Activation function " TypeError: 'Tensor' object is not callable"

1

I am trying to use the relu activation function in PyTorch LSTM but getting the error on " Tensor object is not callable. any guideline or help? Can i use the different activation function in forward propogation? but i am using the same activation function in hidden layers and forward propagation. your kind review will be more help full.

class LSTM(nn.Module):
def init(self, input_size=1, hidden_layer_size=20, output_size=1):
super().init()

self.hidden_layer_size = hidden_layer_size
self.lstm = nn.LSTM(input_size, hidden_layer_size)
self.relu = nn.functional.relu(torch.FloatTensor(hidden_layer_size), torch.FloatTensor(output_size))     
self.hidden_cell = (torch.zeros(1, 1, self.hidden_layer_size),    
                    torch.zeros(1, 1, self.hidden_layer_size))
 def forward(self, input_seq):
lstm_out, self.hidden_cell = self.lstm(input_seq.view(len(input_seq), 1, -1), self.hidden_cell)
predictions = self.relu(lstm_out.view(len(input_seq), -1))
return predictions[-1]



model = LSTM()
loss_function = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr = 0.0001)





epochs = 150

 for i in range(epochs):
   for seq, labels in train_inout_seq:
    optimizer.zero_grad()
    model.hidden_cell = (torch.zeros(1, 1, model.hidden_layer_size),
                        torch.zeros(1, 1, model.hidden_layer_size))    
   y_pred = model(seq)

single_loss = loss_function(y_pred, labels)
single_loss.backward()
optimizer.step()

 if i%25 == 1:
print(f'epoch: {i:3} loss: {single_loss.item():10.8f}')

print(f'epoch: {i:3} loss: {single_loss.item():10.10f}')

After that i am getting an error:

TypeError Traceback (most recent call last)
in
6 model.hidden_cell = (torch.zeros(1, 1, model.hidden_layer_size),
7 torch.zeros(1, 1, model.hidden_layer_size))
----> 8 y_pred = model(seq)
9
10 single_loss = loss_function(y_pred, labels)

/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py in call(self, *input, **kwargs)
548 result = self._slow_forward(*input, **kwargs)
549 else:
→ 550 result = self.forward(*input, **kwargs)
551 for hook in self._forward_hooks.values():
552 hook_result = hook(self, input, result)

in forward(self, input_seq)
12 def forward(self, input_seq):
13 lstm_out, self.hidden_cell = self.lstm(input_seq.view(len(input_seq), 1, -1), self.hidden_cell)
—> 14 predictions = self.relu(lstm_out.view(len(input_seq), -1))
15 return predictions[-1]

TypeError: ‘Tensor’ object is not callable```

2

You are trying to define self.relu as a tensor in:

self.relu = nn.functional.relu(torch.FloatTensor(hidden_layer_size), torch.FloatTensor(output_size))

Note that this call is most likely not, what you are trying to achieve, as the second argument would be used as the inplace argument.
Also, torch.FloatTensorwill create a new tensor in the provided shape with uninitialized memory, so I would recommend to use the factory methods, such astorch.zeros, torch.randn` etc.

The original error is later raised, since you are trying to call the tensor in:

self.relu(lstm_out.view(len(input_seq), -1))

Assuming you would like to use self.relu as a module, use self.relu = nn.ReLU().

3

As i used the self.relu = nn.ReLU() but how i will give the input size and hidden layer size to that relu function?

4

As in linear activation function we use the hidden layer size and output size so how we will give the hiiden layer size and output size in relu function?
self.linear = nn.Linear(hidden_layer_size, output_size)

As u guided to use the self.relu = nn.ReLU()so i tried and i cannot see my loss is changing its getting same on every epoch:

epoch: 1 loss: 0.88755035
epoch: 26 loss: 0.88755035
epoch: 51 loss: 0.88755035
epoch: 76 loss: 0.88755035
epoch: 101 loss: 0.88755035
epoch: 126 loss: 0.88755035
epoch: 149 loss: 0.8875503540

5

The nn.ReLU() module doesn’t have any parameters and will work on any input, so you don’t need to provide a shape for it.