Difficulty setting batch size correctltly in 2 layer RNN

I am building an RNN that makes a multi-class classification output for 11 dimensions in the output. The input are word embeddings that I took from a pretrained glove model.

The error I get is (full traceback at the end of the question):

ValueError: Expected input batch_size (1) to match target batch_size (11).

Note that here I use batch_size=1, and the error says “expected batch size 1 to match target batch_size (11)”. However, if I change batch size to 11, the error changes to:

ValueError: Expected input batch_size (11) to match target batch_size (121).

I think that the error is coming from the shape of text which is torch.Size([11, 300]), which lacks a sequence length, but I thought that if I do not assign a seq length it defaults to 1. However, I do not know how to add this in.

Training loop:

def train(model, device, train_loader, valid_loader, epochs, learning_rate):

  criterion = nn.CrossEntropyLoss()
  optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
  
  train_loss, validation_loss = [], []
  train_acc, validation_acc = [], []

  for epoch in range(epochs):
    #train
    model.train()
    running_loss = 0.
    correct, total = 0, 0
    steps = 0
    for idx, batch in enumerate(train_loader):
      text = batch["Sample"].to(device)
      target = batch['Class'].to(device)
      print(text.shape, target.shape)
      text, target = text.to(device), target.to(device)
      # add micro for coding training loop
      optimizer.zero_grad()
      print(text.shape)
      output, hidden = model(text.unsqueeze(1))
      #print(output.shape, target.shape, target.view(-1).shape)
      loss = criterion(output, target.view(-1))
      loss.backward()
      optimizer.step()
      steps += 1
      running_loss += loss.item()

      # get accuracy
      _, predicted = torch.max(output, 1)
      print(predicted)
      #predicted = torch.round(output.squeeze())
      total += target.size(0)
      correct += (predicted == target).sum().item()

    train_loss.append(running_loss/len(train_loader))
    train_acc.append(correct/total)

    print(f'Epoch: {epoch + 1}, '
          f'Training Loss: {running_loss/len(train_loader):.4f}, '
          f'Training Accuracy: {100*correct/total: .2f}%')

    # evaluate on validation data
    model.eval()
    running_loss = 0.
    correct, total = 0, 0

    with torch.no_grad():
      for idx, batch in enumerate(valid_loader):
        text = batch["Sample"].to(device)
        print(type(text), text.shape)
        target = batch['Class'].to(device)
        target = torch.autograd.Variable(target).long()
        text, target = text.to(device), target.to(device)

        optimizer.zero_grad()
        output = model(text)
        
        loss = criterion(output, target)
        running_loss += loss.item()

        # get accuracy
        _, predicted = torch.max(output, 1)
        #predicted = torch.round(output.squeeze())
        total += target.size(0)
        correct += (predicted == target).sum().item()

    validation_loss.append(running_loss/len(valid_loader))
    validation_acc.append(correct/total)

    print (f'Validation Loss: {running_loss/len(valid_loader):.4f}, '
           f'Validation Accuracy: {100*correct/total: .2f}%')

  return train_loss, train_acc, validation_loss, validation_acc

This is how I call the training loop:

# Model hyperparamters
#vocab_size = len(word_array)
learning_rate = 1e-3
hidden_dim = 100
output_size = 11
input_size = 300
epochs = 10
n_layers = 2

# Initialize model, training and testing
set_seed(SEED)
vanilla_rnn_model = VanillaRNN(input_size, output_size, hidden_dim, n_layers)
vanilla_rnn_model.to(DEVICE)
vanilla_rnn_start_time = time.time()
vanilla_train_loss, vanilla_train_acc, vanilla_validation_loss, vanilla_validation_acc = train(vanilla_rnn_model,
                                                                                               DEVICE,
                                                                                               train_loader,
                                                                                               valid_loader,
                                                                                               epochs = epochs,
                                                                                               learning_rate = learning_rate)

This is how I create the dataloaders:

# Splitting dataset
# define a batch_size, I'll use 4 as an example
batch_size = 1

train_dset = CustomDataset(X2, y)  # create data set
train_loader = DataLoader(train_dset, batch_size=batch_size, shuffle=True) #load data with batch size
valid_dset = CustomDataset(X2, y)
valid_loader = DataLoader(valid_dset, batch_size=batch_size, shuffle=True)

g_seed = torch.Generator()
g_seed.manual_seed(SEED)

Full traceback:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-23-bfd2f8f3456f> in <module>()
     19                                                                                                valid_loader,
     20                                                                                                epochs = epochs,
---> 21                                                                                                learning_rate = learning_rate)
     22 print("--- Time taken to train = %s seconds ---" % (time.time() - vanilla_rnn_start_time))
     23 #test_accuracy = test(vanilla_rnn_model, DEVICE, test_iter)

3 frames
<ipython-input-22-16748701034f> in train(model, device, train_loader, valid_loader, epochs, learning_rate)
     47       output, hidden = model(text.unsqueeze(1))
     48       #print(output.shape, target.shape, target.view(-1).shape)
---> 49       loss = criterion(output, target.view(-1))
     50       loss.backward()
     51       optimizer.step()

/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
   1049         if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1050                 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1051             return forward_call(*input, **kwargs)
   1052         # Do not call functions when jit is used
   1053         full_backward_hooks, non_full_backward_hooks = [], []

/usr/local/lib/python3.7/dist-packages/torch/nn/modules/loss.py in forward(self, input, target)
   1119     def forward(self, input: Tensor, target: Tensor) -> Tensor:
   1120         return F.cross_entropy(input, target, weight=self.weight,
-> 1121                                ignore_index=self.ignore_index, reduction=self.reduction)
   1122 
   1123 

/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction)
   2822     if size_average is not None or reduce is not None:
   2823         reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 2824     return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
   2825 
   2826 

ValueError: Expected input batch_size (1) to match target batch_size (11).

Answer

You should not be using .view(-1). This line:

loss = criterion(output, target.view(-1))

should be:

loss = criterion(output, target)

It is effectively removing your batch dimension. For batch_size=1, it changes (1, 11) to (11,). When you changed batch_size to 11, then the view changed the shape from (11, 11) to (121,), hence the error.