margin_ranking_报错：All input tensors should have same dimension but got sizes: input1: torch.Size([1024, 1]), input2: torch.Size([1024, 1]), target: torch.Size([1])

[Isaiah-pq]

Traceback (most recent call last):
File "C:\Users\Administrator\Desktop\GNN\MetaR-master\main.py", line 61, in
trainer.train()
File "C:\Users\Administrator\Desktop\GNN\MetaR-master\trainer.py", line 145, in train
loss, _, _ = self.do_one_step(train_task, iseval=False, curr_rel=curr_rel)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\Desktop\GNN\MetaR-master\trainer.py", line 124, in do_one_step
p_score, n_score = self.metaR(task, iseval, curr_rel)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\anaconda3\envs\MetaR\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\anaconda3\envs\MetaR\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\Desktop\GNN\MetaR-master\models.py", line 110, in forward
loss = self.loss_func(p_score, n_score, y)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\anaconda3\envs\MetaR\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\anaconda3\envs\MetaR\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\anaconda3\envs\MetaR\Lib\site-packages\torch\nn\modules\loss.py", line 1338, in forward
return F.margin_ranking_loss(input1, input2, target, margin=self.margin, reduction=self.reduction)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\anaconda3\envs\MetaR\Lib\site-packages\torch\nn\functional.py", line 3362, in margin_ranking_loss
raise RuntimeError(
RuntimeError: margin_ranking_loss : All input tensors should have same dimension but got sizes: input1: torch.Size([1024, 1]), input2: torch.Size([1024, 1]), target: torch.Size([1])

请问是哪里出了问题？

[YuanMan-00]

@Isaiah-pq 你好，请问这个维度问题你解决了吗