ValueError: Using a target size (torch.Size([2, 1])) that is different to the input size (torch.Size([2])) is deprecated. Please ensure they have the same size

1

Hello. I am using a loss function BCE Loss for Siamese Network. The inputs to loss function are target (y_true) and input (dy) in my case. 'dy' is the pairwise distance between output embeddings produced from siamese network and 'y_true' are the true labels.

The true labels are between 0 and 1, and dy is also between 0 and 1.

When I use the above loss function, it gives me the error:
ValueError: Using a target size (torch.Size([2, 1])) that is different to the input size (torch.Size([2])) is deprecated. Please ensure they have the same size.

The following code is for train_epoch function:

def train_epoch(train_loader, model, loss_fn, optimizer, cuda, log_interval, metrics):
    for metric in metrics:
        metric.reset()

    model.train()
    losses = []
    total_loss = 0


    for batch_idx, ((x0, x1), y) in enumerate(train_loader):

        x0, x1, y_true = x0.cpu(), x1.cpu(), y.cpu()
        #y_true = (y_true, (2,))
        optimizer.zero_grad()
        output1, output2 = model(x0, x1)

        #output1 = np.reshape(output1, (2,1))
        #output2 = np.reshape(output2, (2,1))
        #y_true = np.reshape(y_true, (2))


        #print('output1 is:', output1)
        #print('output2 is:', output2)
        #print('y_true is', y_true)

        '''Distance metric - PairwiseDistance'''
        p_dist = torch.nn.PairwiseDistance(keepdim=True)

        dy = p_dist(output1, output2)
        #dy = torch.reshape(dy, (2,1))
        #print('dy_shape after squeeze', dy.size())
        dy = torch.nan_to_num(dy)
        #y_true = torch.reshape(y_true, (2,))
        #print('y_true_shape after squeeze', y_true.size())
        y_true = torch.nan_to_num(y_true)
        #print('dy is:', dy)

        '''2 lines indicated the normalization of dy to 0 and 1 by dividing it with max value'''

        maximum_dy = torch.max(dy)
        maximum_dy = torch.nan_to_num(maximum_dy)
        #print('maximum dy is', maximum_dy )
        dy = dy/maximum_dy

        #print('dy after max is', dy)
        #print('y_true is', y_true)

        maximum_y_true = torch.max(y_true)
        maximum_y_true = torch.nan_to_num(maximum_y_true)

        #print('maximum y_true is', maximum_y_true)
        y_true = y_true/maximum_y_true

        #print(' y_true after max is', y_true)

        #print('dy_shape:', dy.size(), 'y_true_shape:', y_true.size())

        #print('dy_shape after squeeze', dy.size())


        dy = torch.unsqueeze(dy,1)
        y_true = torch.unsqueeze(y_true, 1)
        loss = loss_fn(dy, y_true)
        loss.backward()
        optimizer.step()

        losses.append(loss.item())
        total_loss += loss.item()

        for metric in metrics:
            metric(dy, y_true)
        for metric in metrics:
            metric.total = (batch_idx+1)*y_true.shape[0]

        if batch_idx % log_interval == 0:
            message = 'Train: [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                batch_idx, len(train_loader),
                100. * batch_idx / len(train_loader), np.mean(losses))
            for metric in metrics:
                message += '\t{}: {}'.format(metric.name(), metric.value())

            print(message)
            losses = []

    total_loss /= (batch_idx + 1)
    return total_loss, metrics

Following code is where the loss function is called:

loss_fn = torch.nn.BCELoss()
lr = 1e-3
optimizer = optim.SGD(model.parameters(), lr=lr)
scheduler = lr_scheduler.StepLR(optimizer, 8, gamma=0.1, last_epoch=-1)
n_epochs = 2
log_interval = 1

I would appreciate some help here @ptrblck

Thanks in advance.

2

The target is of shape 2 x 1 while the input is 2, so you could use either target.squeeze(-1) or input.unsqueeze(-1) to make them match (but, obviously, not both or you’d have the symmetric mismatch).

Best regards

Thomas

3

Thank you for your help @tom

4 
from torch.utils.data import DataLoader
from torchvision import datasets

import torchvision.transforms as transforms
import torch.optim as optim
import torch.nn as nn


class BinaryCNN(nn.Module):
    def __init__(self, num_classes):
        super(BinaryCNN, self).__init__()
        self.feature_extractor = nn.Sequential(
            nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Flatten(),
            nn.Linear(64 * 16 * 16, out_features=num_classes)
         )

        self.classifier = nn.Sigmoid()

    def forward(self, x):
        x = self.feature_extractor(x)
        x = self.classifier(x)
        return x


train_dir = '/images_dataset/train/'
train_transform = transforms.Compose([
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Resize((64, 64))
])

train_dataset = datasets.ImageFolder(root=train_dir,
                                     transform=train_transform)

dataloader_train = DataLoader(train_dataset, batch_size=1, shuffle=True)

cnn = BinaryCNN(num_classes=1)
criterion = nn.BCELoss()
optimizer = optim.Adam(cnn.parameters(), lr=.01)

for epoch in range(2):
    running_loss = 0.0
    for images, labels in dataloader_train:
        optimizer.zero_grad()
        outputs = cnn(images)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()

    epoch_loss = running_loss / len(dataloader_train)
    print(f'Epoch {epoch + 1}, Loss: {epoch_loss}')

Hi All, I am trying to build an image classifier to classify dogs and cats. This particular code throws this error:

ValueError: Using a target size (torch.Size([1])) that is different to the input size (torch.Size([1, 1])) is deprecated. Please ensure they have the same size.

I tried .unsqueeze(1) but it throws the same error. What am I doing wrong in this code? Please suggest.

The Problem is with loss function, but can’t figure out how to fix it.