GSConv implementation

[zeobec]

Currently, im trying to implement GSConv module into Yolov10b module.  
conv.py

task.py

also imported module in init.py

.yaml

however, i received this error message

What's the possible reason that could be the source of the error?

[AlanLi1997]

@zeobec You should note the definition of the Conv in YOLOv10. Try to use this GSConv:

  class GSConv(nn.Module):
      # GSConv https://github.com/AlanLi1997/slim-neck-by-gsconv
      def __init__(self, c1, c2, k=1, s=1, g=1, d=1, act=True):
          super().__init__()
          c_ = c2 // 2
          self.cv1 = Conv(c1, c_, k, s, None, g, d, act)
          self.cv2 = Conv(c_, c_, 5, 1, None, c_, d, act)
  
      def forward(self, x):
          x1 = self.cv1(x)
          x2 = torch.cat((x1, self.cv2(x1)), 1)
          # shuffle
          y = x2.reshape(x2.shape[0], 2, x2.shape[1] // 2, x2.shape[2], x2.shape[3])
          y = y.permute(0, 2, 1, 3, 4)
          return y.reshape(y.shape[0], -1, y.shape[3], y.shape[4])

I have not checked the definition of "Conv" in YOLOv10 yet, so please don't hesitate to let me know if you have any further questions.

[zeobec]

hi, thankyou for your response. i noticed that you have added new parameter which is d. Based on my understanding, is it true that d is representing dilation? would you mind to explain why you add the new parameter to make the module works?

[AlanLi1997]

hi, thankyou for your response. i noticed that you have added new parameter which is d. Based on my understanding, is it true that d is representing dilation? would you mind to explain why you add the new parameter to make the module works?

Is your project have worked? You need to correctly define the "Conv" class in the Yolov10 to make it works. NOTE: please check the definition of "Conv" in YOLOv10.