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.
6495 Discussions

mvNCcheck fails when I was trying to check mobilenet ssd

idata
Employee
1,125 Views

mvNCcheck fails when I was trying to check mobilenet ssd. Is there anyone run mobilenet ssd succcessfully with the latest 1.11 NCSDK release?

 

the command I used: "mvNCCheck MobileNetSSD_deploy.prototxt -w MobileNetSSD_deploy.caffemodel -s 12 -is 300 300 -i /opt/movidius/ncappzoo/data/images/512_Monitor.jpg"

 

the caffemodel and prototxt are from https://github.com/chuanqi305/MobileNet-SSD.

 

the error message is as follows:

 

mvNCCheck v02.00, Copyright @ Movidius Ltd 2016

 

/usr/local/lib/python3.5/dist-packages/scipy/lib/decorator.py:219: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead

 

first = inspect.getargspec(caller)[0][0] # first arg

 

/usr/local/lib/python3.5/dist-packages/scipy/optimize/nonlin.py:1498: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead

 

args, varargs, varkw, defaults = inspect.getargspec(jac.init)

 

/usr/local/lib/python3.5/dist-packages/scipy/stats/_distn_infrastructure.py:611: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead

 

sign = inspect.getargspec(self._stats)

 

/usr/local/lib/python3.5/dist-packages/scipy/stats/_distn_infrastructure.py:648: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead

 

shapes_args = inspect.getargspec(meth)

 

/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: (1, 25, 7)

 

1) 44 nan

 

2) 9 nan

 

3) 23 nan

 

4) 30 nan

 

5) 149 nan

 

Expected: (1, 1, 7)

 

1) 1 20.0

 

2) 2 0.99951

 

3) 5 0.99219

 

4) 6 0.9126

 

5) 3 0.059631

 

/usr/local/bin/ncsdk/Controllers/Metrics.py:75: RuntimeWarning: invalid value encountered in greater

 

diff)) / total_values * 100

 

Obtained values

 

Obtained Min Pixel Accuracy: nan% (max allowed=2%), Fail

 

Obtained Average Pixel Accuracy: nan% (max allowed=1%), Fail

 

Obtained Percentage of wrong values: 1700.0% (max allowed=0%), Fail

 

Obtained Pixel-wise L2 error: nan% (max allowed=1%), Fail

 

Obtained Global Sum Difference: nan
0 Kudos
3 Replies
idata
Employee
757 Views

I tried to run inference with the compiled graph file and get result of length 707, some values are inf or nan.

 

The following is the script I ran:

 

dim=(300, 300)

 

mvnc.SetGlobalOption(mvnc.GlobalOption.LOG_LEVEL, 2)

 

devices = mvnc.EnumerateDevices()

 

device = mvnc.Device(devices[0])

 

device.OpenDevice()

 

network_blob="/home/intel/workspace/ncappzoo/caffe/MobileNetSSD/graph"

 

with open(network_blob, mode="rb") as f:

 

blob = f.read()

 

graph = device.AllocateGraph(blob)

 

img = cv2.imread("/home/intel/workspace/ncappzoo/data/images/cat.jpg")

 

img = cv2.resize(img, dim)

 

img = np.subtract(img, 127.5)

 

img = np.multiply(img, 0.007843)

 

graph.LoadTensor(img.astype(np.float16), 'user object')

 

output, userobj = graph.GetResult()

 

print (len(output))

 

print (output)

 

graph.DeallocateGraph()

 

device.CloseDevice()
0 Kudos
idata
Employee
757 Views

some of the results as follows:

 

2.50000000e+01 8.13125000e+01 5.33203125e+00 4.25312500e+01

 

8.11219215e-05 8.03125000e+01 8.53125000e+01 0.00000000e+00

 

1.00000000e+00 nan -inf -5.27187500e+01

 

inf -5.27187500e+01 0.00000000e+00 2.00000000e+00

 

nan -inf -5.27187500e+01 inf

 

-5.27187500e+01 0.00000000e+00 3.00000000e+00 nan

 

-inf -5.27187500e+01 inf -5.27187500e+01

 

0.00000000e+00 4.00000000e+00 nan -inf

 

-5.27187500e+01 inf -5.27187500e+01 0.00000000e+00

 

5.00000000e+00 nan -inf -5.27187500e+01

 

inf -5.27187500e+01 0.00000000e+00 6.00000000e+00

 

nan -inf -5.27187500e+01 inf

 

-5.27187500e+01 0.00000000e+00 7.00000000e+00 nan

 

-inf -5.27187500e+01 inf -5.27187500e+01

 

0.00000000e+00 8.00000000e+00 nan -inf

 

-5.27187500e+01 inf -5.27187500e+01 0.00000000e+00

 

8.00000000e+00 1.00000000e+00 5.37109375e-03 -2.92968750e-03

 

9.48242188e-01 9.67285156e-01 0.00000000e+00 9.00000000e+00

 

nan -inf -5.27187500e+01 inf

 

-5.27187500e+01 0.00000000e+00 1.00000000e+01 nan

 

-inf -5.27187500e+01 inf -5.27187500e+01

 

0.00000000e+00 1.10000000e+01 nan -inf

 

-5.27187500e+01 inf -5.27187500e+01 0.00000000e+00

 

1.20000000e+01 nan -inf -5.27187500e+01

 

inf -5.27187500e+01 0.00000000e+00 1.30000000e+01

 

nan -inf -5.27187500e+01 inf

 

-5.27187500e+01 0.00000000e+00 1.40000000e+01 nan

 

-inf -5.27187500e+01 inf -5.27187500e+01

 

0.00000000e+00 1.50000000e+01 nan -inf
0 Kudos
idata
Employee
757 Views

I face the same problem. Have you solved it?@xhuan28

0 Kudos
Reply