802 Views

Hi, Tome

 

Thanks for your support and I uploaded the model and prototxt files in following URL.

 

0 Kudos
idata
Employee
802 Views

@jongseong.kim I was unable to compile the model. I received an error: [Error 17] Toolkit Error: Internal Error: Could not build graph. Missing link: ReLU2. Please double check your model and send it again please. Thanks.

 

Here is the log for my run:

 

$ mvNCCompile deploy.prototxt -w model.caffemodel -s 12 mvNCCompile v02.00, Copyright @ Movidius Ltd 2016 [Error 17] Toolkit Error: Internal Error: Could not build graph. Missing link: ReLU2
0 Kudos
idata
Employee
802 Views

@Tome_at_Intel

 

I think that mvNCCompile version is different with our case.

 

In case of ours, it shows like that "mvNCCompile v02.00, Copyright @ Intel Corporation 2017".

 

And I downloaded the files which I uploaded, I run again via "mvNCCompile deploy.prototxt -w model.caffemodel -s 12".

 

It shows the following log:

 

====================== LOG start ======================

 

mvNCCompile deploy.prototxt -w model.caffemodel -s 12

 

/usr/local/bin/ncsdk/Controllers/Parsers/TensorFlowParser/Convolution.py:46: SyntaxWarning: assertion is always true, perhaps remove parentheses?

 

assert(False, "Layer type not supported by Convolution: " + obj.type)

 

/usr/local/bin/ncsdk/Controllers/Parsers/Phases.py:322: SyntaxWarning: assertion is always true, perhaps remove parentheses?

 

assert(len(pred) == 1, "Slice not supported to have >1 predecessors")

 

mvNCCompile v02.00, Copyright @ Intel Corporation 2017

 

Eltwise Eltwise1 does not have coefficient. Use the default one

 

Eltwise Eltwise2 does not have coefficient. Use the default one

 

Eltwise Eltwise3 does not have coefficient. Use the default one

 

Eltwise Eltwise4 does not have coefficient. Use the default one

 

Eltwise Eltwise5 does not have coefficient. Use the default one

 

Eltwise Eltwise6 does not have coefficient. Use the default one

 

Eltwise Eltwise7 does not have coefficient. Use the default one

 

Eltwise Eltwise8 does not have coefficient. Use the default one

 

Eltwise Eltwise9 does not have coefficient. Use the default one

 

Fusing Pad and Convolution2D

 

Fusing BatchNorm and Scale after Convolution

 

Replacing BN with Bias&Scale

 

Fusing Permute and Flatten

 

Fusing Eltwise and Relu

 

[Error 17] Toolkit Error: Internal Error: Could not build graph. Missing link: Fusing into a layer with multiple successors is not supported: (Output#140)

 

====================== LOG end ======================

 

Please check again.

 

Thanks so much for your support.
0 Kudos
idata
Employee
802 Views

@jongseong.kim There seems to be multiple issues with running this network. I'm getting wrong results right after the first concat. Will look into this some more.

0 Kudos
idata
Employee
802 Views

@Tome_at_Intel

 

Thanks for your reply, and I will wait for your answer to use Movidius that is a very nice.
0 Kudos
idata
Employee
802 Views

@jongseong.kim It seems like NCSDK is having issues with the Eltwise and ReLU layers. Eltwise1 layer seems to have multiple outputs and the NCSDK is having issues processing this with the ReLU5 layer. Looks like a bug on our end. Thanks for reporting this.

0 Kudos
idata
Employee
802 Views

Is there any resolve?

 

I got the exact same problem here.
0 Kudos
idata
Employee
802 Views

Hi @DableUTeeF

 

Have you tried updating to the latest NCSDK 2.10.01?

 

Best Regards,

 

Sahira
0 Kudos
idata
Employee
802 Views

@Sahira_at_Intel

 

I compiled it with version 2 like in instruction but how could I check what exactly version it is?

 

I just clone the repo and compiled it last month though.
0 Kudos
idata
Employee
802 Views

It's very interesting to see that even this page https://ncsforum.movidius.com/discussion/370/intel-ncs-troubleshooting-help-and-guidelines doesn't have how to check the installed software version.

0 Kudos
idata
Employee
802 Views

Hi @DableUTeeF

 

You can navigate to the directory that you initally installed the NCSDK in and see what version you have installed from there!

 

Best Regards,

 

Sahira
0 Kudos
idata
Employee
802 Views

Hi @Sahira_at_Intel

 

It shows only ncsdk2 for git branch in the repo I use, the latest possible in this repo is v2.10.01.01, I think it's already v2.10.

 

There's nothing about version in /usr/local/bin/bcsdk at all.
0 Kudos
Reply