NCNN模型分析

NCNN模型分析

层类型layer type

层名称layer name

输入

数量input count

输出

数量output count

网络输入层名input blobs

网络

输出层名output blobs

特殊参数layer specific params

 

Convolution

0_22

1

1

data

0_22_bn_leaky

 

 

Convolution 0_22 1 1 data 0_22_bn_leaky -23330=4,3,160,160,8 0=8 1=3 3=2 4=1 5=1 6=216 9=2 -23310=1,1.000000e-01

分析如下:

-23330=4,-23303表明当前参数为数组,数组大小为4,内容为 3,160,160,8

 

operation

param id

param phase

value

Convolution

0

num_output

8

 

1

kernel_w

3

 

2

dilation_w

 
 

3

stride_w

2

 

4

pad_left

1

 

5

bias_term

1

 

6

weight_data_size

216

 

9

activation_type

2

 

-23310=1,1.000000e-01,-23303表明当前参数为数组,数组大小为1,内容为 1.000000e-01

 

参考:

https://github.com/Tencent/ncnn/wiki/param-and-model-file-structure

https://github.com/Tencent/ncnn/wiki/operation-param-weight-table

NCNN模型分析_第1张图片

(图摘自:https://github.com/Tencent/ncnn/wiki/operation-param-weight-table)

  1. 7767517 # param文件版本
  2. 127 147 #层(layer)数量 数据交换结构(blob)数量
  3. Input                    data                     0 1 data -23330=4,3,320,320,3 0=320 1=320 2=3
  4. [input 层类型 层名称 输入数据结构数量 输出数据结构数量]
  5. Convolution              0_22                     1 1 data 0_22_bn_leaky -23330=4,3,160,160,8 0=8 1=3 3=2 4=1 5=1 6=216 9=2 -23310=1,1.000000e-01
  6. Convolution              1_31                     1 1 0_22_bn_leaky 1_31_bn_leaky -23330=4,3,160,160,8 0=8 1=1 5=1 6=64 9=2 -23310=1,1.000000e-01
  7. ConvolutionDepthWise     2_39                     1 1 1_31_bn_leaky 2_39_bn_leaky -23330=4,3,160,160,8 0=8 1=3 4=1 5=1 6=72 7=8 9=2 -23310=1,1.000000e-01
  8. Convolution              3_48                     1 1 2_39_bn_leaky 3_48_bn -23330=4,3,160,160,4 0=4 1=1 5=1 6=32
  9. Split                    3_48_bn_split            1 2 3_48_bn 3_48_bn_split_0 3_48_bn_split_1 -23330=8,3,160,160,4,3,160,160,4
  10. Convolution              4_57                     1 1 3_48_bn_split_0 4_57_bn_leaky -23330=4,3,160,160,8 0=8 1=1 5=1 6=32 9=2 -23310=1,1.000000e-01
  11. ConvolutionDepthWise     5_65                     1 1 4_57_bn_leaky 5_65_bn_leaky -23330=4,3,160,160,8 0=8 1=3 4=1 5=1 6=72 7=8 9=2 -23310=1,1.000000e-01
  12. Convolution              6_74                     1 1 5_65_bn_leaky 6_74_bn -23330=4,3,160,160,4 0=4 1=1 5=1 6=32
  13. Eltwise                  8_86                     2 1 6_74_bn 3_48_bn_split_1 8_86 -23330=4,3,160,160,4 0=1
  14. Convolution              9_90                     1 1 8_86 9_90_bn_leaky -23330=4,3,160,160,24 0=24 1=1 5=1 6=96 9=2 -23310=1,1.000000e-01
  15. ConvolutionDepthWise     10_98                    1 1 9_90_bn_leaky 10_98_bn_leaky -23330=4,3,80,80,24 0=24 1=3 3=2 4=1 5=1 6=216 7=24 9=2 -23310=1,1.000000e-01
  16. Convolution              11_107                   1 1 10_98_bn_leaky 11_107_bn -23330=4,3,80,80,8 0=8 1=1 5=1 6=192
  17. Split                    11_107_bn_split          1 2 11_107_bn 11_107_bn_split_0 11_107_bn_split_1 -23330=8,3,80,80,8,3,80,80,8
  18. Convolution              12_116                   1 1 11_107_bn_split_0 12_116_bn_leaky -23330=4,3,80,80,32 0=32 1=1 5=1 6=256 9=2 -23310=1,1.000000e-01
  19. ConvolutionDepthWise     13_124                   1 1 12_116_bn_leaky 13_124_bn_leaky -23330=4,3,80,80,32 0=32 1=3 4=1 5=1 6=288 7=32 9=2 -23310=1,1.000000e-01
  20. Convolution              14_133                   1 1 13_124_bn_leaky 14_133_bn -23330=4,3,80,80,8 0=8 1=1 5=1 6=256
  21. Eltwise                  16_145                   2 1 14_133_bn 11_107_bn_split_1 16_145 -23330=4,3,80,80,8 0=1
  22. Split                    16_145_split             1 2 16_145 16_145_split_0 16_145_split_1 -23330=8,3,80,80,8,3,80,80,8
  23. Convolution              17_149                   1 1 16_145_split_0 17_149_bn_leaky -23330=4,3,80,80,32 0=32 1=1 5=1 6=256 9=2 -23310=1,1.000000e-01
  24. ConvolutionDepthWise     18_157                   1 1 17_149_bn_leaky 18_157_bn_leaky -23330=4,3,80,80,32 0=32 1=3 4=1 5=1 6=288 7=32 9=2 -23310=1,1.000000e-01
  25. Convolution              19_166                   1 1 18_157_bn_leaky 19_166_bn -23330=4,3,80,80,8 0=8 1=1 5=1 6=256
  26. Eltwise                  21_179                   2 1 19_166_bn 16_145_split_1 21_179 -23330=4,3,80,80,8 0=1
  27. Convolution              22_183                   1 1 21_179 22_183_bn_leaky -23330=4,3,80,80,32 0=32 1=1 5=1 6=256 9=2 -23310=1,1.000000e-01
  28. ConvolutionDepthWise     23_191                   1 1 22_183_bn_leaky 23_191_bn_leaky -23330=4,3,40,40,32 0=32 1=3 3=2 4=1 5=1 6=288 7=32 9=2 -23310=1,1.000000e-01
  29. Convolution              24_200                   1 1 23_191_bn_leaky 24_200_bn -23330=4,3,40,40,8 0=8 1=1 5=1 6=256
  30. Split                    24_200_bn_split          1 2 24_200_bn 24_200_bn_split_0 24_200_bn_split_1 -23330=8,3,40,40,8,3,40,40,8
  31. Convolution              25_209                   1 1 24_200_bn_split_0 25_209_bn_leaky -23330=4,3,40,40,48 0=48 1=1 5=1 6=384 9=2 -23310=1,1.000000e-01
  32. ConvolutionDepthWise     26_217                   1 1 25_209_bn_leaky 26_217_bn_leaky -23330=4,3,40,40,48 0=48 1=3 4=1 5=1 6=432 7=48 9=2 -23310=1,1.000000e-01
  33. Convolution              27_226                   1 1 26_217_bn_leaky 27_226_bn -23330=4,3,40,40,8 0=8 1=1 5=1 6=384
  34. Eltwise                  29_238                   2 1 27_226_bn 24_200_bn_split_1 29_238 -23330=4,3,40,40,8 0=1
  35. Split                    29_238_split             1 2 29_238 29_238_split_0 29_238_split_1 -23330=8,3,40,40,8,3,40,40,8
  36. Convolution              30_242                   1 1 29_238_split_0 30_242_bn_leaky -23330=4,3,40,40,48 0=48 1=1 5=1 6=384 9=2 -23310=1,1.000000e-01
  37. ConvolutionDepthWise     31_250                   1 1 30_242_bn_leaky 31_250_bn_leaky -23330=4,3,40,40,48 0=48 1=3 4=1 5=1 6=432 7=48 9=2 -23310=1,1.000000e-01
  38. Convolution              32_259                   1 1 31_250_bn_leaky 32_259_bn -23330=4,3,40,40,8 0=8 1=1 5=1 6=384
  39. Eltwise                  34_273                   2 1 32_259_bn 29_238_split_1 34_273 -23330=4,3,40,40,8 0=1
  40. Convolution              35_277                   1 1 34_273 35_277_bn_leaky -23330=4,3,40,40,48 0=48 1=1 5=1 6=384 9=2 -23310=1,1.000000e-01
  41. ConvolutionDepthWise     36_285                   1 1 35_277_bn_leaky 36_285_bn_leaky -23330=4,3,40,40,48 0=48 1=3 4=1 5=1 6=432 7=48 9=2 -23310=1,1.000000e-01
  42. Convolution              37_294                   1 1 36_285_bn_leaky 37_294_bn -23330=4,3,40,40,16 0=16 1=1 5=1 6=768
  43. Split                    37_294_bn_split          1 2 37_294_bn 37_294_bn_split_0 37_294_bn_split_1 -23330=8,3,40,40,16,3,40,40,16
  44. Convolution              38_303                   1 1 37_294_bn_split_0 38_303_bn_leaky -23330=4,3,40,40,96 0=96 1=1 5=1 6=1536 9=2 -23310=1,1.000000e-01
  45. ConvolutionDepthWise     39_311                   1 1 38_303_bn_leaky 39_311_bn_leaky -23330=4,3,40,40,96 0=96 1=3 4=1 5=1 6=864 7=96 9=2 -23310=1,1.000000e-01
  46. Convolution              40_320                   1 1 39_311_bn_leaky 40_320_bn -23330=4,3,40,40,16 0=16 1=1 5=1 6=1536
  47. Eltwise                  42_332                   2 1 40_320_bn 37_294_bn_split_1 42_332 -23330=4,3,40,40,16 0=1
  48. Split                    42_332_split             1 2 42_332 42_332_split_0 42_332_split_1 -23330=8,3,40,40,16,3,40,40,16
  49. Convolution              43_336                   1 1 42_332_split_0 43_336_bn_leaky -23330=4,3,40,40,96 0=96 1=1 5=1 6=1536 9=2 -23310=1,1.000000e-01
  50. ConvolutionDepthWise     44_344                   1 1 43_336_bn_leaky 44_344_bn_leaky -23330=4,3,40,40,96 0=96 1=3 4=1 5=1 6=864 7=96 9=2 -23310=1,1.000000e-01
  51. Convolution              45_353                   1 1 44_344_bn_leaky 45_353_bn -23330=4,3,40,40,16 0=16 1=1 5=1 6=1536
  52. Eltwise                  47_365                   2 1 45_353_bn 42_332_split_1 47_365 -23330=4,3,40,40,16 0=1
  53. Split                    47_365_split             1 2 47_365 47_365_split_0 47_365_split_1 -23330=8,3,40,40,16,3,40,40,16
  54. Convolution              48_369                   1 1 47_365_split_0 48_369_bn_leaky -23330=4,3,40,40,96 0=96 1=1 5=1 6=1536 9=2 -23310=1,1.000000e-01
  55. ConvolutionDepthWise     49_377                   1 1 48_369_bn_leaky 49_377_bn_leaky -23330=4,3,40,40,96 0=96 1=3 4=1 5=1 6=864 7=96 9=2 -23310=1,1.000000e-01
  56. Convolution              50_386                   1 1 49_377_bn_leaky 50_386_bn -23330=4,3,40,40,16 0=16 1=1 5=1 6=1536
  57. Eltwise                  52_399                   2 1 50_386_bn 47_365_split_1 52_399 -23330=4,3,40,40,16 0=1
  58. Split                    52_399_split             1 2 52_399 52_399_split_0 52_399_split_1 -23330=8,3,40,40,16,3,40,40,16
  59. Convolution              53_403                   1 1 52_399_split_0 53_403_bn_leaky -23330=4,3,40,40,96 0=96 1=1 5=1 6=1536 9=2 -23310=1,1.000000e-01
  60. ConvolutionDepthWise     54_411                   1 1 53_403_bn_leaky 54_411_bn_leaky -23330=4,3,40,40,96 0=96 1=3 4=1 5=1 6=864 7=96 9=2 -23310=1,1.000000e-01
  61. Convolution              55_420                   1 1 54_411_bn_leaky 55_420_bn -23330=4,3,40,40,16 0=16 1=1 5=1 6=1536
  62. Eltwise                  57_433                   2 1 55_420_bn 52_399_split_1 57_433 -23330=4,3,40,40,16 0=1
  63. Convolution              58_437                   1 1 57_433 58_437_bn_leaky -23330=4,3,40,40,96 0=96 1=1 5=1 6=1536 9=2 -23310=1,1.000000e-01
  64. ConvolutionDepthWise     59_445                   1 1 58_437_bn_leaky 59_445_bn_leaky -23330=4,3,20,20,96 0=96 1=3 3=2 4=1 5=1 6=864 7=96 9=2 -23310=1,1.000000e-01
  65. Convolution              60_454                   1 1 59_445_bn_leaky 60_454_bn -23330=4,3,20,20,24 0=24 1=1 5=1 6=2304
  66. Split                    60_454_bn_split          1 2 60_454_bn 60_454_bn_split_0 60_454_bn_split_1 -23330=8,3,20,20,24,3,20,20,24
  67. Convolution              61_463                   1 1 60_454_bn_split_0 61_463_bn_leaky -23330=4,3,20,20,136 0=136 1=1 5=1 6=3264 9=2 -23310=1,1.000000e-01
  68. ConvolutionDepthWise     62_471                   1 1 61_463_bn_leaky 62_471_bn_leaky -23330=4,3,20,20,136 0=136 1=3 4=1 5=1 6=1224 7=136 9=2 -23310=1,1.000000e-01
  69. Convolution              63_480                   1 1 62_471_bn_leaky 63_480_bn -23330=4,3,20,20,24 0=24 1=1 5=1 6=3264
  70. Eltwise                  65_492                   2 1 63_480_bn 60_454_bn_split_1 65_492 -23330=4,3,20,20,24 0=1
  71. Split                    65_492_split             1 2 65_492 65_492_split_0 65_492_split_1 -23330=8,3,20,20,24,3,20,20,24
  72. Convolution              66_496                   1 1 65_492_split_0 66_496_bn_leaky -23330=4,3,20,20,136 0=136 1=1 5=1 6=3264 9=2 -23310=1,1.000000e-01
  73. ConvolutionDepthWise     67_504                   1 1 66_496_bn_leaky 67_504_bn_leaky -23330=4,3,20,20,136 0=136 1=3 4=1 5=1 6=1224 7=136 9=2 -23310=1,1.000000e-01
  74. Convolution              68_513                   1 1 67_504_bn_leaky 68_513_bn -23330=4,3,20,20,24 0=24 1=1 5=1 6=3264
  75. Eltwise                  70_526                   2 1 68_513_bn 65_492_split_1 70_526 -23330=4,3,20,20,24 0=1
  76. Split                    70_526_split             1 2 70_526 70_526_split_0 70_526_split_1 -23330=8,3,20,20,24,3,20,20,24
  77. Convolution              71_530                   1 1 70_526_split_0 71_530_bn_leaky -23330=4,3,20,20,136 0=136 1=1 5=1 6=3264 9=2 -23310=1,1.000000e-01
  78. ConvolutionDepthWise     72_538                   1 1 71_530_bn_leaky 72_538_bn_leaky -23330=4,3,20,20,136 0=136 1=3 4=1 5=1 6=1224 7=136 9=2 -23310=1,1.000000e-01
  79. Convolution              73_547                   1 1 72_538_bn_leaky 73_547_bn -23330=4,3,20,20,24 0=24 1=1 5=1 6=3264
  80. Eltwise                  75_559                   2 1 73_547_bn 70_526_split_1 75_559 -23330=4,3,20,20,24 0=1
  81. Split                    75_559_split             1 2 75_559 75_559_split_0 75_559_split_1 -23330=8,3,20,20,24,3,20,20,24
  82. Convolution              76_563                   1 1 75_559_split_0 76_563_bn_leaky -23330=4,3,20,20,136 0=136 1=1 5=1 6=3264 9=2 -23310=1,1.000000e-01
  83. ConvolutionDepthWise     77_571                   1 1 76_563_bn_leaky 77_571_bn_leaky -23330=4,3,20,20,136 0=136 1=3 4=1 5=1 6=1224 7=136 9=2 -23310=1,1.000000e-01
  84. Convolution              78_580                   1 1 77_571_bn_leaky 78_580_bn -23330=4,3,20,20,24 0=24 1=1 5=1 6=3264
  85. Eltwise                  80_593                   2 1 78_580_bn 75_559_split_1 80_593 -23330=4,3,20,20,24 0=1
  86. Convolution              81_597                   1 1 80_593 81_597_bn_leaky -23330=4,3,20,20,136 0=136 1=1 5=1 6=3264 9=2 -23310=1,1.000000e-01
  87. Split                    81_597_bn_leaky_split    1 2 81_597_bn_leaky 81_597_bn_leaky_split_0 81_597_bn_leaky_split_1 -23330=8,3,20,20,136,3,20,20,136
  88. ConvolutionDepthWise     82_605                   1 1 81_597_bn_leaky_split_0 82_605_bn_leaky -23330=4,3,10,10,136 0=136 1=3 3=2 4=1 5=1 6=1224 7=136 9=2 -23310=1,1.000000e-01
  89. Convolution              83_615                   1 1 82_605_bn_leaky 83_615_bn -23330=4,3,10,10,48 0=48 1=1 5=1 6=6528
  90. Split                    83_615_bn_split          1 2 83_615_bn 83_615_bn_split_0 83_615_bn_split_1 -23330=8,3,10,10,48,3,10,10,48
  91. Convolution              84_624                   1 1 83_615_bn_split_0 84_624_bn_leaky -23330=4,3,10,10,224 0=224 1=1 5=1 6=10752 9=2 -23310=1,1.000000e-01
  92. ConvolutionDepthWise     85_632                   1 1 84_624_bn_leaky 85_632_bn_leaky -23330=4,3,10,10,224 0=224 1=3 4=1 5=1 6=2016 7=224 9=2 -23310=1,1.000000e-01
  93. Convolution              86_641                   1 1 85_632_bn_leaky 86_641_bn -23330=4,3,10,10,48 0=48 1=1 5=1 6=10752
  94. Eltwise                  88_653                   2 1 86_641_bn 83_615_bn_split_1 88_653 -23330=4,3,10,10,48 0=1
  95. Split                    88_653_split             1 2 88_653 88_653_split_0 88_653_split_1 -23330=8,3,10,10,48,3,10,10,48
  96. Convolution              89_657                   1 1 88_653_split_0 89_657_bn_leaky -23330=4,3,10,10,224 0=224 1=1 5=1 6=10752 9=2 -23310=1,1.000000e-01
  97. ConvolutionDepthWise     90_665                   1 1 89_657_bn_leaky 90_665_bn_leaky -23330=4,3,10,10,224 0=224 1=3 4=1 5=1 6=2016 7=224 9=2 -23310=1,1.000000e-01
  98. Convolution              91_674                   1 1 90_665_bn_leaky 91_674_bn -23330=4,3,10,10,48 0=48 1=1 5=1 6=10752
  99. Eltwise                  93_686                   2 1 91_674_bn 88_653_split_1 93_686 -23330=4,3,10,10,48 0=1
  100. Split                    93_686_split             1 2 93_686 93_686_split_0 93_686_split_1 -23330=8,3,10,10,48,3,10,10,48
  101. Convolution              94_690                   1 1 93_686_split_0 94_690_bn_leaky -23330=4,3,10,10,224 0=224 1=1 5=1 6=10752 9=2 -23310=1,1.000000e-01
  102. ConvolutionDepthWise     95_698                   1 1 94_690_bn_leaky 95_698_bn_leaky -23330=4,3,10,10,224 0=224 1=3 4=1 5=1 6=2016 7=224 9=2 -23310=1,1.000000e-01
  103. Convolution              96_707                   1 1 95_698_bn_leaky 96_707_bn -23330=4,3,10,10,48 0=48 1=1 5=1 6=10752
  104. Eltwise                  98_719                   2 1 96_707_bn 93_686_split_1 98_719 -23330=4,3,10,10,48 0=1
  105. Split                    98_719_split             1 2 98_719 98_719_split_0 98_719_split_1 -23330=8,3,10,10,48,3,10,10,48
  106. Convolution              99_723                   1 1 98_719_split_0 99_723_bn_leaky -23330=4,3,10,10,224 0=224 1=1 5=1 6=10752 9=2 -23310=1,1.000000e-01
  107. ConvolutionDepthWise     100_731                  1 1 99_723_bn_leaky 100_731_bn_leaky -23330=4,3,10,10,224 0=224 1=3 4=1 5=1 6=2016 7=224 9=2 -23310=1,1.000000e-01
  108. Convolution              101_740                  1 1 100_731_bn_leaky 101_740_bn -23330=4,3,10,10,48 0=48 1=1 5=1 6=10752
  109. Eltwise                  103_752                  2 1 101_740_bn 98_719_split_1 103_752 -23330=4,3,10,10,48 0=1
  110. Split                    103_752_split            1 2 103_752 103_752_split_0 103_752_split_1 -23330=8,3,10,10,48,3,10,10,48
  111. Convolution              104_756                  1 1 103_752_split_0 104_756_bn_leaky -23330=4,3,10,10,224 0=224 1=1 5=1 6=10752 9=2 -23310=1,1.000000e-01
  112. ConvolutionDepthWise     105_764                  1 1 104_756_bn_leaky 105_764_bn_leaky -23330=4,3,10,10,224 0=224 1=3 4=1 5=1 6=2016 7=224 9=2 -23310=1,1.000000e-01
  113. Convolution              106_773                  1 1 105_764_bn_leaky 106_773_bn -23330=4,3,10,10,48 0=48 1=1 5=1 6=10752
  114. Eltwise                  108_784                  2 1 106_773_bn 103_752_split_1 108_784 -23330=4,3,10,10,48 0=1
  115. Convolution              109_788                  1 1 108_784 109_788_bn_leaky -23330=4,3,10,10,96 0=96 1=1 5=1 6=4608 9=2 -23310=1,1.000000e-01
  116. Split                    109_788_bn_leaky_split   1 2 109_788_bn_leaky 109_788_bn_leaky_split_0 109_788_bn_leaky_split_1 -23330=8,3,10,10,96,3,10,10,96
  117. ConvolutionDepthWise     110_796                  1 1 109_788_bn_leaky_split_0 110_796_bn_leaky -23330=4,3,10,10,96 0=96 1=5 4=2 5=1 6=2400 7=96 9=2 -23310=1,1.000000e-01
  118. Convolution              111_805                  1 1 110_796_bn_leaky 111_805_bn -23330=4,3,10,10,128 0=128 1=1 5=1 6=12288
  119. ConvolutionDepthWise     112_813                  1 1 111_805_bn 112_813_bn_leaky -23330=4,3,10,10,128 0=128 1=5 4=2 5=1 6=3200 7=128 9=2 -23310=1,1.000000e-01
  120. Convolution              113_822                  1 1 112_813_bn_leaky 113_822_bn -23330=4,3,10,10,128 0=128 1=1 5=1 6=16384
  121. Convolution              114_830                  1 1 113_822_bn 114_830 -23330=4,3,10,10,75 0=75 1=1 5=1 6=9600
  122. Interp                   117_858                  1 1 109_788_bn_leaky_split_1 117_858 -23330=4,3,20,20,96 0=1 1=2.000000e+00 2=2.000000e+00
  123. Concat                   118_861                  2 1 117_858 81_597_bn_leaky_split_1 118_861 -23330=4,3,20,20,232
  124. Convolution              119_864                  1 1 118_861 119_864_bn_leaky -23330=4,3,20,20,96 0=96 1=1 5=1 6=22272 9=2 -23310=1,1.000000e-01
  125. ConvolutionDepthWise     120_872                  1 1 119_864_bn_leaky 120_872_bn_leaky -23330=4,3,20,20,96 0=96 1=5 4=2 5=1 6=2400 7=96 9=2 -23310=1,1.000000e-01
  126. Convolution              121_881                  1 1 120_872_bn_leaky 121_881_bn -23330=4,3,20,20,96 0=96 1=1 5=1 6=9216
  127. ConvolutionDepthWise     122_889                  1 1 121_881_bn 122_889_bn_leaky -23330=4,3,20,20,96 0=96 1=5 4=2 5=1 6=2400 7=96 9=2 -23310=1,1.000000e-01
  128. Convolution              123_898                  1 1 122_889_bn_leaky 123_898_bn -23330=4,3,20,20,96 0=96 1=1 5=1 6=9216
  129. Convolution              124_906                  1 1 123_898_bn 124_906 -23330=4,3,20,20,75 0=75 1=1 5=1 6=7200
  130. Yolov3DetectionOutput    detection_out            2 1 114_830 124_906 output -23330=4,2,6,1045,1 1=3 2=2.500000e-01 -23304=12,2.600000e+01,4.800000e+01,6.700000e+01,8.400000e+01,7.200000e+01,1.750000e+02,1.890000e+02,1.260000e+02,1.370000e+02,2.360000e+02,2.650000e+02,2.590000e+02 -23305=6,1077936128,1082130432,1084227584,0,1065353216,1073741824 -23306=2,3.200000e+01,1.600000e+01  

 

 

你可能感兴趣的:(AI框架,移动端AI,Deep,Learning)