Yolov5 changing the upper sampling mode

Yolov5 Change up sampling mode

---

Introduction to common sampling methods

1. Nearest neighbor interpolation (Nearest neighbor interpolation)

2. Bilinear interpolation (Bi-Linear interpolation)

3. Bicubic interpolation (Bi-Cubic interpolation)

Calculation effect ： Nearest neighbor interpolation algorithm < Bilinear interpolation < Bicubic interpolation
Calculation speed ： Nearest neighbor interpolation algorithm > Bilinear interpolation > Bicubic interpolation

4. Anti pooling

5. Transposition convolution

yolov5 The default is Nearest neighbor interpolation

---

experimental result

Here I will present the original Nearest neighbor interpolation The upsampling method of is replaced by Transposition convolution ; Some people have proved through experiments that it does rise , But I am VOC Data sets Up test No rise ,mAP0.5 Probably less than 1 spot

Modify the way ：

First step ; stay models/yolo.py add to nn.ConvTranspose2d

The second step ;models/yolo.py Add the following code

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

The third step ; Modify the configuration file , With yolov5s.yaml For example

# 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)
  ]

---

The following is a successful operation