代码运行问题

[Luckycat518]

您好，我在将您的代码配置在yolov5-v6.0版本上进行训练时，出现了如下错误，您知道如何解决吗？
line 376, in kaiming_uniform_
std = gain / math.sqrt(fan)
ZeroDivisionError: float division by zero

[AlanLi1997]

您好，我在将您的代码配置在yolov5-v6.0版本上进行训练时，出现了如下错误，您知道如何解决吗？ line 376, in kaiming_uniform_ std = gain / math.sqrt(fan) ZeroDivisionError: float division by zero

你好，该仓库包含的yolov5代码版本为v6.1，更新您的代码库为v6.1即可，或选择克隆本仓库的yolov5代码到本地或服务器端运行🍺

[Luckycat518]

好的，谢谢您，现在又遇到一个问题AttributeError: module 'torch.nn' has no attribute 'Mish'，这是torch版本的问题还是哪里没设置好呢？我的torch版本是1.8.0

[AlanLi1997]

好的，谢谢您，现在又遇到一个问题AttributeError: module 'torch.nn' has no attribute 'Mish'，这是torch版本的问题还是哪里没设置好呢？我的torch版本是1.8.0

请将以下代码copy至common.py(注意缩进)，并将原代码中的 nn.Mish 字段更改为 Mish 字段。

class Mish(nn.Module):
@staticmethod
def forward(x):
return x * torch.nn.functional.softplus(x).tanh()

[Luckycat518]

好的，解决了，十分感谢您的耐心解答~

[llillei]

您好，我在将您的代码配置在yolov5-v7.0版本上进行训练时，出现了如下错误，您知道如何解决吗？
TypeError: conv2d() received an invalid combination of arguments - got (Tensor, 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: (Tensor, !Parameter!, !NoneType!, !tuple of (int, int)!, !tuple of (int, int)!, !tuple of (bool, bool)!, 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: (Tensor, !Parameter!, !NoneType!, !tuple of (int, int)!, !tuple of (int, int)!, !tuple of (bool, bool)!, int)

详细报错信息如下
Traceback (most recent call last):
File "E:\PycharmProjects\yolov5-7.0\train_mycar.py", line 635, in
main(opt)
File "E:\PycharmProjects\yolov5-7.0\train_mycar.py", line 529, in main
train(opt.hyp, opt, device, callbacks)
File "E:\PycharmProjects\yolov5-7.0\train_mycar.py", line 125, in train
model = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
File "E:\PycharmProjects\yolov5-7.0\models\yolo.py", line 195, in init
m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))]) # forward
File "E:\PycharmProjects\yolov5-7.0\models\yolo.py", line 194, in
forward = lambda x: self.forward(x)[0] if isinstance(m, Segment) else self.forward(x)
File "E:\PycharmProjects\yolov5-7.0\models\yolo.py", line 209, in forward
return self._forward_once(x, profile, visualize) # single-scale inference, train
File "E:\PycharmProjects\yolov5-7.0\models\yolo.py", line 121, in _forward_once
x = m(x) # run
File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "E:\PycharmProjects\yolov5-7.0\models\common.py", line 1069, in forward
x1 = self.cv1(x)
File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "E:\PycharmProjects\yolov5-7.0\models\common.py", line 58, in forward
return self.act(self.bn(self.conv(x)))
File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
return self._conv_forward(input, self.weight, self.bias)
File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
TypeError: conv2d() received an invalid combination of arguments - got (Tensor, 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: (Tensor, !Parameter!, !NoneType!, !tuple of (int, int)!, !tuple of (int, int)!, !tuple of (bool, bool)!, 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: (Tensor, !Parameter!, !NoneType!, !tuple of (int, int)!, !tuple of (int, int)!, !tuple of (bool, bool)!, int)

[AlanLi1997]

您好，我在将您的代码配置在yolov5-v7.0版本上进行训练时，出现了如下错误，您知道如何解决吗？ TypeError: conv2d() received an invalid combination of arguments - got (Tensor, 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: (Tensor, !Parameter!, !NoneType!, !tuple of (int, int)!, !tuple of (int, int)!, !tuple of (bool, bool)!, 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: (Tensor, !Parameter!, !NoneType!, !tuple of (int, int)!, !tuple of (int, int)!, !tuple of (bool, bool)!, int)

详细报错信息如下 Traceback (most recent call last): File "E:\PycharmProjects\yolov5-7.0\train_mycar.py", line 635, in main(opt) File "E:\PycharmProjects\yolov5-7.0\train_mycar.py", line 529, in main train(opt.hyp, opt, device, callbacks) File "E:\PycharmProjects\yolov5-7.0\train_mycar.py", line 125, in train model = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create File "E:\PycharmProjects\yolov5-7.0\models\yolo.py", line 195, in init m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))]) # forward File "E:\PycharmProjects\yolov5-7.0\models\yolo.py", line 194, in forward = lambda x: self.forward(x)[0] if isinstance(m, Segment) else self.forward(x) File "E:\PycharmProjects\yolov5-7.0\models\yolo.py", line 209, in forward return self._forward_once(x, profile, visualize) # single-scale inference, train File "E:\PycharmProjects\yolov5-7.0\models\yolo.py", line 121, in _forward_once x = m(x) # run File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "E:\PycharmProjects\yolov5-7.0\models\common.py", line 1069, in forward x1 = self.cv1(x) File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "E:\PycharmProjects\yolov5-7.0\models\common.py", line 58, in forward return self.act(self.bn(self.conv(x))) File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward return self._conv_forward(input, self.weight, self.bias) File "E:\develop\anaconda\envs\yolov57\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward return F.conv2d(input, weight, bias, self.stride, TypeError: conv2d() received an invalid combination of arguments - got (Tensor, 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: (Tensor, !Parameter!, !NoneType!, !tuple of (int, int)!, !tuple of (int, int)!, !tuple of (bool, bool)!, 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: (Tensor, !Parameter!, !NoneType!, !tuple of (int, int)!, !tuple of (int, int)!, !tuple of (bool, bool)!, int)

你好，我猜测可能是7.0版本的基础卷积代码更新导致的，你可以尝试使用下面的GSConv代码：

---

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])

请注意，7.0版本新增了参数‘d’ (c1, c2, k, s, g, d, act)，你必须让任何调用了‘GSConv’和‘Conv’类的那些类的传入参数的个数正确。

[harryc7]

'ReLU' object has no attribute 'dim'，用yolov5-6.1报了这个错误，应该如何解决

[AlanLi1997]

'ReLU' object has no attribute 'dim'，用yolov5-6.1报了这个错误，应该如何解决

你需要提供完整的报错信息让我更好地帮你定位和修复错误。我猜测你可能使用了GSConvs(使用了ReLU)，尝试使用GSConv.