Pytorch: 1D target tensor expected, multi-target not supported

I want to train a 1D CNN on time series. I get the following error message 1D target tensor expected, multi-target not supported

Here is the code with simulated data corresponding to the structures of my data as well as the error message

import torch
from torch.utils.data import DataLoader
import torch.utils.data as data
import torch.nn as nn

import numpy as np
import random
from tqdm.notebook import tqdm

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(device)


train_dataset = []
n_item = 20
for i in range(0,n_item):
    train_data = np.random.uniform(-10, 10, 500)
    train_dataset.append(train_data)
train_dataset = np.asarray(train_dataset)
train_dataset.shape
ecg_train = torch.from_numpy(train_dataset).float()
labels_train = np.random.randint(2, size=n_item)
labels_train = torch.from_numpy(labels_train).long()


val_dataset = []
n_item = 10
for i in range(0,n_item):
    val_data = np.random.uniform(-10, 10, 500)
    val_dataset.append(val_data)
val_dataset = np.asarray(val_dataset)
val_dataset.shape
ecg_validation = torch.from_numpy(val_dataset).float()
labels_validation = np.random.randint(2, size=n_item)
labels_validation = torch.from_numpy(labels_validation).long()

class ECGNet(data.Dataset):
    """ImageNet Limited dataset."""
    
    def __init__(self, ecgs, labls, transform=None):
            self.ecg = ecgs
            self.target = labls
            self.transform = transform

    def __getitem__(self, idx):
        ecgVec = self.ecg[idx] #.reshape(10, -1)
        labelID = self.target[idx].reshape(1)

        return ecgVec,labelID

    def __len__(self):
        return len(self.ecg)


train_data = ECGNet(ecg_train, 
                             labels_train, 
                   )
print("size of Training dataset: {}".format(len(train_data)))

validation_data = ECGNet(ecg_validation, 
                             labels_validation, 
                   )
print("size of Training dataset: {}".format(len(validation_data)))


batch_size = 1
train_dataloader = DataLoader(dataset = train_data,
                              batch_size=batch_size, 
                              shuffle = True, 
                              num_workers = 0)

val_dataloader = DataLoader(dataset = validation_data,
                              batch_size=batch_size, 
                              shuffle = True, 
                              num_workers = 0)


def train_epoch(model, train_dataloader, optimizer, loss_fn):
    losses = []
    correct_predictions = 0
    # Iterate mini batches over training dataset
    for images, labels in tqdm(train_dataloader):
        images = images.to(device)
    #labels = labels.squeeze_()
        labels = labels.to(device)

        #labels = labels.to(device=device, dtype=torch.int64)
        # Run predictions
        output = model(images)
        # Set gradients to zero
        optimizer.zero_grad()
        # Compute loss
        loss = loss_fn(output, labels)
        # Backpropagate (compute gradients)
        loss.backward()
        # Make an optimization step (update parameters)
        optimizer.step()
        # Log metrics
        losses.append(loss.item())
        predicted_labels = output.argmax(dim=1)
        correct_predictions += (predicted_labels == labels).sum().item()
    accuracy = 100.0 * correct_predictions / len(train_dataloader.dataset)
    # Return loss values for each iteration and accuracy
    mean_loss = np.array(losses).mean()
    return mean_loss, accuracy

def evaluate(model, dataloader, loss_fn):
    losses = []
    correct_predictions = 0
    with torch.no_grad():
        for images, labels in dataloader:
            images = images.to(device)
            #labels = labels.squeeze_()
            labels = labels.to(device=device, dtype=torch.int64)
            # Run predictions
            output = model(images)
            # Compute loss
            loss = loss_fn(output, labels)
            # Save metrics
            predicted_labels = output.argmax(dim=1)
            correct_predictions += (predicted_labels == labels).sum().item()
            losses.append(loss.item())
    mean_loss = np.array(losses).mean()
    accuracy = 100.0 * correct_predictions / len(dataloader.dataset)
    # Return mean loss and accuracy
    return mean_loss, accuracy

def train(model, train_dataloader, val_dataloader, optimizer, n_epochs, loss_function):
    # We will monitor loss functions as the training progresses
    train_losses = []
    val_losses = []
    train_accuracies = []
    val_accuracies = []

    for epoch in range(n_epochs):
        model.train()
        train_loss, train_accuracy = train_epoch(model, train_dataloader, optimizer, loss_fn)
        model.eval()
        val_loss, val_accuracy = evaluate(model, val_dataloader, loss_fn)
        train_losses.append(train_loss)
        val_losses.append(val_loss)
        train_accuracies.append(train_accuracy)
        val_accuracies.append(val_accuracy)
        print('Epoch {}/{}: train_loss: {:.4f},        train_accuracy: {:.4f}, val_loss: {:.4f},        val_accuracy: {:.4f}'.format(epoch+1, n_epochs,
                                     train_losses[-1],
                                     train_accuracies[-1],
                                     val_losses[-1],
                                     val_accuracies[-1]))
    return train_losses, val_losses, train_accuracies, val_accuracies


class Simple1DCNN(torch.nn.Module):
    def __init__(self):
        super(Simple1DCNN, self).__init__()
        self.layer1 = torch.nn.Conv1d(in_channels=50, 
                                      out_channels=20, 
                                      kernel_size=5, 
                                      stride=2)
        self.act1 = torch.nn.ReLU()
        self.layer2 = torch.nn.Conv1d(in_channels=20, 
                                      out_channels=10, 
                                      kernel_size=1)
        
        self.fc1 = nn.Linear(10* 3, 2)
    def forward(self, x):
        print(x.shape)
        x = x.view(1, 50,-1)
        print(x.shape)
        x = self.layer1(x)
        print(x.shape)
        x = self.act1(x)
        print(x.shape)
        x = self.layer2(x)
        print(x.shape)
        x = x.view(1,-1)
        print(x.shape)
        x = self.fc1(x)
        print(x.shape)
        print(x)
        
        return x



model_a = Simple1DCNN()
model_a = model_a.to(device)

criterion = nn.CrossEntropyLoss()

loss_fn = torch.nn.CrossEntropyLoss()
n_epochs_a = 50
learning_rate_a = 0.01
alpha_a = 1e-5
momentum_a = 0.9
optimizer = torch.optim.SGD(model_a.parameters(), 
                            momentum = momentum_a,
                            nesterov = True,
                            weight_decay = alpha_a,
                            lr=learning_rate_a)
train_losses_a, val_losses_a, train_acc_a, val_acc_a = train(model_a,
                                                             train_dataloader,
                                                             val_dataloader,
                                                             optimizer,
                                                             n_epochs_a,
                                                             loss_fn
                                                            )

Error message:

cpu
size of Training dataset: 20
size of Training dataset: 10
  0%|          | 0/20 [00:00<?, ?it/s]
torch.Size([1, 500])
torch.Size([1, 50, 10])
torch.Size([1, 20, 3])
torch.Size([1, 20, 3])
torch.Size([1, 10, 3])
torch.Size([1, 30])
torch.Size([1, 2])
tensor([[ 0.5785, -1.0169]], grad_fn=<AddmmBackward>)
Traceback (most recent call last):
  File "SO_question.py", line 219, in <module>
    train_losses_a, val_losses_a, train_acc_a, val_acc_a = train(model_a,
  File "SO_question.py", line 137, in train
    train_loss, train_accuracy = train_epoch(model, train_dataloader, optimizer, loss_fn)
  File "SO_question.py", line 93, in train_epoch
    loss = loss_fn(output, labels)
  File "/Users/mymac/Documents/programming/python/mainenv/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/Users/mymac/Documents/programming/python/mainenv/lib/python3.8/site-packages/torch/nn/modules/loss.py", line 961, in forward
    return F.cross_entropy(input, target, weight=self.weight,
  File "/Users/mymac/Documents/programming/python/mainenv/lib/python3.8/site-packages/torch/nn/functional.py", line 2468, in cross_entropy
    return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
  File "/Users/mymac/Documents/programming/python/mainenv/lib/python3.8/site-packages/torch/nn/functional.py", line 2264, in nll_loss
    ret = torch._C._nn.nll_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
RuntimeError: 1D target tensor expected, multi-target not supported

What am I doing wrong?

Answer

You are using nn.CrossEntropyLoss as the criterion for your training. You correctly passed the labels as indices of the ground truth class: 0s and 1s. However, as the error message suggests, it needs to be a 1D tensor!

Simply remove the reshape in ECGNet‘s __getitem__:

def __getitem__(self, idx):
    ecgVec = self.ecg[idx]
    labelID = self.target[idx]
    return ecgVec,labelID

---

Edit

I want to increase the batch_size to 8. But now I get the error […]

You are doing a lot of broadcasting (flattening) which surely will affect the batch size. As a general rule of thumb never fiddle with axis=0. For instance, if you have an input shape of (8, 500), straight off you have a problem when doing x.view(1, 50, -1). Since the resulting tensor will be (1, 50, 80) (the desired shape would have been (8, 50, 10)). Instead, you could broadcast with x.view(x.size(0), 50, -1).

Same with x.view(1, -1) later down forward. You are looking to flatten the tensor, but you should not flatten it along with the batches, they need to stay separated! It’s safer to use torch.flatten, yet I prefer nn.Flatten which flattens from axis=1 to axis=-1 by default.

---

My personal advice is to start with a simple setup (without train loops etc…) to verify the architecture and intermediate output shapes. Then, add the necessary logic to handle the training.

class ECGNet(data.Dataset):
    """ImageNet Limited dataset."""
    
    def __init__(self, ecgs, labls, transform=None):
        self.ecg = ecgs
        self.target = labls
        self.transform = transform

    def __getitem__(self, idx):
        ecgVec = self.ecg[idx]
        labelID = self.target[idx]
        return ecgVec, labelID

    def __len__(self):
        return len(self.ecg)


class Simple1DCNN(nn.Module):
    def __init__(self):
        super(Simple1DCNN, self).__init__()
        self.layer1 = nn.Conv1d(in_channels=50, 
                                out_channels=20, 
                                kernel_size=5, 
                                stride=2)
        self.act1 = nn.ReLU()
        self.layer2 = nn.Conv1d(in_channels=20, 
                                out_channels=10, 
                                kernel_size=1)
        
        self.fc1 = nn.Linear(10*3, 2)
        self.flatten = nn.Flatten()

    def forward(self, x):
        x = x.view(x.size(0), 50, -1)
        x = self.layer1(x)
        x = self.act1(x)
        x = self.layer2(x)
        x = self.flatten(x)
        x = self.fc1(x)
        
        return x

batch_size = 8
train_data = ECGNet(ecg_train, labels_train)
train_dl = DataLoader(dataset=train_data,
                      batch_size=batch_size, 
                      shuffle=True,
                      num_workers=0)

model = Simple1DCNN()
criterion = nn.CrossEntropyLoss()

Then

>>> x, y = next(iter(train_dl))
>>> y_hat = model(x)

>>> y_hat.shape
torch.Size([8, 2])

Also, make sure your loss works:

>>> criterion(y_hat, y)
tensor(..., grad_fn=<NllLossBackward>)