SHARE
TWEET

mvNCCheck

a guest Jun 19th, 2019 71 Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
  1. vlad@vlad-lenovo:~/Downloads/deep-learning-face-detection$ mvNCCheck 1.prototxt -w 1.caffemodel
  2. /usr/lib/python3/dist-packages/scipy/stats/morestats.py:16: DeprecationWarning: Importing from numpy.testing.decorators is deprecated, import from numpy.testing instead.
  3.   from numpy.testing.decorators import setastest
  4. /usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88
  5.   return f(*args, **kwds)
  6. mvNCCheck v02.00, Copyright @ Intel Corporation 2017
  7.  
  8. Eltwise layer_64_1_sum does not have coefficient. Use the default one
  9. Eltwise layer_128_1_sum does not have coefficient. Use the default one
  10. Eltwise layer_256_1_sum does not have coefficient. Use the default one
  11. Eltwise layer_512_1_sum does not have coefficient. Use the default one
  12. Eliminate layers that have been parsed as NoOp
  13. Fusing Pad and Convolution2D
  14. Fusing Scale after Convolution or FullyConnect
  15. Fusing standalone postOps
  16. Fusing Permute and Flatten
  17. Fusing Eltwise and Relu
  18. Fusing Concat of Concats
  19. Evaluating input and weigths for each hw layer
  20. --------------------------------------
  21. # Network Input tensors ['data#113']
  22. # Network Output tensors ['detection_out#193']
  23. /usr/local/bin/ncsdk/Controllers/FileIO.py:65: UserWarning: You are using a large type. Consider reducing your data sizes for best performance
  24. Blob generated
  25. USB: Transferring Data...
  26. /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
  27. USB: Myriad Execution Finished
  28. USB: Myriad Connection Closing.
  29. USB: Myriad Connection Closed.
  30. Result:  (1, 1, 112, 7)
  31. 1) 27 4.984
  32. 2) 19 4.97
  33. 3) 76 4.883
  34. 4) 34 4.867
  35. 5) 104 4.855
  36. Expected:  (1, 1, 112, 7)
  37. 1) 27 4.98
  38. 2) 19 4.97
  39. 3) 76 4.883
  40. 4) 34 4.87
  41. 5) 104 4.855
  42. ------------------------------------------------------------
  43.  Obtained values
  44. ------------------------------------------------------------
  45.  Obtained Min Pixel Accuracy: 65.7058835029602% (max allowed=2%), Fail
  46.  Obtained Average Pixel Accuracy: 3.691522777080536% (max allowed=1%), Fail
  47.  Obtained Percentage of wrong values: 25.127551020408163% (max allowed=0%), Fail
  48.  Obtained Pixel-wise L2 error: 9.12335379286863% (max allowed=1%), Fail
  49.  Obtained Global Sum Difference: 144.14242553710938
  50. ------------------------------------------------------------
  51. vlad@vlad-lenovo:~/Downloads/deep-learning-face-detection$ mvNCCheck 1.prototxt -w 1.caffemodel
  52. /usr/lib/python3/dist-packages/scipy/stats/morestats.py:16: DeprecationWarning: Importing from numpy.testing.decorators is deprecated, import from numpy.testing instead.
  53.   from numpy.testing.decorators import setastest
  54. /usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88
  55.   return f(*args, **kwds)
  56. mvNCCheck v02.00, Copyright @ Intel Corporation 2017
  57.  
  58. Eltwise layer_64_1_sum does not have coefficient. Use the default one
  59. Eltwise layer_128_1_sum does not have coefficient. Use the default one
  60. Eltwise layer_256_1_sum does not have coefficient. Use the default one
  61. Eltwise layer_512_1_sum does not have coefficient. Use the default one
  62. Eliminate layers that have been parsed as NoOp
  63. Fusing Pad and Convolution2D
  64. Fusing Scale after Convolution or FullyConnect
  65. Fusing standalone postOps
  66. Fusing Permute and Flatten
  67. Fusing Eltwise and Relu
  68. Fusing Concat of Concats
  69. Evaluating input and weigths for each hw layer
  70. --------------------------------------
  71. # Network Input tensors ['data#113']
  72. # Network Output tensors ['detection_out#193']
  73. /usr/local/bin/ncsdk/Controllers/FileIO.py:65: UserWarning: You are using a large type. Consider reducing your data sizes for best performance
  74. Blob generated
  75. USB: Transferring Data...
  76. /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
  77. USB: Myriad Execution Finished
  78. USB: Myriad Connection Closing.
  79. USB: Myriad Connection Closed.
  80. Result:  (1, 1, 114, 7)
  81. 1) 27 4.984
  82. 2) 19 4.97
  83. 3) 76 4.883
  84. 4) 34 4.867
  85. 5) 104 4.855
  86. Expected:  (1, 1, 114, 7)
  87. 1) 27 4.98
  88. 2) 19 4.97
  89. 3) 76 4.883
  90. 4) 34 4.87
  91. 5) 104 4.855
  92. ------------------------------------------------------------
  93.  Obtained values
  94. ------------------------------------------------------------
  95.  Obtained Min Pixel Accuracy: 51.686275005340576% (max allowed=2%), Fail
  96.  Obtained Average Pixel Accuracy: 3.594377264380455% (max allowed=1%), Fail
  97.  Obtained Percentage of wrong values: 27.31829573934837% (max allowed=0%), Fail
  98.  Obtained Pixel-wise L2 error: 8.374855117824673% (max allowed=1%), Fail
  99.  Obtained Global Sum Difference: 142.85543823242188
  100. ------------------------------------------------------------
  101. vlad@vlad-lenovo:~/Downloads/deep-learning-face-detection$ mvNCCheck 1.prototxt -w 1.caffemodel
  102. /usr/lib/python3/dist-packages/scipy/stats/morestats.py:16: DeprecationWarning: Importing from numpy.testing.decorators is deprecated, import from numpy.testing instead.
  103.   from numpy.testing.decorators import setastest
  104. /usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88
  105.   return f(*args, **kwds)
  106. mvNCCheck v02.00, Copyright @ Intel Corporation 2017
  107.  
  108. Eltwise layer_64_1_sum does not have coefficient. Use the default one
  109. Eltwise layer_128_1_sum does not have coefficient. Use the default one
  110. Eltwise layer_256_1_sum does not have coefficient. Use the default one
  111. Eltwise layer_512_1_sum does not have coefficient. Use the default one
  112. Eliminate layers that have been parsed as NoOp
  113. Fusing Pad and Convolution2D
  114. Fusing Scale after Convolution or FullyConnect
  115. Fusing standalone postOps
  116. Fusing Permute and Flatten
  117. Fusing Eltwise and Relu
  118. Fusing Concat of Concats
  119. Evaluating input and weigths for each hw layer
  120. --------------------------------------
  121. # Network Input tensors ['data#113']
  122. # Network Output tensors ['detection_out#193']
  123. /usr/local/bin/ncsdk/Controllers/FileIO.py:65: UserWarning: You are using a large type. Consider reducing your data sizes for best performance
  124. Blob generated
  125. USB: Transferring Data...
  126. /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
  127. USB: Myriad Execution Finished
  128. USB: Myriad Connection Closing.
  129. USB: Myriad Connection Closed.
  130. Result:  (1, 1, 112, 7)
  131. 1) 27 4.984
  132. 2) 19 4.97
  133. 3) 76 4.883
  134. 4) 34 4.867
  135. 5) 104 4.855
  136. Expected:  (1, 1, 111, 7)
  137. 1) 27 4.98
  138. 2) 19 4.97
  139. 3) 76 4.883
  140. 4) 34 4.87
  141. 5) 104 4.86
  142. Traceback (most recent call last):
  143.   File "/usr/local/bin/mvNCCheck", line 239, in <module>
  144.     quit_code = check_net(args.network, args.image, args.inputnode, args.outputnode, args.nshaves, args.inputsize, args.weights, args)
  145.   File "/usr/local/bin/mvNCCheck", line 229, in check_net
  146.     ValidationStatistic[extargs.metric], report_filename, args)
  147.   File "/usr/local/bin/ncsdk/Views/Validate.py", line 216, in validation
  148.     compare_matricies(result, expected, filename)
  149.   File "/usr/local/bin/ncsdk/Controllers/Metrics.py", line 185, in compare_matricies
  150.     compare_obj.generate_report(csv, result, expected)
  151.   File "/usr/local/bin/ncsdk/Controllers/Metrics.py", line 116, in generate_report
  152.     obtained_val = self.metrics(result.astype(np.float32), reference)
  153.   File "/usr/local/bin/ncsdk/Controllers/Metrics.py", line 59, in metrics
  154.     diff = np.abs(a - b)
  155. ValueError: operands could not be broadcast together with shapes (1,1,112,7) (1,1,111,7)
  156. vlad@vlad-lenovo:~/Downloads/deep-learning-face-detection$ mvNCCheck 1.prototxt -w 1.caffemodel -s 12 -in data_bn -on detection_out
  157. /usr/lib/python3/dist-packages/scipy/stats/morestats.py:16: DeprecationWarning: Importing from numpy.testing.decorators is deprecated, import from numpy.testing instead.
  158.   from numpy.testing.decorators import setastest
  159. /usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88
  160.   return f(*args, **kwds)
  161. mvNCCheck v02.00, Copyright @ Intel Corporation 2017
  162.  
  163. Eltwise layer_64_1_sum does not have coefficient. Use the default one
  164. Eltwise layer_128_1_sum does not have coefficient. Use the default one
  165. Eltwise layer_256_1_sum does not have coefficient. Use the default one
  166. Eltwise layer_512_1_sum does not have coefficient. Use the default one
  167. Start Layer: [Layer]: 'data_bn#1', type: <class 'Controllers.Parsers.Parser.Scale.Scale'>
  168.   [Inputs]:
  169.     data#113 [shape:(1, 3, 300, 300), enc_shape:(1, 3, 300, 300), layout: None]
  170.   [Outputs]:
  171.     data_bn#194 [shape:(1, 3, 300, 300), enc_shape:(1, 3, 300, 300), layout: None]
  172. Source:  [Layer]: 'Input#227', type: <class 'Controllers.Parsers.Parser.Input.Input'>
  173.   [Inputs]:
  174.   [Outputs]:
  175.     data#113 [shape:(1, 3, 300, 300), enc_shape:(1, 3, 300, 300), layout: None]
  176. detection_out == detection_out
  177. Eliminate layers that have been parsed as NoOp
  178. Fusing Pad and Convolution2D
  179. Fusing Scale after Convolution or FullyConnect
  180. Fusing standalone postOps
  181. Fusing Permute and Flatten
  182. Fusing Eltwise and Relu
  183. Fusing Concat of Concats
  184. Evaluating input and weigths for each hw layer
  185. --------------------------------------
  186. # Network Input tensors ['data#113']
  187. # Network Output tensors ['detection_out#193']
  188. /usr/local/bin/ncsdk/Controllers/FileIO.py:65: UserWarning: You are using a large type. Consider reducing your data sizes for best performance
  189. Blob generated
  190. USB: Transferring Data...
  191. /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
  192. USB: Myriad Execution Finished
  193. USB: Myriad Connection Closing.
  194. USB: Myriad Connection Closed.
  195. Result:  (1, 1, 112, 7)
  196. 1) 27 4.984
  197. 2) 19 4.97
  198. 3) 83 4.883
  199. 4) 34 4.867
  200. 5) 104 4.855
  201. Expected:  (1, 1, 111, 7)
  202. 1) 27 4.98
  203. 2) 19 4.97
  204. 3) 76 4.883
  205. 4) 34 4.87
  206. 5) 104 4.855
  207. Traceback (most recent call last):
  208.   File "/usr/local/bin/mvNCCheck", line 239, in <module>
  209.     quit_code = check_net(args.network, args.image, args.inputnode, args.outputnode, args.nshaves, args.inputsize, args.weights, args)
  210.   File "/usr/local/bin/mvNCCheck", line 229, in check_net
  211.     ValidationStatistic[extargs.metric], report_filename, args)
  212.   File "/usr/local/bin/ncsdk/Views/Validate.py", line 216, in validation
  213.     compare_matricies(result, expected, filename)
  214.   File "/usr/local/bin/ncsdk/Controllers/Metrics.py", line 185, in compare_matricies
  215.     compare_obj.generate_report(csv, result, expected)
  216.   File "/usr/local/bin/ncsdk/Controllers/Metrics.py", line 116, in generate_report
  217.     obtained_val = self.metrics(result.astype(np.float32), reference)
  218.   File "/usr/local/bin/ncsdk/Controllers/Metrics.py", line 59, in metrics
  219.     diff = np.abs(a - b)
  220. ValueError: operands could not be broadcast together with shapes (1,1,112,7) (1,1,111,7)
  221. vlad@vlad-lenovo:~/Downloads/deep-learning-face-detection$
RAW Paste Data
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy. OK, I Understand
 
Top