你好,onnx模型转NCNN错误，按照教程修改了detect部分

[pangedeshijie]

File "export.py", line 72, in y = model(img) # dry run File "E:\Anaconda\envs\yolo\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "F:\yolov5-face-master\models\yolo.py", line 222, in forward return self.forward_once(x, profile) # single-scale inference, train File "F:\yolov5-face-master\models\yolo.py", line 238, in forward_once x = m(x) # run File "E:\Anaconda\envs\yolo\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "F:\yolov5-face-master\models\yolo.py", line 62, in forward y = y + torch.cat((x[i][:, :, :, :, 0:5].sigmoid(), IndexError: too many indices for tensor of dimension 4

这一步老是过不去？