替换yolov8Conv报错

[JackyCs13]

请问为什么我直接替换yolov8的Conv会出现报错 Traceback (most recent call last): File "/home/ubuntu/ultralytics-main/Mytrain.py", line 4, in model = YOLO("/home/ubuntu/ultralytics-main/ultralytics/cfg/models/v8/yolov8_test.yaml") # 从头开始构建新模型 File "/home/ubuntu/ultralytics-main/ultralytics/engine/model.py", line 89, in init self._new(model, task) File "/home/ubuntu/ultralytics-main/ultralytics/engine/model.py", line 118, in _new self.model = (model or self._smart_load('model'))(cfg_dict, verbose=verbose and RANK == -1) # build model File "/home/ubuntu/ultralytics-main/ultralytics/nn/tasks.py", line 233, in init self.model, self.save = parse_model(deepcopy(self.yaml), ch=ch, verbose=verbose) # model, savelist File "/home/ubuntu/ultralytics-main/ultralytics/nn/tasks.py", line 689, in parsemodel m = nn.Sequential((m(args) for _ in range(n))) if n > 1 else m(*args) # module File "/home/ubuntu/ultralytics-main/ultralytics/nn/modules/conv.py", line 856, in init self.CRU = CRU( op_channel, File "/home/ubuntu/ultralytics-main/ultralytics/nn/modules/conv.py", line 820, in init self.squeeze2 = nn.Conv2d(low_channel,low_channel//squeeze_radio,kernel_size=1,bias=False) File "/home/ubuntu/anaconda3/envs/v8/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 450, in init super().init( File "/home/ubuntu/anaconda3/envs/v8/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 137, in init self.weight = Parameter(torch.empty( RuntimeError: Trying to create tensor with negative dimension -64: [-64, -128, 1, 1]

[jiangyangbo]

出现，一样的错误

[ghostmiao5]

一样

[luoni123]

请问大家解决了吗？

[ghostmiao5]

你好，邮件收到了，会尽快回复。