Yolov5更换上采样方式( 最近邻 / 双线性 / 双立方 / 三线性 / 转置卷积)

原文地址: https://www.iotword.com/3138.html

1. 常用上采样方式介绍

1. 1 最近邻插值(Nearest neighbor interpolation)

>>> input = torch.arange(1, 5, dtype=torch.float32).view(1, 1, 2, 2)
>>> input
tensor([[[[ 1.,  2.],
          [ 3.,  4.]]]])
          
>>> m = nn.Upsample(scale_factor=2, mode='nearest')
>>> m(input)
tensor([[[[ 1.,  1.,  2.,  2.],
          [ 1.,  1.,  2.,  2.],
          [ 3.,  3.,  4.,  4.],
          [ 3.,  3.,  4.,  4.]]]])

1.2. 双线性插值(Bi-Linear interpolation)

>>> input = torch.arange(1, 5, dtype=torch.float32).view(1, 1, 2, 2)
>>> input
tensor([[[[ 1.,  2.],
          [ 3.,  4.]]]])
          
>>> m = nn.Upsample(scale_factor=2, mode='bilinear')  # align_corners=False
>>> m(input)
tensor([[[[ 1.0000,  1.2500,  1.7500,  2.0000],
          [ 1.5000,  1.7500,  2.2500,  2.5000],
          [ 2.5000,  2.7500,  3.2500,  3.5000],
          [ 3.0000,  3.2500,  3.7500,  4.0000]]]])
          
>>> m = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
>>> m(input)
tensor([[[[ 1.0000,  1.3333,  1.6667,  2.0000],
          [ 1.6667,  2.0000,  2.3333,  2.6667],
          [ 2.3333,  2.6667,  3.0000,  3.3333],
          [ 3.0000,  3.3333,  3.6667,  4.0000]]]])

1.3. 双立方插值(Bi-Cubic interpolation)

>>> input = torch.arange(1, 5, dtype=torch.float32).view(1, 1, 2, 2)
>>> input
tensor([[[[ 1.,  2.],
          [ 3.,  4.]]]])
          
>>> m = nn.Upsample(scale_factor=2, mode='bicubic') # align_corners=False
>>> m(input)
tensor([[[[0.6836, 1.0156, 1.5625, 1.8945],
          [1.3477, 1.6797, 2.2266, 2.5586],
          [2.4414, 2.7734, 3.3203, 3.6523],
          [3.1055, 3.4375, 3.9844, 4.3164]]]])

>>> m = nn.Upsample(scale_factor=2, mode='bicubic', align_corners=True)
>>> m(input)
tensor([[[[1.0000, 1.3148, 1.6852, 2.0000],
          [1.6296, 1.9444, 2.3148, 2.6296],
          [2.3704, 2.6852, 3.0556, 3.3704],
          [3.0000, 3.3148, 3.6852, 4.0000]]]])

计算效果：最近邻插值算法 < 双线性插值 < 双三次插值
计算速度：最近邻插值算法 > 双线性插值 > 双三次插值

1.4 三线性插值(Trilinear Interpolation)

当align_corners = True时，线性插值模式(线性、双线性、双三线性和三线性)不按比例对齐输出和输入像素，因此输出值可以依赖于输入的大小

1.5. 反池化

2. 转置卷积

yolov5默认采用的就是最近邻插值

2.1 实验结果

这里我将原本的最近邻插值的上采样方式替换为转置卷积；有人通过实验证明了确实涨点，但是我在VOC数据集上测试并没有涨点，mAP0.5大概掉了不到1点

2.2 修改方式：

• 第一步；在models/yolo.py添加nn.ConvTranspose2d
  
• 第二步；models/yolo.py添加如下代码
  

elif m is nn.ConvTranspose2d:
     if len(args) >= 7:
         args[6] = make_divisible(args[6] * gw, 8)

• 第三步；修改配置文件，以yolov5s.yaml为例

# YOLOv5  by Ultralytics, GPL-3.0 license

# Parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # 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:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]


# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.ConvTranspose2d, [512, 4, 2, 1, 0, 512]],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.ConvTranspose2d, [256, 4, 2, 1, 0, 256]],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

出现下面这样子就是运行成功啦