Loss functions (MSELoss, CrossEntropyLoss) in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a Mean Squared Error loss function in PyTorch.

PyTorch

import torch.nn as nn
loss_fn = nn.[1]()

Drag options to blanks, or click blank then click option'

ABCELoss

BMSELoss

CL1Loss

DCrossEntropyLoss

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing CrossEntropyLoss which is for classification tasks.

Using BCELoss which is for binary classification.

The Mean Squared Error loss function in PyTorch is nn.MSELoss(). It measures the average squared difference between predicted and true values.

2fill in blank

medium

Complete the code to create a Cross Entropy loss function in PyTorch.

PyTorch

import torch.nn as nn
loss_fn = nn.[1]()

Drag options to blanks, or click blank then click option'

AL1Loss

BMSELoss

CCrossEntropyLoss

DNLLLoss

Attempts:

3 left

💡 Hint

Common Mistakes

Using MSELoss for classification tasks.

Using NLLLoss directly without applying LogSoftmax.

The Cross Entropy loss function in PyTorch is nn.CrossEntropyLoss(). It is used for multi-class classification problems.

3fill in blank

hard

Fix the error in the code to compute the loss between predictions and targets using MSELoss.

PyTorch

import torch
import torch.nn as nn

predictions = torch.tensor([2.5, 0.0, 2.1])
targets = torch.tensor([3.0, -0.5, 2.0])

loss_fn = nn.MSELoss()
loss = loss_fn([1], targets)
print(loss.item())

Drag options to blanks, or click blank then click option'

Atargets.detach()

Btargets

Cpredictions.detach()

Dpredictions

Attempts:

3 left

💡 Hint

Common Mistakes

Swapping predictions and targets in the loss function.

Using detached tensors which breaks gradient flow.

The first argument to the loss function should be the model's predictions. Here, predictions is correct.

4fill in blank

hard

Fill both blanks to compute Cross Entropy loss for classification outputs and labels.

PyTorch

import torch
import torch.nn as nn

outputs = torch.tensor([[1.0, 2.0, 0.5], [0.5, 1.5, 1.0]])
labels = torch.tensor([1, [1]])

loss_fn = nn.CrossEntropyLoss()
loss = loss_fn(outputs, [2])
print(loss.item())

Drag options to blanks, or click blank then click option'

A0

Blabels

C2

D3

Attempts:

3 left

💡 Hint

Common Mistakes

Using label values outside the range of classes.

Passing outputs as labels or vice versa.

The labels tensor contains class indices. The second label is class 2. The loss function takes outputs and labels as arguments.

5fill in blank

hard

Fill all three blanks to create MSE loss and compute it between predictions and targets.

PyTorch

import torch
import torch.nn as nn

predictions = torch.tensor([[1], [2], 2.0])
targets = torch.tensor([3.0, 0.0, [3]])

loss_fn = nn.MSELoss()
loss = loss_fn(predictions, targets)
print(loss.item())

Drag options to blanks, or click blank then click option'

A2.5

B0.0

C2.1

D3.0

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up prediction and target values.

Using values not consistent with the example.

The predictions tensor has values 2.5, 0.0, and 2.0. The targets tensor has 3.0, 0.0, and 2.1. These values match the example for computing MSE loss.

Practice

1. Which loss function in PyTorch is best suited for predicting continuous values like house prices?

easy

A. torch.nn.MSELoss

B. torch.nn.CrossEntropyLoss

C. torch.nn.BCELoss

D. torch.nn.NLLLoss

Solution

1. Step 1: Understand the type of prediction

   Predicting house prices is a regression problem where output is continuous.

2. Step 2: Match loss function to problem type

   MSELoss calculates mean squared error, ideal for continuous outputs. CrossEntropyLoss is for classification, not regression.

3. Final Answer:

   torch.nn.MSELoss -> Option A

4. Quick Check:

   Regression uses MSELoss = C [OK]

Hint: Use MSELoss for continuous outputs, CrossEntropyLoss for classes [OK]

Common Mistakes:

• Choosing CrossEntropyLoss for regression tasks
• Confusing BCELoss with MSELoss
• Using NLLLoss without log probabilities

2. Which of the following is the correct way to create a CrossEntropyLoss object in PyTorch?

easy

A. loss = torch.nn.CrossEntropy()

B. loss = torch.nn.MSELoss()

C. loss = torch.nn.CrossEntropyLoss()

D. loss = torch.CrossEntropyLoss()

Solution

1. Step 1: Recall PyTorch loss function syntax

   Loss functions are in torch.nn and instantiated with parentheses.

2. Step 2: Identify correct class name and module

   CrossEntropyLoss is the correct class name under torch.nn. Options A misses 'Loss' and C misses 'nn'.

3. Final Answer:

   loss = torch.nn.CrossEntropyLoss() -> Option C

4. Quick Check:

   Correct class and module = D [OK]

Hint: Use torch.nn.CrossEntropyLoss() exactly for classification loss [OK]

Common Mistakes:

• Missing parentheses when creating loss object
• Using torch.CrossEntropyLoss() instead of torch.nn.CrossEntropyLoss()
• Confusing MSELoss with CrossEntropyLoss

3. What will be the output loss value when using torch.nn.MSELoss on predictions tensor([2.0, 3.0]) and targets tensor([1.0, 5.0])?

medium

A. 2.5

B. 3.0

C. 1.5

D. 4.0

Solution

1. Step 1: Calculate squared differences

   Differences: (2.0-1.0)=1.0, (3.0-5.0)=-2.0; squared: 1.0, 4.0

2. Step 2: Compute mean of squared differences

   Mean = (1.0 + 4.0) / 2 = 2.5

3. Final Answer:

   2.5 -> Option A

4. Quick Check:

   MSE = mean squared error = 2.5 [OK]

Hint: Square errors, then average for MSELoss output [OK]

Common Mistakes:

• Forgetting to square the differences
• Summing without averaging
• Mixing up prediction and target order

4. Given this code snippet, what is the error?

import torch
loss_fn = torch.nn.CrossEntropyLoss()
pred = torch.tensor([[0.2, 0.8], [0.6, 0.4]])
target = torch.tensor([1, 0])
loss = loss_fn(pred, target)
print(loss.item())

medium

A. Loss function should be MSELoss for this target

B. Target tensor should be one-hot encoded

C. No error, code runs correctly

D. Predictions should be raw scores (logits), not probabilities

Solution

1. Step 1: Check input requirements for CrossEntropyLoss

   CrossEntropyLoss expects raw scores (logits), not probabilities.

2. Step 2: Analyze given predictions

   Predictions are probabilities (sum to 1), so applying CrossEntropyLoss directly causes incorrect loss calculation.

3. Final Answer:

   Predictions should be raw scores (logits), not probabilities -> Option D

4. Quick Check:

   CrossEntropyLoss needs logits = A [OK]

Hint: Use logits, not probabilities, with CrossEntropyLoss [OK]

Common Mistakes:

• Passing probabilities instead of logits to CrossEntropyLoss
• Using one-hot targets instead of class indices
• Confusing MSELoss with CrossEntropyLoss for classification

5. You have a multi-class classification problem with 4 classes. Your model outputs raw scores (logits) of shape (batch_size, 4). Which loss function and target format should you use in PyTorch?

hard

A. Use torch.nn.MSELoss with target as one-hot vectors

B. Use torch.nn.CrossEntropyLoss with target as class indices (0 to 3)

C. Use torch.nn.BCELoss with target as class indices

D. Use torch.nn.CrossEntropyLoss with target as one-hot vectors

Solution

1. Step 1: Identify loss function for multi-class classification

   CrossEntropyLoss is designed for multi-class classification with logits.

2. Step 2: Determine correct target format

   CrossEntropyLoss expects target as class indices (integers), not one-hot vectors.

3. Final Answer:

   Use torch.nn.CrossEntropyLoss with target as class indices (0 to 3) -> Option B

4. Quick Check:

   CrossEntropyLoss + class indices = B [OK]

Hint: CrossEntropyLoss needs logits and integer class labels [OK]

Common Mistakes:

• Passing one-hot vectors as targets to CrossEntropyLoss
• Using MSELoss for classification
• Using BCELoss for multi-class without sigmoid