How do I fix this size of tensor error for my NN classifier PyTorch

user_4669536 0
Viewed 26

I'm having trouble understanding why this is throwing an error. This code is pulled directly from the PyTorch documentation for a NN classifier for the fashion MNIST dataset. However when I try to flip this to the MNIST handwritten digits data set it comes up with the following error:

RuntimeError: The size of tensor a (10) must match the size of tensor b (64) at non-singleton dimension 1

This occurs when using the loss function during the training loop function. Can anyone help me understand why this is happening. Thanks!

import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor, Lambda
import torchvision.models as models
import matplotlib.pyplot as plt

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
#device = "cpu"
print(f"Using {device} device")

training_data = datasets.MNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor()
)

test_data = datasets.MNIST(
    root="data",
    train=False,
    download=True,
    transform=ToTensor()
)

train_dataloader = DataLoader(training_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

class NeuralNetwork(nn.Module):
    def __init__(self):
        super(NeuralNetwork, self).__init__()
        self.flatten = nn.Flatten()
        self.linear_relu_stack = nn.Sequential(
            nn.Linear(28*28, 512),
            nn.ReLU(),
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Linear(512, 10),
        )

    def forward(self, x):
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits

def train_loop(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    for batch, (X, y) in enumerate(dataloader):
        # Compute prediction and loss
        X, y = X.to(device), y.to(device)
        pred = model(X)
        
        loss = loss_fn(pred, y)
        
        # Backpropagation
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if batch % 100 == 0:
            loss, current = loss.item(), batch * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")


def test_loop(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    test_loss, correct = 0, 0

    with torch.no_grad():
        for X, y in dataloader:
            X, y = X.to(device), y.to(device)
            pred = model(X)
            test_loss += loss_fn(pred, y).item()
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()

    test_loss /= num_batches
    correct /= size
    print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")
    
def save_checkpoint(state, filename = "checkpoint.pth.tar"):
    print("=> Saving checkpoint")
    torch.save(state, filename)

model = NeuralNetwork().to(device)

learning_rate = 1e-3
batch_size = 64
epochs = 10

# Initialize the loss function
loss_fn = nn.MSELoss()

optimiser = torch.optim.Adam(model.parameters(), lr=learning_rate)

for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")
    train_loop(train_dataloader, model, loss_fn, optimiser)
    test_loop(test_dataloader, model, loss_fn)
print("Done!")
pytorch neural-network python
1 Answers

torch.nn.MSELoss is an implemention of mean squared error. You can't measure the difference between two tensors if they're different sizes (MSELoss does not allow for broadcasting). So if you're using MSELoss, then the predictions and the targets must be the same shape. In your case, preds is a tensor of shape [64, 10], and y is a tensor of shape [64].

The reason y is of shape [64] rather than [64, 10] is that most classification dataset implementations represent targets as integer labels rather than one-hot encoded vectors. In theory, you could convert these integer label targets to one-hot encoded targets.

But in reality, since this is a classification problem, you should probably be using something like nn.CrossEntropyLoss rather than nn.MSELoss. The former is a conventional classification loss function, and it allows the targets to be integer labels rather than one-hot labels (so just swapping out MSELoss for CrossEntropyLoss should solve your problem). MSELoss is better suited for regression tasks and such.

user_41093260
Related