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

idata · ‎01-30-2019

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")

__ 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

idata · ‎01-30-2019

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