GhostnetV2问题

[fenton-lu]

您好，请问ghostV2直接替换YOLOv5中的ghostV1会报错，是需要修改ghostV2的代码吗？

Traceback (most recent call last):
  File "train.py", line 667, in <module>
    main(opt)
  File "train.py", line 562, in main
    train(opt.hyp, opt, device, callbacks)
  File "train.py", line 121, in train
    model = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)  # create
  File "/home/tmp/lhr/yolov5/models/yolo.py", line 121, in __init__
    m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
  File "/home/tmp/lhr/yolov5/models/yolo.py", line 135, in forward
    return self._forward_once(x, profile, visualize)  # single-scale inference, train
  File "/home/tmp/lhr/yolov5/models/yolo.py", line 158, in _forward_once
    x = m(x)  # run
  File "/home/tmp/anaconda3/envs/yolov5-lhr/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/tmp/lhr/yolov5/models/common.py", line 144, in forward
    return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))
  File "/home/tmp/anaconda3/envs/yolov5-lhr/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/tmp/lhr/yolov5/models/common.py", line 52, in forward
    return self.act(self.bn(self.conv(x)))
  File "/home/tmp/anaconda3/envs/yolov5-lhr/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/tmp/anaconda3/envs/yolov5-lhr/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 447, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "/home/tmp/anaconda3/envs/yolov5-lhr/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 443, in _conv_forward
    return F.conv2d(input, weight, bias, self.stride,
TypeError: conv2d() received an invalid combination of arguments - got (NoneType, Parameter, NoneType, tuple, tuple, tuple, int), but expected one of:
 * (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, tuple of ints padding, tuple of ints dilation, int groups)
      didn't match because some of the arguments have invalid types: (NoneType, Parameter, NoneType, tuple, tuple, tuple, int)
 * (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, str padding, tuple of ints dilation, int groups)
      didn't match because some of the arguments have invalid types: (NoneType, Parameter, NoneType, tuple, tuple, tuple, int)

[Shin-God]

我也是这错误。。。请问下如何解决呢。。。

[nortorious]

我也想知道如何加入到yolov5中，ghostbottleneckv2他要输入三个通道数，而ghostbottleneck只需要两个，不晓得咋整？

[Administor123]

同问，我想把GhostnetV2加入C3模块，请问大家有方法吗