shufflenet v2 yolo

news2024/11/27 6:12:24

设计理念

1x1卷积进行平衡输入和输出的通道大小；
组卷积要谨慎使用，注意分组数；
避免网络的碎片化；
减少元素级运算。
ShuffleNet v2中弃用了1x1的group convolution操作，而直接使用了input/output channels数目相同的1x1普通conv。它更是提出了一种ChannelSplit新的类型操作，将module的输入channels分为两部分，一部分直接向下传递，另外一部分则进行真正的向后计算。到了module的末尾，直接将两分支上的output channels数目级连起来，从而规避了原来ShuffleNet v1中Element-wise sum的操作。然后我们再对最终输出的output feature maps进行RandomShuffle操作，从而使得各channels之间的信息相互交通。。精彩至极，看至此处已然拍案叫绝。

backbone:
  # [from, number, module, args]
  # Shuffle_Block: [out, stride]
  [[ -1, 1, CBRM, [ 32 ] ], # 0-P2/4
   [ -1, 1, Shuffle_Block, [ 128, 2 ] ],  # 1-P3/8
   [ -1, 3, Shuffle_Block, [ 128, 1 ] ],  # 2
   [ -1, 1, Shuffle_Block, [ 256, 2 ] ],  # 3-P4/16
   [ -1, 7, Shuffle_Block, [ 256, 1 ] ],  # 4
   [ -1, 1, Shuffle_Block, [ 512, 2 ] ],  # 5-P5/32
   [ -1, 3, Shuffle_Block, [ 512, 1 ] ],  # 6
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P4
   [-1, 1, C3, [256, False]],  # 10

   [-1, 1, Conv, [128, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 2], 1, Concat, [1]],  # cat backbone P3
   [-1, 1, C3, [128, False]],  # 14 (P3/8-small)

   [-1, 1, Conv, [128, 3, 2]],
   [[-1, 11], 1, Concat, [1]],  # cat head P4
   [-1, 1, C3, [256, False]],  # 17 (P4/16-medium)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 7], 1, Concat, [1]],  # cat head P5
   [-1, 1, C3, [512, False]],  # 20 (P5/32-large)

   [[14, 17, 20], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]