Community
cancel
Showing results for 
Search instead for 
Did you mean: 
idata
Community Manager
500 Views

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

I ran the example of mobilenet V1 as the following instructions:

 

https://github.com/movidius/ncappzoo/tree/master/tensorflow/mobilenets

 

But when I ran 'make', the error happend:

 

meom@meom:~/PycharmProjects/shenfang/NCScodes/ncappzoo/tensorflow/mobilenets$ make

 

TF_SRC_PATH is /home/meom/PycharmProjects/shenfang/NCScodes/ncappzoo/tensorflow/tensorflow

 

Downloading checkpoint files…

 

(mkdir -p model)

 

(cd model; wget -nc http://download.tensorflow.org/models/mobilenet_v1_1.0_224_2017_06_14.tar.gz;)

 

File ‘mobilenet_v1_1.0_224_2017_06_14.tar.gz’ already there; not retrieving.

 

(cd model; tar -xvf mobilenet_v1_1.0_224_2017_06_14.tar.gz;)

 

mobilenet_v1_1.0_224.ckpt.data-00000-of-00001

 

mobilenet_v1_1.0_224.ckpt.meta

 

mobilenet_v1_1.0_224.ckpt.index

 

TF_MODELS_PATH is /home/meom/PycharmProjects/shenfang/NCScodes/ncappzoo/tensorflow/models

 

Exporting GraphDef file…

 

(cd model; python3 /home/meom/PycharmProjects/shenfang/NCScodes/ncappzoo/tensorflow/models/research/slim/export_inference_graph.py \

 

--alsologtostderr \

 

--model_name=mobilenet_v1 \

 

--batch_size=1 \

 

--dataset_name=imagenet \

 

--image_size=224 \

 

--output_file=mobilenet_v1_1.0_224.pb;)

 

/usr/local/lib/python3.5/dist-packages/h5py/init.py:34: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type.

 

from ._conv import register_converters as _register_converters

 

INFO:tensorflow:Scale of 0 disables regularizer.

 

Freezing model for inference…

 

(cd model; python3 /home/meom/PycharmProjects/shenfang/NCScodes/ncappzoo/tensorflow/tensorflow/tensorflow/python/tools/freeze_graph.py \

 

--input_graph=mobilenet_v1_1.0_224.pb \

 

--input_binary=true \

 

--input_checkpoint=mobilenet_v1_1.0_224.ckpt \

 

--output_graph=mobilenet_v1_1.0_224_frozen.pb \

 

--output_node_name=MobilenetV1/Predictions/Reshape_1;)

 

/usr/local/lib/python3.5/dist-packages/h5py/init.py:34: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type.

 

from ._conv import register_converters as _register_converters

 

2019-01-03 10:47:32.615937: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA

 

2019-01-03 10:47:32.698358: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero

 

2019-01-03 10:47:32.698634: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties:

 

name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.62

 

pciBusID: 0000:01:00.0

 

totalMemory: 10.91GiB freeMemory: 10.03GiB

 

2019-01-03 10:47:32.698648: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:01:00.0, compute capability: 6.1)

 

Converted 137 variables to const ops.

 

Profiling the model…

 

(cd model; mvNCProfile -s 12 mobilenet_v1_1.0_224_frozen.pb -in=input -on=MobilenetV1/Predictions/Reshape_1;)

 

mvNCProfile v02.00, Copyright @ Intel Corporation 2017

 

/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/tensor_util.py:509: DeprecationWarning: The binary mode of fromstring is deprecated, as it behaves surprisingly on unicode inputs. Use frombuffer instead

 

shape: (1, 224, 224, 3)

 

res.shape: (1, 1001)

 

TensorFlow output shape: (1, 1, 1001)

 

/usr/local/bin/ncsdk/Controllers/FileIO.py:65: UserWarning: You are using a large type. Consider reducing your data sizes for best performance

 

Blob generated

 

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

 

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

 

Makefile:96: recipe for target 'profile' failed

 

make: *** [profile] Error 255

 

#

 

Please help me to solve this problem. I also cannot run 'make examples' after the installation.

Tags (1)
0 Kudos
7 Replies
idata
Community Manager
156 Views

I found it works in NCS1 but in NCS2, the error happened.

idata
Community Manager
156 Views

I found it works in NCS1 but in NCS2, the error happened.

idata
Community Manager
156 Views

I found it works in NCS1 but in NCS2, the error happened.

idata
Community Manager
156 Views

I found it works in NCS1 but in NCS2, the error happened.

idata
Community Manager
156 Views

Hi @Meow10

 

Thank you for reaching out! Could you please provide additional information about your setup?

 

     

  • Are you using the NCSDK1 or NCSDK2? (version 1.12, 2.08 or older)
  •  

  • Which branch did you clone of the ncappzoo repository? (ncsdk2 or master)
  •  

  • Are you using the original Neural Compute Stick or the Neural Compute Stick 2?
  •  

  • Is the device listed when running lsusb?
  •  

  • Are you running Ubuntu as a virtual machine?
  •  

  • Have you tried connecting the device to a powered USB Hub or a different USB 3.0 port?
  •  

 

Regards,

 

Jesus
idata
Community Manager
156 Views

@Jesus_at_Intel The following are the answers to your questions:

 

     

  1. NCSDK2 2.08.01.02
  2.  

  3. master
  4.  

  5. the Neural Compute Stick 2
  6.  

  7. The device is listed when running Isusb.
  8.  

  9. Ubuntu
  10.  

  11. I haven't tried.

     

    Thank you!
  12.  

idata
Community Manager
156 Views

Hi @Meow10

 

You will need to use the OpenVINO toolkit with the Intel Neural Compute Stick 2 as the NCSDK only support the original Neural Compute Stick.

 

Take a look at the Get Started Guide.

 

Hope this helps!

 

Regards,

 

Jesus
Reply