YOLOv5结合MobileNetV3-small与MobileNetV3-large

原创已于 2023-03-03 11:39:10 修改 · 4.7k 阅读

57 ·

CC 4.0 BY-SA版权

文章标签：

#python #人工智能 #深度学习

于 2022-11-23 13:41:29 首次发布

本文对比分析了MobileNetV3-small与MobileNetV3-large两种架构与YOLOv5融合的方法，详细介绍了这两种配置下网络的具体结构与参数设定，包括卷积层、上采样层、特征融合层等，并探讨了它们之间的性能差异。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

网上有很多代码都是结合MobileNetV3-small-YOLOv5，结合MobileNetV3-large代码不全，他们区别在于yaml文件中head中concat连接不同，深度因子和宽度因子不同

MobileNetV3-small-YOLOv5

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license

# Parameters
nc: 20  # number of classes
depth_multiple: 1.0  # model depth multiple
width_multiple: 1.0  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5 v6.0 backbone
backbone:
  # MobileNetV3-small 11层
  # [from, number, module, args]
  # MobileNet_Block: [out_ch, hidden_ch, kernel_size, stride, use_se, use_hs]
  # hidden_ch表示在Inverted residuals中的扩张通道数
  # use_se 表示是否使用 SELayer, use_hs 表示使用 h_swish 还是 ReLU
  [[-1, 1, conv_bn_hswish, [16, 2]],                 # 0-p1/2
   [-1, 1, MobileNet_Block, [16,  16, 3, 2, 1, 0]],  # 1-p2/4
   [-1, 1, MobileNet_Block, [24,  72, 3, 2, 0, 0]],  # 2-p3/8
   [-1, 1, MobileNet_Block, [24,  88, 3, 1, 0, 0]],  # 3-p3/8
   [-1, 1, MobileNet_Block, [40,  96, 5, 2, 1, 1]],  # 4-p4/16
   [-1, 1, MobileNet_Block, [40, 240, 5, 1, 1, 1]],  # 5-p4/16
   [-1, 1, MobileNet_Block, [40, 240, 5, 1, 1, 1]],  # 6-p4/16
   [-1, 1, MobileNet_Block, [48, 120, 5, 1, 1, 1]],  # 7-p4/16
   [-1, 1, MobileNet_Block, [48, 144, 5, 1, 1, 1]],  # 8-p4/16
   [-1, 1, MobileNet_Block, [96, 288, 5, 2, 1, 1]],  # 9-p5/32
   [-1, 1, MobileNet_Block, [96, 576, 5, 1, 1, 1]],  # 10-p5/32
   [-1, 1, MobileNet_Block, [96, 576, 5, 1, 1, 1]],  # 11-p5/32
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
   [-1, 1, C3, [256, False]],  # 15

   [-1, 1, Conv, [128, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 3], 1, Concat, [1]],  # cat backbone P3
   [-1, 1, C3, [128, False]],  # 19 (P3/8-small)

   [-1, 1, Conv, [128, 3, 2]],
   [[-1, 16], 1, Concat, [1]],  # cat head P4
   [-1, 1, C3, [256, False]],  # 22 (P4/16-medium)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 12], 1, Concat, [1]],  # cat head P5
   [-1, 1, C3, [512, False]],  # 25 (P5/32-large)

   [[19, 22, 25], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

注意由于 MobileNetV3-small作为主干网格参数很少，这里宽度因子和深度因子可以设置为1，且head部分通道数缩减，最初的作者可能想进一步轻量化

MobileNetV3-large

# Parameters
nc: 20  # number of classes
depth_multiple: 1.0  # model depth multiple
width_multiple: 1.0  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5 v6.0 backbone
backbone:
  # MobileNetV3-small 11层
  # [from, number, module, args]
  # MobileNet_Block: [out_ch, hidden_ch, kernel_size, stride, use_se, use_hs]
  # hidden_ch表示在Inverted residuals中的扩张通道数
  # use_se 表示是否使用 SELayer, use_hs 表示使用 h_swish 还是 ReLU
  # MobileNetV3-large
  # [from, number, module, args]
  [[-1, 1, conv_bn_hswish, [16, 2]],                   # 0-p1/2
   [-1, 1, MobileNet_Block, [ 16,  16, 3, 1, 0, 0]],  # 1-p1/2
   [-1, 1, MobileNet_Block, [ 24,  64, 3, 2, 0, 0]],  # 2-p2/4
   [-1, 1, MobileNet_Block, [ 24,  72, 3, 1, 0, 0]],  # 3-p2/4
   [-1, 1, MobileNet_Block, [ 40,  72, 5, 2, 1, 0]],  # 4-p3/8
   [-1, 1, MobileNet_Block, [ 40, 120, 5, 1, 1, 0]],  # 5-p3/8
   [-1, 1, MobileNet_Block, [ 40, 120, 5, 1, 1, 0]],  # 6-p3/8
   [-1, 1, MobileNet_Block, [ 80, 240, 3, 2, 0, 1]],  # 7-p4/16
   [-1, 1, MobileNet_Block, [ 80, 200, 3, 1, 0, 1]],  # 8-p4/16
   [-1, 1, MobileNet_Block, [ 80, 184, 3, 1, 0, 1]],  # 9-p4/16
   [-1, 1, MobileNet_Block, [ 80, 184, 3, 1, 0, 1]],  # 10-p4/16
   [-1, 1, MobileNet_Block, [112, 480, 3, 1, 1, 1]],  # 11-p4/16
   [-1, 1, MobileNet_Block, [112, 672, 3, 1, 1, 1]],  # 12-p4/16
   [-1, 1, MobileNet_Block, [160, 672, 5, 1, 1, 1]],  # 13-p4/16
   [-1, 1, MobileNet_Block, [160, 960, 5, 2, 1, 1]],  # 14-p5/32   原672改为原算法960
   [-1, 1, MobileNet_Block, [160, 960, 5, 1, 1, 1]],  # 15-p5/32
  ]
# YOLOv5 v6.0 head
head:
  [ [ -1, 1, Conv, [ 256, 1, 1 ] ],
    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
    [ [ -1, 13], 1, Concat, [ 1 ] ],  # cat backbone P4
    [ -1, 1, C3, [ 256, False ] ],  # 13

    [ -1, 1, Conv, [ 128, 1, 1 ] ],
    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
    [ [ -1, 6 ], 1, Concat, [ 1 ] ],  # cat backbone P3
    [ -1, 1, C3, [ 128, False ] ],  # 17 (P3/8-small)

    [ -1, 1, Conv, [ 128, 3, 2 ] ],
    [ [ -1, 20 ], 1, Concat, [ 1 ] ],  # cat head P4
    [ -1, 1, C3, [ 256, False ] ],  # 20 (P4/16-medium)

    [ -1, 1, Conv, [ 256, 3, 2 ] ],
    [ [ -1, 16 ], 1, Concat, [ 1 ] ],  # cat head P5
    [ -1, 1, C3, [ 512, False ] ],  # 23 (P5/32-large)

    [ [ 23, 26, 29 ], 1, Detect, [ nc, anchors ] ],  # Detect(P3, P4, P5)
  ]

MobileNetV3-large模型比MobileNetV3-small多了更多的MobileNet_Block结构，残差倒置结构中通道数维度也增大了许多，速度比YOLOv5s慢将近一半，但是参数变少，效果介乎MobileNetV3-small和YOLOv5s之间，可以作为模型对比，凸显自己模型优势