AttributeError: 'NoneType' object has no attribute 'squeeze'

[x15-eth]

I keep getting an attribute error when i try running my train and test loop for my model.

Here's the code below. Pls I really need help with this. Will appreciate any form of help , thanks

#Training loop
torch_manual_seed = 42

#set the numberof epochs
epochs = 1000

X_train, y_train = X_train.to(device), y_train.to(device)
X_test, y_test = X_test.to(device), y_test.to(device)

#build training and evaluation loop
for epoch in range(epochs):
  #Training
  model_3.train()

  #1. Forward pass (model outputs raw logits)
  y_logits = model_3(X_train).squeeze()
  y_pred = torch.round(torch.sigmoid(y_logits))

  #2. Calculate the loss and the accuracy
  loss = loss_fn(y_logits, y_train)
  acc = accuracy_fn(y_true = y_train, y_pred=y_pred)

  #3. Opitmizer to zero grad
  optimizer.zero_grad()

  #4. Backprop
  loss.backward()

  #5.Optimizer Step
  optimizer.step()

  ##Testing loop
  model_3.eval()

  with torch.inference_mode():
    #1. Forward pass
    test_logits = model_3(X_test).squeeze()
    test_pred = torch.round(torch.sigmoid(test_logits))

    #2. Compute loss/accuracy
    test_loss = loss_fn(test_logits, y_test)
    test_acc = accuracy_fn(y_true =y_test, y_pred=test_pred)

  
  if epoch % 10==0:
    print(f"Epoch: {epoch} | Train loss: {loss:.5f} |Accuracy: {acc:.5f}| Test loss: {test_loss:.5f} | Accuracy: {test_acc:.5f}")

[mrdbourke]

Hi @promiseeselojor,

What have you tried so far?

Could you share where in the course you're getting this error?

You might need to rerun some cells above your code to get the data/model to work again.

I just ran this notebook: https://www.learnpytorch.io/02_pytorch_classification/

And the following code worked for me:

# Fit the model
torch.manual_seed(42)
epochs = 1000

# Put all data on target device
X_train, y_train = X_train.to(device), y_train.to(device)
X_test, y_test = X_test.to(device), y_test.to(device)

for epoch in range(epochs):
    # 1. Forward pass
    y_logits = model_3(X_train).squeeze()
    y_pred = torch.round(torch.sigmoid(y_logits)) # logits -> prediction probabilities -> prediction labels
    
    # 2. Calculate loss and accuracy
    loss = loss_fn(y_logits, y_train) # BCEWithLogitsLoss calculates loss using logits
    acc = accuracy_fn(y_true=y_train, 
                      y_pred=y_pred)
    
    # 3. Optimizer zero grad
    optimizer.zero_grad()

    # 4. Loss backward
    loss.backward()

    # 5. Optimizer step
    optimizer.step()

    ### Testing
    model_3.eval()
    with torch.inference_mode():
      # 1. Forward pass
      test_logits = model_3(X_test).squeeze()
      test_pred = torch.round(torch.sigmoid(test_logits)) # logits -> prediction probabilities -> prediction labels
      # 2. Calcuate loss and accuracy
      test_loss = loss_fn(test_logits, y_test)
      test_acc = accuracy_fn(y_true=y_test,
                             y_pred=test_pred)

    # Print out what's happening
    if epoch % 100 == 0:
        print(f"Epoch: {epoch} | Loss: {loss:.5f}, Accuracy: {acc:.2f}% | Test Loss: {test_loss:.5f}, Test Accuracy: {test_acc:.2f}%")

[x15-eth]

It's been solved thanks. The squeeze() method was returning an Attribute error because there were some typo errors when I was creating the class for the model