jupyter分割图片生成报错

[ggnogg]

---

RuntimeError Traceback (most recent call last)
Cell In[18], line 6
4 image = data["image"].cuda()
5 mask = data["mask"].cuda()
----> 6 out = model.forward(image)
7 out = torch.sigmoid(out)
8 out[out < 0.5] = 0

File D:\Simon\downloads\Edgedetection\MobileUNETR\experiments_medical\isic_2016\exp_2_dice_b8_a2../../..\architectures\mobileunetr.py:1016, in MViTxxsSegPretrained.forward(self, x)
1015 def forward(self, x):
-> 1016 enc_dict = self.encoder(x)
1017 btlneck = self.bottleneck(enc_dict["hidden_states"][-1])
1018 dec_out = self.decoder(btlneck, list(enc_dict["hidden_states"]))

File D:\Simon\downloads\anaconda\envs\munetr\lib\site-packages\torch\nn\modules\module.py:1736, in Module._wrapped_call_impl(self, *args, **kwargs)
1734 return self._compiled_call_impl(*args, **kwargs) # type: ignore[misc]
1735 else:
-> 1736 return self._call_impl(*args, **kwargs)

File D:\Simon\downloads\anaconda\envs\munetr\lib\site-packages\torch\nn\modules\module.py:1747, in Module._call_impl(self, *args, **kwargs)
1742 # If we don't have any hooks, we want to skip the rest of the logic in
1743 # this function, and just call forward.
1744 if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks or self._forward_pre_hooks
1745 or _global_backward_pre_hooks or _global_backward_hooks
1746 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1747 return forward_call(*args, **kwargs)
1749 result = None
1750 called_always_called_hooks = set()

File D:\Simon\downloads\Edgedetection\MobileUNETR\experiments_medical\isic_2016\exp_2_dice_b8_a2../../..\architectures\mobileunetr.py:949, in MViTxxsEncoderPretrained.forward(self, x)
947 def forward(self, x):
948 raw_input = x.clone()
--> 949 hidden_states = self.encoder.forward(x, output_hidden_states=True).hidden_states
950 out_dict = {"raw_input": raw_input, "hidden_states": hidden_states}
951 return out_dict

File D:\Simon\downloads\anaconda\envs\munetr\lib\site-packages\transformers\models\mobilevit\modeling_mobilevit.py:754, in MobileViTModel.forward(self, pixel_values, output_hidden_states, return_dict)
751 if pixel_values is None:
752 raise ValueError("You have to specify pixel_values")
--> 754 embedding_output = self.conv_stem(pixel_values)
756 encoder_outputs = self.encoder(
757 embedding_output,
758 output_hidden_states=output_hidden_states,
759 return_dict=return_dict,
760 )
762 if self.expand_output:

File D:\Simon\downloads\anaconda\envs\munetr\lib\site-packages\torch\nn\modules\module.py:1736, in Module._wrapped_call_impl(self, *args, **kwargs)
1734 return self._compiled_call_impl(*args, **kwargs) # type: ignore[misc]
1735 else:
-> 1736 return self._call_impl(*args, **kwargs)

File D:\Simon\downloads\anaconda\envs\munetr\lib\site-packages\torch\nn\modules\module.py:1747, in Module._call_impl(self, *args, **kwargs)
1742 # If we don't have any hooks, we want to skip the rest of the logic in
1743 # this function, and just call forward.
1744 if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks or self._forward_pre_hooks
1745 or _global_backward_pre_hooks or _global_backward_hooks
1746 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1747 return forward_call(*args, **kwargs)
1749 result = None
1750 called_always_called_hooks = set()

File D:\Simon\downloads\anaconda\envs\munetr\lib\site-packages\transformers\models\mobilevit\modeling_mobilevit.py:133, in MobileViTConvLayer.forward(self, features)
132 def forward(self, features: torch.Tensor) -> torch.Tensor:
--> 133 features = self.convolution(features)
134 if self.normalization is not None:
135 features = self.normalization(features)

File D:\Simon\downloads\anaconda\envs\munetr\lib\site-packages\torch\nn\modules\module.py:1736, in Module._wrapped_call_impl(self, *args, **kwargs)
1734 return self._compiled_call_impl(*args, **kwargs) # type: ignore[misc]
1735 else:
-> 1736 return self._call_impl(*args, **kwargs)

File D:\Simon\downloads\anaconda\envs\munetr\lib\site-packages\torch\nn\modules\module.py:1747, in Module._call_impl(self, *args, **kwargs)
1742 # If we don't have any hooks, we want to skip the rest of the logic in
1743 # this function, and just call forward.
1744 if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks or self._forward_pre_hooks
1745 or _global_backward_pre_hooks or _global_backward_hooks
1746 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1747 return forward_call(*args, **kwargs)
1749 result = None
1750 called_always_called_hooks = set()

File D:\Simon\downloads\anaconda\envs\munetr\lib\site-packages\torch\nn\modules\conv.py:554, in Conv2d.forward(self, input)
553 def forward(self, input: Tensor) -> Tensor:
--> 554 return self._conv_forward(input, self.weight, self.bias)

File D:\Simon\downloads\anaconda\envs\munetr\lib\site-packages\torch\nn\modules\conv.py:549, in Conv2d._conv_forward(self, input, weight, bias)
537 if self.padding_mode != "zeros":
538 return F.conv2d(
539 F.pad(
540 input, self._reversed_padding_repeated_twice, mode=self.padding_mode
(...)
547 self.groups,
548 )
--> 549 return F.conv2d(
550 input, weight, bias, self.stride, self.padding, self.dilation, self.groups
551 )

RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same

[ggnogg]

already solved