“RuntimeError：Sizes of tensors must match except in dimension1.Expected size 512 but got size 256_runtimeerror: sizes of tensors must match except i

复现csdn这篇文章：YOLOv5改进——使用深度可分离卷积轻量化C3_c3模块_晓shuo的博客-CSDN博客

把yolo卷积块换成深度可分离卷积时遇到：

1、问题：完全按照他的步骤来一步步做下来，结果yaml文件有问题导致这个问题

2、原因：主要是Upsample将图像维度变为原来两倍导致维度对不上，后面concat的时候就有问题

3、解决删除模型中的两个Upsample模块，后面的tconcat和detect对应的层数也改一下即可。

4、修改后的yaml文件：

backbone:
  # [from, number, module, args]  
  [[-1, 1, Conv, [64, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 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, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13 12
 
   [-1, 1, Conv, [256, 1]],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small) 15
 
   [-1, 1, Conv, [256, 2]],
   [[-1, 13], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium) 18
 
   [-1, 1, Conv, [512, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
 
   [[15, 18, 21], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]