frame

Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Sign In

Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

"make examples" error

Hello. I have newly installed Ubuntu 16.04 LTS.

I am following instructions on this page: https://developer.movidius.com/start

Executed these commands without error

mkdir -p ~/workspace
cd ~/workspace
git clone https://github.com/movidius/ncsdk.git
cd ~/workspace/ncsdk
make install

But when I am trying to run these commands on a new terminal window

cd ~/workspace/ncsdk
make examples

Getting errors below. What should I do?:

 /bin/sh: 1: ./get_ilsvrc_aux.sh: not found
    Makefile:9: recipe for target 'all' failed
    make[5]: *** [all] Error 127
    make[5]: Leaving directory '/home/master/workspace/ncsdk/examples/data/ilsvrc12'
    Makefile:23: recipe for target 'prereqs' failed
    make[4]: *** [prereqs] Error 2
    make[4]: Leaving directory '/home/master/workspace/ncsdk/examples/caffe/GoogLeNet'
    cp: '../../caffe/GoogLeNet/graph' durumlanamadı: Böyle bir dosya ya da dizin yok
    Makefile:9: recipe for target 'googlenet' failed
    make[3]: *** [googlenet] Error 1
    make[3]: Leaving directory '/home/master/workspace/ncsdk/examples/apps/multistick_cpp'
    Makefile:12: recipe for target 'multistick_cpp/.' failed
    make[2]: *** [multistick_cpp/.] Error 2
    make[2]: Leaving directory '/home/master/workspace/ncsdk/examples/apps'
    Makefile:12: recipe for target 'apps/.' failed
    make[1]: *** [apps/.] Error 2
    make[1]: Leaving directory '/home/master/workspace/ncsdk/examples'
    Makefile:57: recipe for target 'examples' failed
    make: *** [examples] Error 2

Comments

  • 20 Comments sorted by Votes Date Added
  • @deepyellow Try running the hello_ncs app (either c or python version) to see if you can ping your NCS device. If your device was detected and no problems were encountered, try making the examples again.

  • @Vlad It seems like your NCS device is definitely being recognized by the system. Do me a favor and see if you can go into each of the NCSDK example directories (like AlexNet) and do a make run. Let me know if this works. Thanks.

  • @gritzhang Can you double check that you don't have a directory inside of '/home/gritzhang/workspace/ncsdk/examples/caffe/GoogLeNet' that is named "graph"?

  • I met the same problem with my Ubuntu 16.04 LTS. I guess it did not find my Movidius NCS stick, which is plugged into my PC. Can someone help us with our problem?

  • @Tome_at_Intel,
    Happy to see you here. I will give you more information about my case:

    First my PC configuration is: Intel-core i5-2400S, @ 2.50GHz × 4, 64bits, USB 2.0, and I installed Ubuntu 16.04 LTS (direct install, no Virtualbox) and Intel Movidius Neural Compute SDK v.1.12.

    Output of running the hello_ncs app (python version) is as follows:
    making run
    python3 hello_ncs.py;
    Hello NCS! Device opened normally.
    Goodbye NCS! Device closed normally.
    NCS device working.

    According to documentation it works properly. What do you think?
    Vlad

  • edited January 19 Vote Up0Vote Down

    @Tome_at_Intel ,
    Examples from both folders caffe and tensorflow do not work. I show you error messages after run make all for two of them:

    Output in the case of AlexNet:

        Error importing caffe 
        making caffemodel
        caffemodel file already exists
        making check
        mvNCCheck -w bvlc_alexnet.caffemodel -i ../../data/images/cat.jpg -s 12 -id 281 deploy.prototxt -M 110 -S 255 -metric top1
        mvNCCheck v02.00, Copyright @ Movidius Ltd 2016
        Error importing caffe
        making compile
        mvNCCompile -w bvlc_alexnet.caffemodel -s 12 deploy.prototxt
        mvNCCompile v02.00, Copyright @ Movidius Ltd 2016                
        Error importing caffe 
        making cpp
        g++ cpp/run.cpp cpp/fp16.c -o cpp/run_cpp -lmvnc
    

    Output in the case of inception_v1:

        [Error 7] Toolkit Error: USB Failure. Code: Error opening device
        mvNCCheck -s 12 output/inception-v1.meta -in=input -on=InceptionV1/Logits/Predictions/Reshape_1 -i ../../data/images/cat.jpg -id 829 -S 2 -M 128 -cs 0,1,2 -metric top1
        mvNCCheck v02.00, Copyright @ Movidius Ltd 2016
        Traceback (most recent call last):
          File "/usr/local/bin/mvNCCheck", line 152, in <module>
            quit_code = check_net(args.network, args.image, args.inputnode, args.outputnode, args.nshaves, args.inputsize, args.weights, args)
          File "/usr/local/bin/mvNCCheck", line 130, in check_net
            net = parse_tensor(args, myriad_config, file_gen=True)
          File "/usr/local/bin/ncsdk/Controllers/TensorFlowParser.py", line 271, in parse_tensor
            channel_swap=arguments.channel_swap)
          File "/usr/local/bin/ncsdk/Controllers/MiscIO.py", line 239, in parse_img
            import skimage.transform
          File "/usr/local/lib/python3.5/dist-packages/skimage/transform/__init__.py", line 1, in <module>
            from .hough_transform import (hough_line, hough_line_peaks,
          File "/usr/local/lib/python3.5/dist-packages/skimage/transform/hough_transform.py", line 3, in <module>
            from .. import measure
          File "/usr/local/lib/python3.5/dist-packages/skimage/measure/__init__.py", line 6, in <module>
            from ._regionprops import regionprops, perimeter
          File "/usr/local/lib/python3.5/dist-packages/skimage/measure/_regionprops.py", line 7, in <module>
            from ._label import label
          File "/usr/local/lib/python3.5/dist-packages/skimage/measure/_label.py", line 1, in <module>
            from ._ccomp import label_cython as clabel
        ImportError: cannot import name 'label_cython'
        Makefile:55: recipe for target 'check' failed
        make: [check] Error 1 (ignored)
        test -f graph || mvNCCompile -s 12 output/inception-v1.meta -in=input -on=InceptionV1/Logits/Predictions/Reshape_1
    

    I managed only to install NC Toolkit successfully and PYTHONPATH variable was also set correctly. After that I could not run ./dlnets.sh or install API archive.

  • @Vlad Try using the Berkeley Caffe and see if you can run an inference using it. You would have to install the Berkeley flavor of Caffe from http://caffe.berkeleyvision.org/install_apt.html. Additionally when installing the NCSDK, you have to edit the ncsdk.conf file in the NCSDK directory and remove the line CAFFE_FLAVOR=ssd.

  • Hi @Tome_at_Intel,
    I managed to install current version of caffe (with python 2.7, CPU version, and OpenCV 3). Then I reinstalled NCSDK and ran successfully caffe and tensorflow examples from NCSDK example directory.
    After that I installed NC Toolkit but again failed to install NC API.

  • @Vlad Make sure you have Python 3. The SDK's Python API is in Python 3 as listed at https://movidius.github.io/ncsdk/py_api/. [EDIT] Apologies. We do have support for Python 2.7 in our API.

  • @Tome_at_Intel
    I meet the same error at 'make examples',so I entry the folder 'app' and run make ,Output:
    {gritzhang@gritzhang-Rev-1-0:~/workspace/ncsdk/examples/apps$ make
    make -C hello_ncs_py/.
    make[1]: Entering directory '/home/gritzhang/workspace/ncsdk/examples/apps/hello_ncs_py'
    nothing to make, use 'make run' to run.
    make[1]: Leaving directory '/home/gritzhang/workspace/ncsdk/examples/apps/hello_ncs_py'
    make -C multistick_cpp/.
    make[1]: Entering directory '/home/gritzhang/workspace/ncsdk/examples/apps/multistick_cpp'

    making googlenet
    (cd ../../caffe/GoogLeNet; make compile; cd ../../apps/multistick_cpp; cp ../../caffe/GoogLeNet/graph ./googlenet.graph;)
    make[2]: Entering directory '/home/gritzhang/workspace/ncsdk/examples/caffe/GoogLeNet'

    making prereqs
    (cd ../../data/ilsvrc12; make)
    make[3]: Entering directory '/home/gritzhang/workspace/ncsdk/examples/data/ilsvrc12'
    make[3]: Leaving directory '/home/gritzhang/workspace/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
    mvNCCompile v02.00, Copyright @ Movidius Ltd 2016

    WARNING: Logging before InitGoogleLogging() is written to STDERR
    F0201 23:45:29.084002 6883 upgrade_proto.cpp:95] Check failed: ReadProtoFromBinaryFile(param_file, param) Failed to parse NetParameter file: bvlc_googlenet.caffemodel
    *** Check failure stack trace: ***
    Makefile:80: recipe for target 'compile' failed
    make[2]: *** [compile] Aborted (core dumped)
    make[2]: Leaving directory '/home/gritzhang/workspace/ncsdk/examples/caffe/GoogLeNet'
    cp: omitting directory '../../caffe/GoogLeNet/graph'
    Makefile:9: recipe for target 'googlenet' failed
    make[1]: *** [googlenet] Error 1
    make[1]: Leaving directory '/home/gritzhang/workspace/ncsdk/examples/apps/multistick_cpp'
    Makefile:12: recipe for target 'multistick_cpp/.' failed
    make: *** [multistick_cpp/.] Error 2
    gritzhang@gritzhang-Rev-1-0:~/workspace/ncsdk/examples/apps$ }


  • Total inference time 48.04

    Generating Profile Report 'output_report.html'...

    making caffemodel
    Downloading caffemodel file
    --2018-02-01 23:49:54-- https://github.com/DeepScale/SqueezeNet/raw/master/SqueezeNet_v1.0/squeezenet_v1.0.caffemodel
    Resolving github.com (github.com)... 192.30.255.113, 192.30.255.112
    Connecting to github.com (github.com)|192.30.255.113|:443... connected.
    HTTP request sent, awaiting response... 302 Found
    Location: https://raw.githubusercontent.com/DeepScale/SqueezeNet/master/SqueezeNet_v1.0/squeezenet_v1.0.caffemodel [following]
    --2018-02-01 23:49:56-- https://raw.githubusercontent.com/DeepScale/SqueezeNet/master/SqueezeNet_v1.0/squeezenet_v1.0.caffemodel
    Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 151.101.196.133
    Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|151.101.196.133|:443... connected.
    HTTP request sent, awaiting response... 200 OK
    Length: 5001403 (4.8M) [application/octet-stream]
    Saving to: ‘./squeezenet_v1.0.caffemodel’

    squeezenet_v1.0.caffemodel 100%[==================================================================>] 4.77M 3.62KB/s in 30m 50s

    Last-modified header missing -- time-stamps turned off.
    2018-02-02 00:20:58 (2.64 KB/s) - ‘./squeezenet_v1.0.caffemodel’ saved [5001403/5001403]

    making check
    mvNCCheck -w squeezenet_v1.0.caffemodel -i ../../data/images/cat.jpg -s 12 -id 281 deploy.prototxt -S 255 -M 120 -metric top1
    mvNCCheck v02.00, Copyright @ Movidius Ltd 2016

    /usr/local/lib/python3.5/dist-packages/skimage/transform/_warps.py:84: UserWarning: The default mode, 'constant', will be changed to 'reflect' in skimage 0.15.
    warn("The default mode, 'constant', will be changed to 'reflect' in "
    /usr/local/bin/ncsdk/Controllers/FileIO.py:52: UserWarning: You are using a large type. Consider reducing your data sizes for best performance
    "Consider reducing your data sizes for best performance\033[0m")
    USB: Transferring Data...
    USB: Myriad Execution Finished
    USB: Myriad Connection Closing.
    USB: Myriad Connection Closed.

    Result: Validation Pass

    Result: (1000, 1, 1)
    1) 281 0.55811
    Expected: (1000, 1, 1)

    1) 281 0.56006

    Obtained values

    Obtained Min Pixel Accuracy: 0.47951177693903446% (max allowed=2%), Pass
    Obtained Average Pixel Accuracy: 0.0019096713003818877% (max allowed=1%), Pass
    Obtained Percentage of wrong values: 0.0% (max allowed=0%), Pass
    Obtained Pixel-wise L2 error: 0.026146444662612452% (max allowed=1%), Pass

    Obtained Global Sum Difference: 0.010695278644561768

    making compile
    mvNCCompile -w squeezenet_v1.0.caffemodel -s 12 deploy.prototxt
    mvNCCompile v02.00, Copyright @ Movidius Ltd 2016

    /usr/local/bin/ncsdk/Controllers/FileIO.py:52: UserWarning: You are using a large type. Consider reducing your data sizes for best performance
    "Consider reducing your data sizes for best performance\033[0m")

    making cpp
    g++ cpp/run.cpp cpp/fp16.c -o cpp/run_cpp -lmvnc
    make[1]: Leaving directory '/home/gritzhang/workspace/ncsdk/examples/caffe/SqueezeNet'
    make -C GoogLeNet/.
    make[1]: Entering directory '/home/gritzhang/workspace/ncsdk/examples/caffe/GoogLeNet'

    making prereqs
    (cd ../../data/ilsvrc12; make)
    make[2]: Entering directory '/home/gritzhang/workspace/ncsdk/examples/data/ilsvrc12'
    make[2]: Leaving directory '/home/gritzhang/workspace/ncsdk/examples/data/ilsvrc12'

    making prototxt
    Prototxt file already exists

    making profile
    mvNCProfile deploy.prototxt -s 12
    mvNCProfile v02.00, Copyright @ Movidius Ltd 2016

    ****** WARNING: using empty weights ******
    Layer inception_3b/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_3b/pool_proj forced to im2col_v2, because its output is used in concat
    Layer inception_4a/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_4a/pool_proj forced to im2col_v2, because its output is used in concat
    Layer inception_4b/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_4b/pool_proj forced to im2col_v2, because its output is used in concat
    Layer inception_4c/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_4c/pool_proj forced to im2col_v2, because its output is used in concat
    Layer inception_4d/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_4d/pool_proj forced to im2col_v2, because its output is used in concat
    Layer inception_4e/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_4e/pool_proj forced to im2col_v2, because its output is used in concat
    Layer inception_5a/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_5a/pool_proj forced to im2col_v2, because its output is used in concat
    Layer inception_5b/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_5b/pool_proj forced to im2col_v2, because its output is used in concat
    Traceback (most recent call last):
    File "/usr/local/bin/mvNCProfile", line 121, in
    profile_net(args.network, args.inputnode, args.outputnode, args.nshaves, args.inputsize, args.weights, args.device_no)
    File "/usr/local/bin/mvNCProfile", line 110, in profile_net
    graph_file.generate()
    File "/usr/local/bin/ncsdk/Models/Blob.py", line 58, in generate
    with open(self.blob_name, 'wb') as f:
    IsADirectoryError: [Errno 21] Is a directory: 'graph'
    Makefile:65: recipe for target 'profile' failed
    make[1]: *** [profile] Error 1
    make[1]: Leaving directory '/home/gritzhang/workspace/ncsdk/examples/caffe/GoogLeNet'
    Makefile:12: recipe for target 'GoogLeNet/.' failed
    make: *** [GoogLeNet/.] Error 2
    gritzhang@gritzhang-Rev-1-0:~/workspace/ncsdk/examples/caffe$

  • @Tome_at_Intel Thanks for your help !I check that directory,there is a foder named "graph",but it empty! What can I do, to resolve my issue ?

  • @gritzhang Please delete the folder named graph inside of '/home/gritzhang/workspace/ncsdk/examples/caffe/GoogLeNet' and try making the example again. It seems that somehow the folder was created and it is causing an issue when the program tries to create a blob from the graph file. Let me know if this fixes your issue.

  • @Tome_at_Intel
    Thanks again! The folder named graph has been deleted!Now ,the issue still be there!In ncsdk ,I run 'make examples' output:
    gritzhang@gritzhang-Rev-1-0:~/workspace/ncsdk$ make examples
    ./install-opencv.sh

    OpenCV already setup for python

    make examples starting.
    (cd examples; make)
    make[1]: Entering directory '/home/gritzhang/workspace/ncsdk/examples'
    make -C apps/.
    make[2]: Entering directory '/home/gritzhang/workspace/ncsdk/examples/apps'
    make -C hello_ncs_py/.
    make[3]: Entering directory '/home/gritzhang/workspace/ncsdk/examples/apps/hello_ncs_py'
    nothing to make, use 'make run' to run.
    make[3]: Leaving directory '/home/gritzhang/workspace/ncsdk/examples/apps/hello_ncs_py'
    make -C multistick_cpp/.
    make[3]: Entering directory '/home/gritzhang/workspace/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/gritzhang/workspace/ncsdk/examples/caffe/GoogLeNet'

    making prereqs
    (cd ../../data/ilsvrc12; make)
    make[5]: Entering directory '/home/gritzhang/workspace/ncsdk/examples/data/ilsvrc12'
    make[5]: Leaving directory '/home/gritzhang/workspace/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
    mvNCCompile v02.00, Copyright @ Movidius Ltd 2016

    WARNING: Logging before InitGoogleLogging() is written to STDERR
    F0207 20:15:39.877845 3132 upgrade_proto.cpp:95] Check failed: ReadProtoFromBinaryFile(param_file, param) Failed to parse NetParameter file: bvlc_googlenet.caffemodel
    *** Check failure stack trace: ***
    Makefile:80: recipe for target 'compile' failed
    make[4]: *** [compile] Aborted (core dumped)
    make[4]: Leaving directory '/home/gritzhang/workspace/ncsdk/examples/caffe/GoogLeNet'
    cp: cannot stat '../../caffe/GoogLeNet/graph': No such file or directory
    Makefile:9: recipe for target 'googlenet' failed
    make[3]: *** [googlenet] Error 1
    make[3]: Leaving directory '/home/gritzhang/workspace/ncsdk/examples/apps/multistick_cpp'
    Makefile:12: recipe for target 'multistick_cpp/.' failed
    make[2]: *** [multistick_cpp/.] Error 2
    make[2]: Leaving directory '/home/gritzhang/workspace/ncsdk/examples/apps'
    Makefile:12: recipe for target 'apps/.' failed
    make[1]: *** [apps/.] Error 2
    make[1]: Leaving directory '/home/gritzhang/workspace/ncsdk/examples'
    Makefile:57: recipe for target 'examples' failed
    make: *** [examples] Error 2
    gritzhang@gritzhang-Rev-1-0:~/workspace/ncsdk$

  • So I entry the folder named "GoogLeNet" inside of'/home/gritzhang/workspace/ncsdk/examples/caffe/GoogLeNet' .Then I run 'make'.
    output :

    gritzhang@gritzhang-Rev-1-0:~/workspace/ncsdk/examples/caffe/GoogLeNet$ make

    making prereqs
    (cd ../../data/ilsvrc12; make)
    make[1]: Entering directory '/home/gritzhang/workspace/ncsdk/examples/data/ilsvrc12'
    make[1]: Leaving directory '/home/gritzhang/workspace/ncsdk/examples/data/ilsvrc12'

    making prototxt
    Prototxt file already exists

    making profile
    mvNCProfile deploy.prototxt -s 12
    mvNCProfile v02.00, Copyright @ Movidius Ltd 2016

    ****** WARNING: using empty weights ******
    Layer inception_3b/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_3b/pool_proj forced to im2col_v2, because its output is used in concat
    Layer inception_4a/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_4a/pool_proj forced to im2col_v2, because its output is used in concat
    Layer inception_4b/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_4b/pool_proj forced to im2col_v2, because its output is used in concat
    Layer inception_4c/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_4c/pool_proj forced to im2col_v2, because its output is used in concat
    Layer inception_4d/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_4d/pool_proj forced to im2col_v2, because its output is used in concat
    Layer inception_4e/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_4e/pool_proj forced to im2col_v2, because its output is used in concat
    Layer inception_5a/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_5a/pool_proj forced to im2col_v2, because its output is used in concat
    Layer inception_5b/1x1 forced to im2col_v2, because its output is used in concat
    Layer inception_5b/pool_proj forced to im2col_v2, because its output is used in concat
    /usr/local/bin/ncsdk/Controllers/FileIO.py:52: UserWarning: You are using a large type. Consider reducing your data sizes for best performance
    "Consider reducing your data sizes for best performance\033[0m")
    USB: Transferring Data...
    Time to Execute : 130.16 ms
    USB: Myriad Execution Finished
    Time to Execute : 108.14 ms
    USB: Myriad Execution Finished
    USB: Myriad Connection Closing.
    USB: Myriad Connection Closed.
    Network Summary

    Detailed Per Layer Profile
    Bandwidth time

    # Name MFLOPs (MB/s) (ms)

    ....

    Total inference time 96.25

    Generating Profile Report 'output_report.html'...

    making caffemodel
    caffemodel file already exists

    making check
    mvNCCheck -w bvlc_googlenet.caffemodel -i ../../data/images/nps_electric_guitar.png -s 12 -id 546 deploy.prototxt -S 255 -M 110 -metric top1
    mvNCCheck v02.00, Copyright @ Movidius Ltd 2016

    WARNING: Logging before InitGoogleLogging() is written to STDERR
    F0207 22:24:43.771184 6833 upgrade_proto.cpp:95] Check failed: ReadProtoFromBinaryFile(param_file, param) Failed to parse NetParameter file: bvlc_googlenet.caffemodel
    *** Check failure stack trace: ***
    Makefile:85: recipe for target 'check' failed
    make: *** [check] Aborted (core dumped)
    gritzhang@gritzhang-Rev-1-0:~/workspace/ncsdk/examples/caffe/GoogLeNet$

  • @Tome_at_Intel
    Now there is a new issue,what is wrong with my computer?Output :
    WARNING: Logging before InitGoogleLogging() is written to STDERR
    F0208 23:37:04.329712 3880 upgrade_proto.cpp:95] Check failed: ReadProtoFromBinaryFile(param_file, param) Failed to parse NetParameter file: bvlc_googlenet.caffemodel
    *** Check failure stack trace: ***
    Makefile:85: recipe for target 'check' failed
    make[3]: *** [check] Aborted (core dumped)
    make[3]: Leaving directory '/home/gritzhang/workspace/ncsdk/examples/caffe/GoogLeNet'
    Makefile:12: recipe for target 'GoogLeNet/.' failed
    make[2]: *** [GoogLeNet/.] Error 2
    make[2]: Leaving directory '/home/gritzhang/workspace/ncsdk/examples/caffe'
    Makefile:12: recipe for target 'caffe/.' failed
    make[1]: *** [caffe/.] Error 2
    make[1]: Leaving directory '/home/gritzhang/workspace/ncsdk/examples'
    Makefile:57: recipe for target 'examples' failed
    make: *** [examples] Error 2
    gritzhang@gritzhang-Rev-1-0:~/workspace/ncsdk$

  • @gritzhang I have not been able to reproduce the issue above and I recommend doing an uninstall and reinstall of the NCSDK. Here are the steps to perform the uninstall and new installation:

    1. Perform an uninstall of the NCSDK by entering the ncsdk root directory and typing in: make uninstall

    2. Afterwards delete the ncsdk folder and its contents

    3. Download a fresh copy of the NCSDK at https://github.com/movidius/ncsdk or do a Git clone https://github.com/movidius/ncsdk to your desired location.

    4. Navigate to the ncsdk folder you just downloaded and type in: make install

    5. After the installation is complete, navigate to ncsdk/examples/caffe/GoogLeNet , plug your NCS in, and type in make run and please let me know if you were successful.

  • @Tome_at_Intel
    follow your instruction. Finaly when I make examples , I did not see the error information! So I try the run.py inside of AlexNet .It is work OK! Thank you very much!
    Output as below:
    gritzhang@gritzhang-Rev-1-0:~/workspace/ncsdk-master/examples/caffe/AlexNet$ ./run.py
    Device 0 Address: 1.1 - VID/PID 03e7:2150
    Starting wait for connect with 2000ms timeout
    Found Address: 1.1 - VID/PID 03e7:2150
    Found EP 0x81 : max packet size is 512 bytes
    Found EP 0x01 : max packet size is 512 bytes
    Found and opened device
    Performing bulk write of 865724 bytes...
    Successfully sent 865724 bytes of data in 215.530091 ms (3.830643 MB/s)
    Boot successful, device address 1.1
    Found Address: 1.1 - VID/PID 03e7:f63b
    done
    Booted 1.1 -> VSC

    ------- predictions --------
    prediction 0 (probability 94.970703125%) is n03272010 electric guitar label index is: 546
    prediction 1 (probability 4.76684570312%) is n02676566 acoustic guitar label index is: 402
    prediction 2 (probability 0.102138519287%) is n02787622 banjo label index is: 420
    prediction 3 (probability 0.0409126281738%) is n04517823 vacuum, vacuum cleaner label index is: 882
    prediction 4 (probability 0.0347137451172%) is n04141076 sax, saxophone label index is: 776
    gritzhang@gritzhang-Rev-1-0:~/workspace/ncsdk-master/examples/caffe/AlexNet$

  • @Tome_at_Intel
    follow your instruction. Finaly when I make examples , I did not see the error information! So I try the run.py inside of AlexNet .It is work OK! Thank you very much!
    Output as below:
    gritzhang@gritzhang-Rev-1-0:~/workspace/ncsdk-master/examples/caffe/AlexNet$ ./run.py
    Device 0 Address: 1.1 - VID/PID 03e7:2150
    Starting wait for connect with 2000ms timeout
    Found Address: 1.1 - VID/PID 03e7:2150
    Found EP 0x81 : max packet size is 512 bytes
    Found EP 0x01 : max packet size is 512 bytes
    Found and opened device
    Performing bulk write of 865724 bytes...
    Successfully sent 865724 bytes of data in 215.530091 ms (3.830643 MB/s)
    Boot successful, device address 1.1
    Found Address: 1.1 - VID/PID 03e7:f63b
    done
    Booted 1.1 -> VSC

    ------- predictions --------
    prediction 0 (probability 94.970703125%) is n03272010 electric guitar label index is: 546
    prediction 1 (probability 4.76684570312%) is n02676566 acoustic guitar label index is: 402
    prediction 2 (probability 0.102138519287%) is n02787622 banjo label index is: 420
    prediction 3 (probability 0.0409126281738%) is n04517823 vacuum, vacuum cleaner label index is: 882
    prediction 4 (probability 0.0347137451172%) is n04141076 sax, saxophone label index is: 776
    gritzhang@gritzhang-Rev-1-0:~/workspace/ncsdk-master/examples/caffe/AlexNet$

  • @gritzhang Glad to hear it's working for you!

Sign In or Register to comment.