Community
cancel
Showing results for 
Search instead for 
Did you mean: 
Highlighted
Community Manager
364 Views

[Error 7] Toolkit Error: USB Failure. Code: Error opening device

I have followed all the instruction in setting up the intel compute stick 2. However, when I run the make examples, I keep getting this error.

 

make examples starting.

 

(cd examples; make)

 

make[1]: Entering directory '/home/francis/ncsdk/examples'

 

make -C apps/.

 

make[2]: Entering directory '/home/francis/ncsdk/examples/apps'

 

make -C hello_ncs_py/.

 

make[3]: Entering directory '/home/francis/ncsdk/examples/apps/hello_ncs_py'

 

nothing to make or download for this example, use 'make run' to run the examples.

 

make[3]: Leaving directory '/home/francis/ncsdk/examples/apps/hello_ncs_py'

 

make -C multistick_cpp/.

 

make[3]: Entering directory '/home/francis/ncsdk/examples/apps/multistick_cpp'

 

making googlenet

 

(cd ../../caffe/GoogLeNet; make compile; cd ../../apps/multistick_cpp; cp ../../caffe/GoogLeNet/graph ./googlenet.graph;)

 

make[4]: Entering directory '/home/francis/ncsdk/examples/caffe/GoogLeNet'

 

making prereqs

 

(cd ../../data/ilsvrc12; make)

 

make[5]: Entering directory '/home/francis/ncsdk/examples/data/ilsvrc12'

 

make[5]: Leaving directory '/home/francis/ncsdk/examples/data/ilsvrc12'

 

making prototxt

 

Prototxt file already exists

 

making caffemodel

 

caffemodel file already exists

 

making compile

 

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

 

/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

 

Fusing Pad and Convolution2D

 

Fusing BatchNorm and Scale after Convolution

 

Replacing BN with Bias&Scale

 

Fusing Permute and Flatten

 

Fusing Eltwise and Relu

 

Eliminate layers that have been parsed as NoOp

 

Evaluating input and weigths for each hw layer

 

----------------------

 

Network Input tensors ['data#143']

 

Network Output tensors ['prob#227']

 

Blob generated

 

make[4]: Leaving directory '/home/francis/ncsdk/examples/caffe/GoogLeNet'

 

making squeezenet

 

(cd ../../caffe/SqueezeNet; make compile; cd ../../apps/multistick_cpp; cp ../../caffe/SqueezeNet/graph ./squeezenet.graph;)

 

make[4]: Entering directory '/home/francis/ncsdk/examples/caffe/SqueezeNet'

 

making prereqs

 

(cd ../../data/ilsvrc12; make)

 

make[5]: Entering directory '/home/francis/ncsdk/examples/data/ilsvrc12'

 

make[5]: Leaving directory '/home/francis/ncsdk/examples/data/ilsvrc12'

 

LICENSE file already exists

 

making prototxt

 

Prototxt file already exists

 

making caffemodel

 

caffemodel file already exists

 

making compile

 

mvNCCompile -w squeezenet_v1.0.caffemodel -s 12 deploy.prototxt

 

/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

 

Fusing Pad and Convolution2D

 

Fusing BatchNorm and Scale after Convolution

 

Replacing BN with Bias&Scale

 

Fusing Permute and Flatten

 

Fusing Eltwise and Relu

 

Eliminate layers that have been parsed as NoOp

 

Evaluating input and weigths for each hw layer

 

----------------------

 

Network Input tensors ['data#67']

 

Network Output tensors ['prob#106']

 

Blob generated

 

make[4]: Leaving directory '/home/francis/ncsdk/examples/caffe/SqueezeNet'

 

making multistick_cpp

 

cp googlenet.graph cpp/googlenet.graph;

 

cp squeezenet.graph cpp/squeezenet.graph;

 

g++ cpp/multistick.cpp -o cpp/multistick_cpp -lmvnc

 

Created cpp/multistick_cpp executable

 

make[3]: Leaving directory '/home/francis/ncsdk/examples/apps/multistick_cpp'

 

make -C hello_ncs_cpp/.

 

make[3]: Entering directory '/home/francis/ncsdk/examples/apps/hello_ncs_cpp'

 

making hello_ncs_cpp

 

g++ cpp/hello_ncs.cpp -o cpp/hello_ncs_cpp -lmvnc

 

Created cpp/hello_ncs_cpp executable

 

make[3]: Leaving directory '/home/francis/ncsdk/examples/apps/hello_ncs_cpp'

 

make[2]: Leaving directory '/home/francis/ncsdk/examples/apps'

 

make -C caffe/.

 

make[2]: Entering directory '/home/francis/ncsdk/examples/caffe'

 

make -C AlexNet

 

make[3]: Entering directory '/home/francis/ncsdk/examples/caffe/AlexNet'

 

making prereqs

 

(cd ../../data/ilsvrc12; make)

 

make[4]: Entering directory '/home/francis/ncsdk/examples/data/ilsvrc12'

 

make[4]: Leaving directory '/home/francis/ncsdk/examples/data/ilsvrc12'

 

chmod +x run.py

 

making prototxt

 

Prototxt file already exists

 

making profile

 

mvNCProfile deploy.prototxt -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")

 

mvNCProfile v02.00, Copyright @ Intel Corporation 2017

 

__ WARNING: No Weights found. using filler weights __

 

Fusing Pad and Convolution2D

 

Fusing BatchNorm and Scale after Convolution

 

Replacing BN with Bias&Scale

 

Fusing Permute and Flatten

 

Fusing Eltwise and Relu

 

Eliminate layers that have been parsed as NoOp

 

Evaluating input and weigths for each hw layer

 

----------------------

 

Network Input tensors ['data#24']

 

Network Output tensors ['prob#38']

 

Blob generated

 

W: [ 0] ncDeviceOpen:528 ncDeviceOpen() XLinkBootRemote returned error 3

 

[Error 7] Toolkit Error: USB Failure. Code: Error opening device

 

Makefile:64: recipe for target 'profile' failed

 

make[3]: *** [profile] Error 255

 

make[3]: Leaving directory '/home/francis/ncsdk/examples/caffe/AlexNet'

 

Makefile:12: recipe for target 'AlexNet' failed

 

make[2]: *** [AlexNet] Error 2

 

make[2]: Leaving directory '/home/francis/ncsdk/examples/caffe'

 

Makefile:12: recipe for target 'caffe/.' failed

 

make[1]: *** [caffe/.] Error 2

 

make[1]: Leaving directory '/home/francis/ncsdk/examples'

 

Makefile:57: recipe for target 'examples' failed

 

make: *** [examples] Error 2
0 Kudos
1 Reply
Highlighted
Community Manager
12 Views

Hi @fobiagwu

 

You will need to use the OpenVINO toolkit as the Neural Compute SDK only supports the original Neural Compute Stick.

 

Please take a look at the Get Started Guide to install OpenVINO for the Neural Compute Stick 2.

 

Hope this helps!

 

Regards,

 

Jesus
0 Kudos