加载预训练权重，但使用修改后的模型结构yaml文件

Question

我是否可以知道我是否可以采用原始的 yolov8s.pt 权重并在修改后的 yolov8s.yaml 文件上训练它们，例如，在结构上添加像 CBAM 这样的注意模块？是否可以转移重量而不是从头开始训练？我尝试了这个命令，但似乎仍然从头开始训练。

model = YOLO("ultralytics/models/v8/yolov8s-cbam.yaml").load('yolov8s.pt')
model.train(**{'cfg':'ultralytics/yolo/cfg/train.yaml'})

yaml 文件是这样的：

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect

# Parameters
nc: 80  # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024]  # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
  s: [0.33, 0.50, 1024]  # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
  m: [0.67, 0.75, 768]   # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
  l: [1.00, 1.00, 512]   # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
  x: [1.00, 1.25, 512]   # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs

# YOLOv8.0n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
  - [-1, 1, CBAM, [7]] # 1
  - [-1, 1, Conv, [128, 3, 2]]  # 2-P2/4
  - [-1, 1, CBAM, [7]] # 3
  - [-1, 3, C2f, [128, True]]   # 4
  - [-1, 1, Conv, [256, 3, 2]]  # 5-P3/8
  - [-1, 1, CBAM, [7]] # 6
  - [-1, 6, C2f, [256, True]]   # 7
  - [-1, 1, Conv, [512, 3, 2]]  # 8-P4/16
  - [-1, 1, CBAM, [7]] # 9
  - [-1, 6, C2f, [512, True]]   # 10
  - [-1, 1, Conv, [1024, 3, 2]]  # 11-P5/32
  - [-1, 1, CBAM, [7]] # 12
  - [-1, 3, C2f, [1024, True]]  # 13
  - [-1, 1, SPPF, [1024, 5]]  # 14

# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']] # 15
  - [[-1, 9], 1, Concat, [1]]  # cat backbone P4 # 16
  - [-1, 3, C2f, [512]]  # 17

  - [-1, 1, nn.Upsample, [None, 2, 'nearest']] # 18
  - [[-1, 6], 1, Concat, [1]]  # cat backbone P3 # 19
  - [-1, 3, C2f, [256]]  # 20 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]] # 21
  - [[-1, 17], 1, Concat, [1]]  # cat head P4 # 22
  - [-1, 3, C2f, [512]]  # 23 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]] # 24
  - [[-1, 14], 1, Concat, [1]]  # cat head P5 # 25
  - [-1, 3, C2f, [1024]]  # 26 (P5/32-large)

  - [[20, 23, 26], 1, Detect, [nc]]  # Detect(P3, P4, P5) # 27

Answer 1

有什么解决办法吗？我遇到了问题。