mvNCCheck

vlad@vlad-lenovo:~/Downloads/deep-learning-face-detection$ mvNCCheck 1.prototxt -w 1.caffemodel
/usr/lib/python3/dist-packages/scipy/stats/morestats.py:16: DeprecationWarning: Importing from numpy.testing.decorators is deprecated, import from numpy.testing instead.
  from numpy.testing.decorators import setastest
/usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88
  return f(*args, **kwds)
mvNCCheck v02.00, Copyright @ Intel Corporation 2017

Eltwise layer_64_1_sum does not have coefficient. Use the default one
Eltwise layer_128_1_sum does not have coefficient. Use the default one
Eltwise layer_256_1_sum does not have coefficient. Use the default one
Eltwise layer_512_1_sum does not have coefficient. Use the default one
Eliminate layers that have been parsed as NoOp
Fusing Pad and Convolution2D
Fusing Scale after Convolution or FullyConnect
Fusing standalone postOps
Fusing Permute and Flatten
Fusing Eltwise and Relu
Fusing Concat of Concats
Evaluating input and weigths for each hw layer
--------------------------------------
# Network Input tensors ['data#113']
# Network Output tensors ['detection_out#193']
/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
USB: Transferring Data...
/usr/local/lib/python3.5/dist-packages/mvnc/mvncapi.py:418: DeprecationWarning: The binary mode of fromstring is deprecated, as it behaves surprisingly on unicode inputs. Use frombuffer instead
USB: Myriad Execution Finished
USB: Myriad Connection Closing.
USB: Myriad Connection Closed.
Result:  (1, 1, 112, 7)
1) 27 4.984
2) 19 4.97
3) 76 4.883
4) 34 4.867
5) 104 4.855
Expected:  (1, 1, 112, 7)
1) 27 4.98
2) 19 4.97
3) 76 4.883
4) 34 4.87
5) 104 4.855
------------------------------------------------------------
 Obtained values
------------------------------------------------------------
 Obtained Min Pixel Accuracy: 65.7058835029602% (max allowed=2%), Fail
 Obtained Average Pixel Accuracy: 3.691522777080536% (max allowed=1%), Fail
 Obtained Percentage of wrong values: 25.127551020408163% (max allowed=0%), Fail
 Obtained Pixel-wise L2 error: 9.12335379286863% (max allowed=1%), Fail
 Obtained Global Sum Difference: 144.14242553710938
------------------------------------------------------------
vlad@vlad-lenovo:~/Downloads/deep-learning-face-detection$ mvNCCheck 1.prototxt -w 1.caffemodel
/usr/lib/python3/dist-packages/scipy/stats/morestats.py:16: DeprecationWarning: Importing from numpy.testing.decorators is deprecated, import from numpy.testing instead.
  from numpy.testing.decorators import setastest
/usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88
  return f(*args, **kwds)
mvNCCheck v02.00, Copyright @ Intel Corporation 2017

Eltwise layer_64_1_sum does not have coefficient. Use the default one
Eltwise layer_128_1_sum does not have coefficient. Use the default one
Eltwise layer_256_1_sum does not have coefficient. Use the default one
Eltwise layer_512_1_sum does not have coefficient. Use the default one
Eliminate layers that have been parsed as NoOp
Fusing Pad and Convolution2D
Fusing Scale after Convolution or FullyConnect
Fusing standalone postOps
Fusing Permute and Flatten
Fusing Eltwise and Relu
Fusing Concat of Concats
Evaluating input and weigths for each hw layer
--------------------------------------
# Network Input tensors ['data#113']
# Network Output tensors ['detection_out#193']
/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
USB: Transferring Data...
/usr/local/lib/python3.5/dist-packages/mvnc/mvncapi.py:418: DeprecationWarning: The binary mode of fromstring is deprecated, as it behaves surprisingly on unicode inputs. Use frombuffer instead
USB: Myriad Execution Finished
USB: Myriad Connection Closing.
USB: Myriad Connection Closed.
Result:  (1, 1, 114, 7)
1) 27 4.984
2) 19 4.97
3) 76 4.883
4) 34 4.867
5) 104 4.855
Expected:  (1, 1, 114, 7)
1) 27 4.98
2) 19 4.97
3) 76 4.883
4) 34 4.87
5) 104 4.855
------------------------------------------------------------
 Obtained values
------------------------------------------------------------
 Obtained Min Pixel Accuracy: 51.686275005340576% (max allowed=2%), Fail
 Obtained Average Pixel Accuracy: 3.594377264380455% (max allowed=1%), Fail
 Obtained Percentage of wrong values: 27.31829573934837% (max allowed=0%), Fail
 Obtained Pixel-wise L2 error: 8.374855117824673% (max allowed=1%), Fail
 Obtained Global Sum Difference: 142.85543823242188
------------------------------------------------------------
vlad@vlad-lenovo:~/Downloads/deep-learning-face-detection$ mvNCCheck 1.prototxt -w 1.caffemodel
/usr/lib/python3/dist-packages/scipy/stats/morestats.py:16: DeprecationWarning: Importing from numpy.testing.decorators is deprecated, import from numpy.testing instead.
  from numpy.testing.decorators import setastest
/usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88
  return f(*args, **kwds)
mvNCCheck v02.00, Copyright @ Intel Corporation 2017

Eltwise layer_64_1_sum does not have coefficient. Use the default one
Eltwise layer_128_1_sum does not have coefficient. Use the default one
Eltwise layer_256_1_sum does not have coefficient. Use the default one
Eltwise layer_512_1_sum does not have coefficient. Use the default one
Eliminate layers that have been parsed as NoOp
Fusing Pad and Convolution2D
Fusing Scale after Convolution or FullyConnect
Fusing standalone postOps
Fusing Permute and Flatten
Fusing Eltwise and Relu
Fusing Concat of Concats
Evaluating input and weigths for each hw layer
--------------------------------------
# Network Input tensors ['data#113']
# Network Output tensors ['detection_out#193']
/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
USB: Transferring Data...
/usr/local/lib/python3.5/dist-packages/mvnc/mvncapi.py:418: DeprecationWarning: The binary mode of fromstring is deprecated, as it behaves surprisingly on unicode inputs. Use frombuffer instead
USB: Myriad Execution Finished
USB: Myriad Connection Closing.
USB: Myriad Connection Closed.
Result:  (1, 1, 112, 7)
1) 27 4.984
2) 19 4.97
3) 76 4.883
4) 34 4.867
5) 104 4.855
Expected:  (1, 1, 111, 7)
1) 27 4.98
2) 19 4.97
3) 76 4.883
4) 34 4.87
5) 104 4.86
Traceback (most recent call last):
  File "/usr/local/bin/mvNCCheck", line 239, 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 229, in check_net
    ValidationStatistic[extargs.metric], report_filename, args)
  File "/usr/local/bin/ncsdk/Views/Validate.py", line 216, in validation
    compare_matricies(result, expected, filename)
  File "/usr/local/bin/ncsdk/Controllers/Metrics.py", line 185, in compare_matricies
    compare_obj.generate_report(csv, result, expected)
  File "/usr/local/bin/ncsdk/Controllers/Metrics.py", line 116, in generate_report
    obtained_val = self.metrics(result.astype(np.float32), reference)
  File "/usr/local/bin/ncsdk/Controllers/Metrics.py", line 59, in metrics
    diff = np.abs(a - b)
ValueError: operands could not be broadcast together with shapes (1,1,112,7) (1,1,111,7)
vlad@vlad-lenovo:~/Downloads/deep-learning-face-detection$ mvNCCheck 1.prototxt -w 1.caffemodel -s 12 -in data_bn -on detection_out
/usr/lib/python3/dist-packages/scipy/stats/morestats.py:16: DeprecationWarning: Importing from numpy.testing.decorators is deprecated, import from numpy.testing instead.
  from numpy.testing.decorators import setastest
/usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88
  return f(*args, **kwds)
mvNCCheck v02.00, Copyright @ Intel Corporation 2017

Eltwise layer_64_1_sum does not have coefficient. Use the default one
Eltwise layer_128_1_sum does not have coefficient. Use the default one
Eltwise layer_256_1_sum does not have coefficient. Use the default one
Eltwise layer_512_1_sum does not have coefficient. Use the default one
Start Layer: [Layer]: 'data_bn#1', type: <class 'Controllers.Parsers.Parser.Scale.Scale'>
  [Inputs]:
    data#113 [shape:(1, 3, 300, 300), enc_shape:(1, 3, 300, 300), layout: None]
  [Outputs]:
    data_bn#194 [shape:(1, 3, 300, 300), enc_shape:(1, 3, 300, 300), layout: None]
Source:  [Layer]: 'Input#227', type: <class 'Controllers.Parsers.Parser.Input.Input'>
  [Inputs]:
  [Outputs]:
    data#113 [shape:(1, 3, 300, 300), enc_shape:(1, 3, 300, 300), layout: None]
detection_out == detection_out
Eliminate layers that have been parsed as NoOp
Fusing Pad and Convolution2D
Fusing Scale after Convolution or FullyConnect
Fusing standalone postOps
Fusing Permute and Flatten
Fusing Eltwise and Relu
Fusing Concat of Concats
Evaluating input and weigths for each hw layer
--------------------------------------
# Network Input tensors ['data#113']
# Network Output tensors ['detection_out#193']
/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
USB: Transferring Data...
/usr/local/lib/python3.5/dist-packages/mvnc/mvncapi.py:418: DeprecationWarning: The binary mode of fromstring is deprecated, as it behaves surprisingly on unicode inputs. Use frombuffer instead
USB: Myriad Execution Finished
USB: Myriad Connection Closing.
USB: Myriad Connection Closed.
Result:  (1, 1, 112, 7)
1) 27 4.984
2) 19 4.97
3) 83 4.883
4) 34 4.867
5) 104 4.855
Expected:  (1, 1, 111, 7)
1) 27 4.98
2) 19 4.97
3) 76 4.883
4) 34 4.87
5) 104 4.855
Traceback (most recent call last):
  File "/usr/local/bin/mvNCCheck", line 239, 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 229, in check_net
    ValidationStatistic[extargs.metric], report_filename, args)
  File "/usr/local/bin/ncsdk/Views/Validate.py", line 216, in validation
    compare_matricies(result, expected, filename)
  File "/usr/local/bin/ncsdk/Controllers/Metrics.py", line 185, in compare_matricies
    compare_obj.generate_report(csv, result, expected)
  File "/usr/local/bin/ncsdk/Controllers/Metrics.py", line 116, in generate_report
    obtained_val = self.metrics(result.astype(np.float32), reference)
  File "/usr/local/bin/ncsdk/Controllers/Metrics.py", line 59, in metrics
    diff = np.abs(a - b)
ValueError: operands could not be broadcast together with shapes (1,1,112,7) (1,1,111,7)
vlad@vlad-lenovo:~/Downloads/deep-learning-face-detection$