a problem for save and load a pytorch model

Question

i am trying designing a neural network to classify signals by a pytorch model. after training the model i save the model and load it for inference phase.

i am trying designing a neural network to classify signals by a pytorch model. after training the model i save the model by the fllowing code:

torch.save(model.state_dict(), ".pth")

afterward i want to load the model for inference phase. i use the following code :

model_test = spectrogram_model(X_Test)
model_test.load_state_dict(torch.load(".pth"))

but i got an error as follows:

AttributeError: 'Tensor' object has no attribute 'load_state_dict'

the content of spectrogram_model is as follows:

class Spectrogram(nn.Module):
    def __init__(self):
        super().__init__()
        self.dropout = nn.Dropout(0.04)
        self.hidden1 = nn.Linear(16, 12)
        self.act1 = nn.ReLU()
        self.hidden2 = nn.Linear(12, 8)
        self.act2 = nn.ReLU()
        self.hidden3 = nn.Linear(8, 4)

    def forward(self, x):
        x = self.dropout(x)
        x = self.act1(self.hidden1(x))
        x = self.act2(self.hidden2(x))
        x = self.hidden3(x)
        return x

do you have any solution?