mobilenetv1,v2网络结构（无原理解析）

mobilenetv1

将普通卷积改为可分离卷积（点卷积+深度卷积）。

具体推导留待补充

mobilenetv2

将可分离卷积应用于残差结构，形成倒卷残差块，堆叠形成线性瓶颈块。

推导留待补充。

应用于SSD时：

SSD(
  (base_net): Sequential(
  #基础卷积，input:300*300*3,output:150*150*32
    (0): Sequential(
      (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU6(inplace)
    )

    #七个线性瓶颈层，（共17个倒卷残差块）n=1,2,3,4,3,3,1（分别为残差块的个数）
    #第一个
    (1): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
        (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(32, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (4): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    #第二个
    (2): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(16, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=96, bias=False)
        (4): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(96, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (3): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(144, 144, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=144, bias=False)
        (4): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(144, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    #第三个
    (4): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(144, 144, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=144, bias=False)
        (4): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(144, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (5): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)
        (4): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (6): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)
        (4): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    #第四个
    (7): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(192, 192, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=192, bias=False)
        (4): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (8): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
        (4): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (9): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
        (4): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (10): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
        (4): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    #第五个
    (11): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
        (4): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (12): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576, bias=False)
        (4): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (13): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576, bias=False)
        #从3）抽取的第一张特征图，此时输出已经为19*19*576
        (4): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )

    #残差块6
    (14): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        #第一张特征图19*19*576
        (3): Conv2d(576, 576, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=576, bias=False)
        (4): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(576, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (15): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)
        (4): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (16): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)
        (4): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    #残差块7
    (17): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)
        (4): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(960, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    #末尾卷积层
    (18): Sequential(
      (0): Conv2d(320, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (1): BatchNorm2d(1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU6(inplace)
    )
     #第二张特征图，10*10*1280
  )

  (extras): ModuleList(
    (0): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(1280, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=256, bias=False)
        (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=128, bias=False)
        (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (2): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=128, bias=False)
        (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (3): InvertedResidual(
      (conv): Sequential(
        (0): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU6(inplace)
        (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=64, bias=False)
        (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU6(inplace)
        (6): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (7): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
  )
  (classification_headers): ModuleList(
    (0): Sequential(
      (0): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576)
      (1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU6()
      (3): Conv2d(576, 24, kernel_size=(1, 1), stride=(1, 1))
    )
    (1): Sequential(
      (0): Conv2d(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=1280)
      (1): BatchNorm2d(1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU6()
      (3): Conv2d(1280, 24, kernel_size=(1, 1), stride=(1, 1))
    )
    (2): Sequential(
      (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=512)
      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU6()
      (3): Conv2d(512, 24, kernel_size=(1, 1), stride=(1, 1))
    )
    (3): Sequential(
      (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256)
      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU6()
      (3): Conv2d(256, 24, kernel_size=(1, 1), stride=(1, 1))
    )
    (4): Sequential(
      (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256)
      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU6()
      (3): Conv2d(256, 24, kernel_size=(1, 1), stride=(1, 1))
    )
    (5): Conv2d(64, 24, kernel_size=(1, 1), stride=(1, 1))
  )
  (regression_headers): ModuleList(
    (0): Sequential(
      (0): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576)
      (1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU6()
      (3): Conv2d(576, 24, kernel_size=(1, 1), stride=(1, 1))
    )
    (1): Sequential(
      (0): Conv2d(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=1280)
      (1): BatchNorm2d(1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU6()
      (3): Conv2d(1280, 24, kernel_size=(1, 1), stride=(1, 1))
    )
    (2): Sequential(
      (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=512)
      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU6()
      (3): Conv2d(512, 24, kernel_size=(1, 1), stride=(1, 1))
    )
    (3): Sequential(
      (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256)
      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU6()
      (3): Conv2d(256, 24, kernel_size=(1, 1), stride=(1, 1))
    )
    (4): Sequential(
      (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256)
      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU6()
      (3): Conv2d(256, 24, kernel_size=(1, 1), stride=(1, 1))
    )
    (5): Conv2d(64, 24, kernel_size=(1, 1), stride=(1, 1))
  )
  (source_layer_add_ons): ModuleList()
)