Validation loop in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of a simple PyTorch validation loop

What will be the printed output after running this PyTorch validation loop snippet?

PyTorch

import torch
from torch import nn

model = nn.Linear(2, 1)
model.eval()

inputs = torch.tensor([[1.0, 2.0], [3.0, 4.0]])
targets = torch.tensor([[1.0], [2.0]])

criterion = nn.MSELoss()

with torch.no_grad():
    outputs = model(inputs)
    loss = criterion(outputs, targets)
    print(f"Loss: {loss.item():.4f}")

A Loss: 2.0000

B Loss: 1.0000

C Loss: 0.0000

D Loss: 0.5000

💡 Hint

Remember that the model is untrained and initialized randomly, so the loss won't be zero.

The model is a linear layer with random weights. The mean squared error loss between the model's output and targets will be around 0.5 for this input.

❓ Model Choice

intermediate

Choosing the correct model mode during validation

Which PyTorch model mode should be set during the validation loop to ensure correct behavior of layers like dropout and batch normalization?

A model.train()

B model.eval()

C model.freeze()

D model.validate()

💡 Hint

Think about which mode disables dropout and uses running statistics for batch norm.

During validation, model.eval() sets the model to evaluation mode, disabling dropout and using running statistics for batch normalization, which is the correct behavior.

❓ Metrics

advanced

Calculating average validation accuracy

Given a validation loop that accumulates correct predictions and total samples, which formula correctly computes the average validation accuracy?

A accuracy = total_correct / total_samples

B accuracy = total_samples / total_correct

C accuracy = total_correct * total_samples

D accuracy = total_correct - total_samples

💡 Hint

Accuracy is the fraction of correct predictions out of all predictions.

Accuracy is calculated as the number of correct predictions divided by the total number of samples evaluated.

🔧 Debug

advanced

Identifying the error in this validation loop snippet

What error will this PyTorch validation loop code raise?

PyTorch

model.eval()
correct = 0
total = 0

for inputs, labels in val_loader:
    outputs = model(inputs)
    predicted = torch.argmax(outputs, dim=1)
    correct += (predicted == labels).sum().item()
    total += labels.size(0)

accuracy = correct / total
print(f"Validation accuracy: {accuracy:.2f}")

A RuntimeError due to missing torch.no_grad() context

B ValueError because torch.argmax needs a dimension argument

C TypeError because predicted and labels have incompatible shapes

D No error, code runs correctly

💡 Hint

Check the shapes of predicted and labels tensors before comparison.

torch.argmax without dimension returns a single value, but labels is a batch tensor. Comparing them causes a shape mismatch and TypeError.

🧠 Conceptual

expert

Purpose of torch.no_grad() in validation loops

Why is it important to use torch.no_grad() during the validation loop in PyTorch?

A It disables gradient calculation to reduce memory usage and speed up computations

B It enables gradient calculation for validation metrics

C It resets model weights to initial values before validation

D It automatically switches the model to evaluation mode

💡 Hint

Think about what happens when gradients are not needed.

torch.no_grad() disables gradient tracking, which reduces memory use and speeds up validation since no backward pass is needed.

Practice

1. What is the main purpose of a validation loop in PyTorch?

easy

A. To update the model weights during training

B. To check how well the model performs on unseen data

C. To load the training dataset

D. To save the model to disk

Solution

1. Step 1: Understand the role of validation

   The validation loop is used to test the model on new data that it has not seen during training.

2. Step 2: Differentiate from training

   Unlike training, validation does not update model weights but measures performance like accuracy or loss.

3. Final Answer:

   To check how well the model performs on unseen data -> Option B

4. Quick Check:

   Validation loop = test model on new data [OK]

Hint: Validation loop tests model without changing weights [OK]

Common Mistakes:

• Confusing validation with training
• Thinking validation updates model weights
• Mixing validation with data loading

2. Which PyTorch code snippet correctly sets the model for validation?

easy

A. model.eval()

B. model.train()

C. model.validate()

D. model.test()

Solution

1. Step 1: Recall PyTorch model modes

   In PyTorch, model.eval() sets the model to evaluation mode, disabling dropout and batch norm updates.

2. Step 2: Identify correct method for validation

   Validation requires evaluation mode, so model.eval() is correct; others do not exist or are for training.

3. Final Answer:

   model.eval() -> Option A

4. Quick Check:

   Use model.eval() for validation [OK]

Hint: Use model.eval() to disable training behaviors [OK]

Common Mistakes:

• Using model.train() during validation
• Assuming model.validate() exists
• Confusing test() with eval()

3. What will be the output of the following validation loop snippet?

model.eval()
correct = 0
with torch.no_grad():
    for inputs, labels in val_loader:
        outputs = model(inputs)
        predicted = outputs.argmax(dim=1)
        correct += (predicted == labels).sum().item()
accuracy = correct / len(val_loader.dataset)
print(f"Accuracy: {accuracy:.2f}")

medium

A. Prints loss value instead of accuracy

B. Raises an error because of missing optimizer

C. Prints the accuracy of the model on validation data

D. Prints training accuracy instead of validation accuracy

Solution

1. Step 1: Analyze the code logic

   The code sets model to eval mode, disables gradient calculation, and counts correct predictions over validation data.

2. Step 2: Understand the output calculation

   Accuracy is computed as correct predictions divided by total validation samples, then printed.

3. Final Answer:

   Prints the accuracy of the model on validation data -> Option C

4. Quick Check:

   Validation loop code prints accuracy [OK]

Hint: Check if code counts correct predictions for accuracy [OK]

Common Mistakes:

• Expecting loss instead of accuracy
• Thinking optimizer is needed in validation
• Confusing training and validation accuracy

4. Identify the error in this validation loop code:

model.eval()
for inputs, labels in val_loader:
    outputs = model(inputs)
    loss = criterion(outputs, labels)
    loss.backward()
    total_loss += loss.item()

medium

A. Not zeroing gradients before backward

B. Not using model.train() before loop

C. Missing optimizer.step() after loss.backward()

D. Calling loss.backward() during validation

Solution

1. Step 1: Understand validation loop purpose

   Validation should not update model weights or compute gradients, so backward() is not needed.

2. Step 2: Identify the error

   Calling loss.backward() computes gradients, which is incorrect in validation; it wastes resources and may cause errors.

3. Final Answer:

   Calling loss.backward() during validation -> Option D

4. Quick Check:

   No backward() in validation loop [OK]

Hint: No backward() in validation, only in training [OK]

Common Mistakes:

• Running backward() in validation
• Confusing train and eval modes
• Forgetting torch.no_grad() in validation

5. You want to add accuracy tracking in your validation loop. Which code snippet correctly computes and updates accuracy inside the loop?

model.eval()
total_correct = 0
total_samples = 0
with torch.no_grad():
    for inputs, labels in val_loader:
        outputs = model(inputs)
        predicted = outputs.argmax(dim=1)
        # What goes here?
accuracy = total_correct / total_samples
print(f"Validation Accuracy: {accuracy:.2f}")

hard

A. total_correct += (predicted == labels).sum().item()
total_samples += labels.size(0)

B. total_correct += predicted.sum().item()
total_samples += labels.size(0)

C. total_correct += (predicted != labels).sum().item()
total_samples += labels.size(0)

D. total_correct += (predicted == labels).sum()
total_samples += len(val_loader)

Solution

1. Step 1: Calculate correct predictions

   Use (predicted == labels).sum().item() to count correct predictions as a Python number.

2. Step 2: Update total samples count

   Use labels.size(0) to add the batch size to total samples for accurate accuracy calculation.

3. Final Answer:

   total_correct += (predicted == labels).sum().item() total_samples += labels.size(0) -> Option A

4. Quick Check:

   Sum correct matches and batch size for accuracy [OK]

Hint: Sum correct predictions and batch size for accuracy [OK]

Common Mistakes:

• Summing predicted values instead of correct matches
• Using != instead of == for correct count
• Adding batch count incorrectly as len(val_loader)