Torch MSE Loss - Python

MSE (Mean Squared Error) is a common loss function used in machine learning for regression problems, where the goal is to predict a continuous value. It measures the average of the squared differences between the predicted and actual values. In PyTorch, this function is provided as the nn.MSELoss() module.

Syntax

loss_fn = nn.MSELoss()
output = loss_fn(predicted, actual)

• predicted : predicted tensor of shape (batch_size, *).
• actual: ground truth tensor of shape (batch_size, *).
• batch_size: number of images or samples in a batch.
• *: represents any number of dimensions.

Example

import torch
import torch.nn as nn

# Define the tensors
predicted = torch.tensor([1.0, 2.1, 3.0, 4.2])
actual = torch.tensor([0.9, 2.2, 3.1, 4.3])

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

# Calculate the loss
loss = loss_fn(predicted, actual)

# Print the loss
print(loss)

Output:

tensor(0.0075)

Conclusion

In this tutorial, we learned how to use the MSE loss function in PyTorch. MSE loss is commonly used in regression problems, where the goal is to predict a continuous value. We also saw how to calculate the loss using the nn.MSELoss() module in PyTorch.