YOLOV5 Upsample 改成 ConvTranspose2d 后的问题_yolov5 unsample修改convtranspose2d

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']], # the origin nn.Upsample layer
   # [-1, 1, nn.ConvTranspose2d, [512, 2, 2]], # nn.ConvTransposed2d with 2x2 deconv kernel
   # [-1, 1, nn.ConvTranspose2d, [512, 4, 2, 1]], # nn.ConvTransposed2d with 4x4 deconv kernel
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']], # the origin nn.Upsample layer
   # [-1, 1, nn.ConvTranspose2d, [256, 2, 2]], # nn.ConvTransposed2d with 2x2 deconv kernel
   # [-1, 1, nn.ConvTranspose2d, [256, 4, 2, 1]], # nn.ConvTransposed2d with 4x4 deconv kernel
   [[-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)]

    return torch.cat(x, self.d)
RuntimeError: torch.cat(): Sizes of tensors must match except in dimension 1. Got 266 and 16 in dimension 2 (The offending index is 1)

出现上面问题

参考：

Do Upsample with ConvTranspose2d · Issue #7520 · ultralytics/yolov5 · GitHub