yolov5运行问题

2.RuntimeError: Given groups=1, weight of size [512, 1024, 1, 1], expected input[1, 512, 8, 8] to have 1024 channels, but got 512 channels instead

问题描述：

运行yolov5下面Tags5的代码出现问题：

Traceback (most recent call last):
  File "/media/ls/娱乐/yolov5/yolov5-5.0/train.py", line 547, in <module>
    train(hyp, opt, device, tb_writer)
  File "/media/ls/娱乐/yolov5/yolov5-5.0/train.py", line 88, in train
    model = Model(opt.cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)  # create
  File "/media/ls/娱乐/yolov5/yolov5-5.0/models/yolo.py", line 93, in __init__
    m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
  File "/media/ls/娱乐/yolov5/yolov5-5.0/models/yolo.py", line 123, in forward
    return self.forward_once(x, profile)  # single-scale inference, train
  File "/media/ls/娱乐/yolov5/yolov5-5.0/models/yolo.py", line 139, in forward_once
    x = m(x)  # run
  File "/home/ls/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
    return forward_call(*input, **kwargs)
  File "/media/ls/娱乐/yolov5/yolov5-5.0/models/common.py", line 32, in forward
    x = self.cv1(x)
  File "/home/ls/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
    return forward_call(*input, **kwargs)
  File "/media/ls/娱乐/yolov5/yolov5-5.0/models/common.py", line 60, in forward
    return self.act(self.bn(self.conv(x)))
  File "/home/ls/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/ls/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 446, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "/home/ls/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 443, in _conv_forward
    self.padding, self.dilation, self.groups)
RuntimeError: Given groups=1, weight of size [512, 1024, 1, 1], expected input[1, 512, 8, 8] to have 1024 channels, but got 512 channels instead

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-xzF3hDHD-1638930734782)(/home/ls/图片/ginen问题截图.png)]

这是由于一些参数没有加载好!!!

• 我们可以看到默认的模型配置文件yaml路径没有指定–在 459 --cfg 参数这一行[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-LT7ZskXR-1638930734785)(file:///home/ls/%E5%9B%BE%E7%89%87/train.png?lastModify=1638929942)]

然后我们指定一个之后

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-Nqmo9ss3-1638930734788)(/home/ls/图片/2021-12-08 10-17-09屏幕截图.png)]

然后就可以正常运行了!!!