大佬如果改动使用MBConvBlock的se模块呢 设置True，会报错

[ahhhxxx]

File "F:/999yolo/YOLOv5-Multibackbone-Compression-main/models/yolo.py", line 331, in
model = Model(opt.cfg).to(device)
File "F:/999yolo/YOLOv5-Multibackbone-Compression-main/models/yolo.py", line 112, in init
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
File "F:/999yolo/YOLOv5-Multibackbone-Compression-main/models/yolo.py", line 128, in forward
return self._forward_once(x, profile, visualize) # single-scale inference, train
File "F:/999yolo/YOLOv5-Multibackbone-Compression-main/models/yolo.py", line 152, in _forward_once
x = m(x) # run
File "D:\Anaconda3\envs\y55\lib\site-packages\torch\nn\modules\module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "F:\999yolo\YOLOv5-Multibackbone-Compression-main\models\common.py", line 142, in forward
x_squeezed = nn.AdaptiveAvgPool2d(x, 1)
TypeError: init() takes 2 positional arguments but 3 were given

[Gumpest]

您好，我目前代码push出现问题，您可以将se模块替换成SeBlock类即可，亲测可用

[Gumpest]

已修复，请git pull