AttributeError: 'str' object has no attribute 'unsqueeze'

[bruceszq]

I have a problem when I run the code loss=model(inputs,label_ids), it happens a problem of AttributeError. I have seached on Google for a long time but I can't find a key to solve it. Could you help me how to solve the problem, thank you very much.

AttributeError Traceback (most recent call last)
in ()
13 with torch.no_grad():
14 inputs,_ = basemodel(input_ids, segment_ids, input_mask)
---> 15 loss = model(inputs, label_ids)
16 loss = loss.mean()
17 loss.backward()

1 frames
in forward(self, inputs, labels)
14
15 def forward(self, inputs, labels=None):
---> 16 output = inputs.unsqueeze(1)
17 output = [nn.functional.relu(conv(output)).squeeze(3) for conv in self.convs]
18 output = [nn.functional.max_pool1d(i, i.size(2)).squeeze(2) for i in output]

AttributeError: 'str' object has no attribute 'unsqueeze'