API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Feb 20th, 2020
335
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 10.74 KB | None | 0 0
raw download clone embed print report
  1. --------------------------------------------------------------------------------
  2. Environment Summary
  3. --------------------------------------------------------------------------------
  4. PyTorch 1.4.0 compiled w/ CUDA 10.1
  5. Running with Python 3.7 and
  6.  
  7. `pip list` truncated output:
  8. numpy==1.18.1
  9. torch==1.4.0
  10. torchvision==0.5.0
  11. --------------------------------------------------------------------------------
  12. cProfile output
  13. --------------------------------------------------------------------------------
  14. 1138288 function calls (1108000 primitive calls) in 27.004 seconds
  15.  
  16. Ordered by: internal time
  17. List reduced from 6815 to 15 due to restriction <15>
  18.  
  19. ncalls tottime percall cumtime percall filename:lineno(function)
  20. 98 20.098 0.205 20.098 0.205 {method 'to' of 'torch._C._TensorBase' objects}
  21. 5 3.306 0.661 3.306 0.661 {built-in method ctc_loss}
  22. 93 1.078 0.012 1.078 0.012 {method 'cuda' of 'torch._C._TensorBase' objects}
  23. 28 0.434 0.016 0.434 0.016 {method 'uniform_' of 'torch._C._TensorBase' objects}
  24. 1545 0.333 0.000 0.333 0.000 {built-in method numpy.fft._pocketfft_internal.execute}
  25. 160 0.220 0.001 0.707 0.004 /opt/miniconda3/envs/pytorchasr/lib/python3.7/site-packages/librosa/core/spectrum.py:2461(_spectrogram)
  26. 70 0.119 0.002 0.119 0.002 {built-in method conv1d}
  27. 160 0.109 0.001 0.487 0.003 /opt/miniconda3/envs/pytorchasr/lib/python3.7/site-packages/librosa/core/spectrum.py:34(stft)
  28. 1066 0.102 0.000 0.102 0.000 {built-in method marshal.loads}
  29. 160 0.079 0.000 0.108 0.001 /opt/miniconda3/envs/pytorchasr/lib/python3.7/site-packages/librosa/filters.py:112(mel)
  30. 160 0.061 0.000 0.064 0.000 /opt/miniconda3/envs/pytorchasr/lib/python3.7/site-packages/librosa/core/spectrum.py:1507(power_to_db)
  31. 28982 0.031 0.000 0.032 0.000 {built-in method builtins.getattr}
  32. 160 0.028 0.000 0.028 0.000 {built-in method scipy.fft._pocketfft.pypocketfft.dct}
  33. 9777/3967 0.027 0.000 0.434 0.000 {built-in method numpy.core._multiarray_umath.implement_array_function}
  34. 2912/2898 0.027 0.000 0.085 0.000 {built-in method builtins.__build_class__}
  35.  
  36.  
  37. --------------------------------------------------------------------------------
  38. autograd profiler output (CPU mode)
  39. --------------------------------------------------------------------------------
  40. top 15 events sorted by cpu_time_total
  41.  
  42. ------------ --------------- --------------- --------------- --------------- --------------- --------------- --------------- --------------- --------------- -----------------------------------
  43. Name Self CPU total % Self CPU total CPU total % CPU total CPU time avg CUDA total % CUDA total CUDA time avg Number of Calls Input Shapes
  44. ------------ --------------- --------------- --------------- --------------- --------------- --------------- --------------- --------------- --------------- -----------------------------------
  45. to 16.56% 5.489s 16.56% 5.489s 5.489s NaN 0.000us 0.000us 1 []
  46. to 16.29% 5.399s 16.29% 5.399s 5.399s NaN 0.000us 0.000us 1 []
  47. to 16.16% 5.355s 16.16% 5.355s 5.355s NaN 0.000us 0.000us 1 []
  48. to 15.23% 5.048s 15.23% 5.048s 5.048s NaN 0.000us 0.000us 1 []
  49. to 14.94% 4.952s 14.94% 4.952s 4.952s NaN 0.000us 0.000us 1 []
  50. ctc_loss 2.11% 698.115ms 2.11% 698.115ms 698.115ms NaN 0.000us 0.000us 1 []
  51. to 2.10% 696.654ms 2.10% 696.654ms 696.654ms NaN 0.000us 0.000us 1 []
  52. ctc_loss 2.10% 696.523ms 2.10% 696.523ms 696.523ms NaN 0.000us 0.000us 1 []
  53. ctc_loss 2.10% 695.301ms 2.10% 695.301ms 695.301ms NaN 0.000us 0.000us 1 []
  54. to 2.10% 695.000ms 2.10% 695.000ms 695.000ms NaN 0.000us 0.000us 1 []
  55. ctc_loss 2.09% 694.288ms 2.09% 694.288ms 694.288ms NaN 0.000us 0.000us 1 []
  56. to 2.09% 693.801ms 2.09% 693.801ms 693.801ms NaN 0.000us 0.000us 1 []
  57. to 2.09% 692.779ms 2.09% 692.779ms 692.779ms NaN 0.000us 0.000us 1 []
  58. ctc_loss 2.02% 668.966ms 2.02% 668.966ms 668.966ms NaN 0.000us 0.000us 1 []
  59. to 2.01% 667.492ms 2.01% 667.492ms 667.492ms NaN 0.000us 0.000us 1 []
  60. ------------ --------------- --------------- --------------- --------------- --------------- --------------- --------------- --------------- --------------- -----------------------------------
  61. Self CPU time total: 33.142s
  62. CUDA time total: 0.000us
  63.  
  64. --------------------------------------------------------------------------------
  65. autograd profiler output (CUDA mode)
  66. --------------------------------------------------------------------------------
  67. top 15 events sorted by cpu_time_total
  68.  
  69. Because the autograd profiler uses the CUDA event API,
  70. the CUDA time column reports approximately max(cuda_time, cpu_time).
  71. Please ignore this output if your code does not use CUDA.
  72.  
  73. ------------ --------------- --------------- --------------- --------------- --------------- --------------- --------------- --------------- --------------- -----------------------------------
  74. Name Self CPU total % Self CPU total CPU total % CPU total CPU time avg CUDA total % CUDA total CUDA time avg Number of Calls Input Shapes
  75. ------------ --------------- --------------- --------------- --------------- --------------- --------------- --------------- --------------- --------------- -----------------------------------
  76. addcmul_ 18.41% 4.543s 18.41% 4.543s 4.543s 0.03% 2.000us 2.000us 1 []
  77. addcmul_ 18.06% 4.455s 18.06% 4.455s 4.455s 0.03% 2.000us 2.000us 1 []
  78. addcmul_ 17.92% 4.423s 17.92% 4.423s 4.423s 0.05% 4.000us 4.000us 1 []
  79. addcmul_ 16.88% 4.164s 16.88% 4.164s 4.164s 0.03% 2.000us 2.000us 1 []
  80. ctc_loss 2.83% 697.706ms 2.83% 697.706ms 697.706ms 20.85% 1.577ms 1.577ms 1 []
  81. to 2.82% 696.173ms 2.82% 696.173ms 696.173ms 1.11% 84.000us 84.000us 1 []
  82. ctc_loss 2.81% 693.902ms 2.81% 693.902ms 693.902ms 21.00% 1.588ms 1.588ms 1 []
  83. ctc_loss 2.81% 693.869ms 2.81% 693.869ms 693.869ms 17.70% 1.339ms 1.339ms 1 []
  84. to 2.81% 692.557ms 2.81% 692.557ms 692.557ms 0.53% 40.000us 40.000us 1 []
  85. to 2.81% 692.366ms 2.81% 692.366ms 692.366ms 1.14% 86.000us 86.000us 1 []
  86. ctc_loss 2.73% 672.559ms 2.73% 672.559ms 672.559ms 17.27% 1.306ms 1.306ms 1 []
  87. to 2.72% 671.276ms 2.72% 671.276ms 671.276ms 0.50% 38.000us 38.000us 1 []
  88. ctc_loss 2.71% 669.494ms 2.71% 669.494ms 669.494ms 19.23% 1.454ms 1.454ms 1 []
  89. to 2.71% 668.190ms 2.71% 668.190ms 668.190ms 0.50% 38.000us 38.000us 1 []
  90. add_ 0.97% 239.802ms 0.97% 239.802ms 239.802ms 0.03% 2.000us 2.000us 1 []
  91. ------------ --------------- --------------- --------------- --------------- --------------- --------------- --------------- --------------- --------------- -----------------------------------
  92. Self CPU time total: 24.673s
  93. CUDA time total: 7.561ms
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
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
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!