[关闭]
@betasy 2017-09-03T02:41:59.000000Z 字数 11179 阅读 952

main network structures

deep-learning

VGG16: Top-5 error 9.62, Top-1 error 28.41

  1. VGG (
  2.   (features): Sequential (
  3.     (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  4.     (1): ReLU (inplace)
  5.     (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  6.     (3): ReLU (inplace)
  7.     (4): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  8.     (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  9.     (6): ReLU (inplace)
  10.     (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  11.     (8): ReLU (inplace)
  12.     (9): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  13.     (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  14.     (11): ReLU (inplace)
  15.     (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  16.     (13): ReLU (inplace)
  17.     (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  18.     (15): ReLU (inplace)
  19.     (16): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  20.     (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  21.     (18): ReLU (inplace)
  22.     (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  23.     (20): ReLU (inplace)
  24.     (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  25.     (22): ReLU (inplace)
  26.     (23): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  27.     (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  28.     (25): ReLU (inplace)
  29.     (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  30.     (27): ReLU (inplace)
  31.     (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  32.     (29): ReLU (inplace)
  33.     (30): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  34.   )
  35.   (classifier): Sequential (
  36.     (0): Linear (25088 -> 4096)
  37.     (1): ReLU (inplace)
  38.     (2): Dropout (p = 0.5)
  39.     (3): Linear (4096 -> 4096)
  40.     (4): ReLU (inplace)
  41.     (5): Dropout (p = 0.5)
  42.     (6): Linear (4096 -> 1000)
  43.   )
  44. )

VGG13 with batch normalization: Top-5 error 10.75, Top-1 error 30.07

  1. VGG (
  2.   (features): Sequential (
  3.     (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  4.     (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
  5.     (2): ReLU (inplace)
  6.     (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  7.     (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
  8.     (5): ReLU (inplace)
  9.     (6): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  10.     (7): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  11.     (8): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
  12.     (9): ReLU (inplace)
  13.     (10): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  14.     (11): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
  15.     (12): ReLU (inplace)
  16.     (13): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  17.     (14): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  18.     (15): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  19.     (16): ReLU (inplace)
  20.     (17): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  21.     (18): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  22.     (19): ReLU (inplace)
  23.     (20): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  24.     (21): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  25.     (22): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
  26.     (23): ReLU (inplace)
  27.     (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  28.     (25): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
  29.     (26): ReLU (inplace)
  30.     (27): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  31.     (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  32.     (29): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
  33.     (30): ReLU (inplace)
  34.     (31): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  35.     (32): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
  36.     (33): ReLU (inplace)
  37.     (34): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  38.   )
  39.   (classifier): Sequential (
  40.     (0): Linear (25088 -> 4096)
  41.     (1): ReLU (inplace)
  42.     (2): Dropout (p = 0.5)
  43.     (3): Linear (4096 -> 4096)
  44.     (4): ReLU (inplace)
  45.     (5): Dropout (p = 0.5)
  46.     (6): Linear (4096 -> 1000)
  47.   )
  48. )

Resnet50: Top-5 error 7.13, Top-1 error 28.15

  1. ResNet (
  2.   (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
  3.   (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
  4.   (relu): ReLU (inplace)
  5.   (maxpool): MaxPool2d (size=(3, 3), stride=(2, 2), padding=(1, 1), dilation=(1, 1))
  6.   (layer1): Sequential (
  7.     (0): Bottleneck (
  8.       (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
  9.       (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
  10.       (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  11.       (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
  12.       (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  13.       (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  14.       (relu): ReLU (inplace)
  15.       (downsample): Sequential (
  16.         (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  17.         (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  18.       )
  19.     )
  20.     (1): Bottleneck (
  21.       (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
  22.       (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
  23.       (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  24.       (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
  25.       (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  26.       (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  27.       (relu): ReLU (inplace)
  28.     )
  29.     (2): Bottleneck (
  30.       (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
  31.       (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
  32.       (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  33.       (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
  34.       (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  35.       (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  36.       (relu): ReLU (inplace)
  37.     )
  38.   )
  39.   (layer2): Sequential (
  40.     (0): Bottleneck (
  41.       (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  42.       (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
  43.       (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
  44.       (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
  45.       (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  46.       (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
  47.       (relu): ReLU (inplace)
  48.       (downsample): Sequential (
  49.         (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
  50.         (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
  51.       )
  52.     )
  53.     (1): Bottleneck (
  54.       (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  55.       (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
  56.       (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  57.       (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
  58.       (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  59.       (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
  60.       (relu): ReLU (inplace)
  61.     )
  62.     (2): Bottleneck (
  63.       (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  64.       (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
  65.       (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  66.       (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
  67.       (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  68.       (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
  69.       (relu): ReLU (inplace)
  70.     )
  71.     (3): Bottleneck (
  72.       (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  73.       (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
  74.       (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  75.       (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
  76.       (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  77.       (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
  78.       (relu): ReLU (inplace)
  79.     )
  80.   )
  81.   (layer3): Sequential (
  82.     (0): Bottleneck (
  83.       (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  84.       (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  85.       (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
  86.       (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  87.       (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
  88.       (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True)
  89.       (relu): ReLU (inplace)
  90.       (downsample): Sequential (
  91.         (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)
  92.         (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True)
  93.       )
  94.     )
  95.     (1): Bottleneck (
  96.       (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  97.       (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  98.       (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  99.       (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  100.       (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
  101.       (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True)
  102.       (relu): ReLU (inplace)
  103.     )
  104.     (2): Bottleneck (
  105.       (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  106.       (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  107.       (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  108.       (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  109.       (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
  110.       (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True)
  111.       (relu): ReLU (inplace)
  112.     )
  113.     (3): Bottleneck (
  114.       (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  115.       (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  116.       (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  117.       (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  118.       (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
  119.       (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True)
  120.       (relu): ReLU (inplace)
  121.     )
  122.     (4): Bottleneck (
  123.       (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  124.       (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  125.       (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  126.       (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  127.       (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
  128.       (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True)
  129.       (relu): ReLU (inplace)
  130.     )
  131.     (5): Bottleneck (
  132.       (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  133.       (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  134.       (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  135.       (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
  136.       (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
  137.       (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True)
  138.       (relu): ReLU (inplace)
  139.     )
  140.   )
  141.   (layer4): Sequential (
  142.     (0): Bottleneck (
  143.       (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  144.       (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
  145.       (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
  146.       (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
  147.       (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
  148.       (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True)
  149.       (relu): ReLU (inplace)
  150.       (downsample): Sequential (
  151.         (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)
  152.         (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True)
  153.       )
  154.     )
  155.     (1): Bottleneck (
  156.       (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  157.       (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
  158.       (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  159.       (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
  160.       (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
  161.       (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True)
  162.       (relu): ReLU (inplace)
  163.     )
  164.     (2): Bottleneck (
  165.       (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  166.       (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
  167.       (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  168.       (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
  169.       (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
  170.       (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True)
  171.       (relu): ReLU (inplace)
  172.     )
  173.   )
  174.   (avgpool): AvgPool2d (size=7, stride=7, padding=0, ceil_mode=False, count_include_pad=True)
  175.   (fc): Linear (2048 -> 1000)
  176. )
添加新批注
在作者公开此批注前，只有你和作者可见。
回复批注