Backward pass (loss.backward) in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to perform the backward pass and compute gradients.

PyTorch

loss.[1]()

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

Abackward

Bforward

Cstep

Dzero_grad

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'forward()' instead of 'backward()' which only runs the forward pass.

Calling 'step()' which updates parameters but does not compute gradients.

The backward() function computes the gradients of the loss with respect to model parameters.

2fill in blank

medium

Complete the code to reset gradients before the backward pass.

PyTorch

optimizer.[1]()

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

Azero_grad

Bstep

Cbackward

Dupdate

Attempts:

3 left

💡 Hint

Common Mistakes

Calling 'step()' before 'backward()' which updates parameters prematurely.

Not resetting gradients causing incorrect gradient sums.

The zero_grad() function clears old gradients before computing new ones.

3fill in blank

hard

Fix the error in the code to correctly perform a training step.

PyTorch

optimizer.zero_grad()
output = model(input)
loss = criterion(output, target)
loss.[1]()
optimizer.step()

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

Azero_grad

Bforward

Cstep

Dbackward

Attempts:

3 left

💡 Hint

Common Mistakes

Calling 'loss.step()' which does not exist.

Forgetting to call 'loss.backward()' causing no gradient computation.

The backward() call computes gradients needed before the optimizer updates parameters.

4fill in blank

hard

Fill both blanks to correctly compute loss and perform backward pass.

PyTorch

output = model(input)
loss = [1](output, target)
loss.[2]()

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

Acriterion

Boptimizer

Cbackward

Dforward

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'optimizer' instead of 'criterion' to compute loss.

Calling 'forward()' instead of 'backward()' on loss.

The loss is computed using the criterion function, then backward() computes gradients.

5fill in blank

hard

Fill all three blanks to complete a training step with gradient reset, loss computation, and backward pass.

PyTorch

optimizer.[1]()
output = model(input)
loss = [2](output, target)
loss.[3]()

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

Azero_grad

Bcriterion

Cbackward

Dstep

Attempts:

3 left

💡 Hint

Common Mistakes

Calling 'step()' before 'backward()' which updates parameters too early.

Not resetting gradients causing accumulation errors.

First reset gradients with zero_grad(), then compute loss with criterion, and finally call backward() to compute gradients.

Practice

1. What does the loss.backward() function do in PyTorch?

easy

A. It computes gradients of the loss with respect to model parameters.

B. It updates the model weights directly.

C. It calculates the loss value from predictions and targets.

D. It initializes the model parameters.

Solution

1. Step 1: Understand the role of loss.backward()

   This function computes gradients needed for updating model weights by backpropagation.

2. Step 2: Differentiate from other functions

   Updating weights is done by the optimizer, not loss.backward(). Calculating loss or initializing parameters are separate steps.

3. Final Answer:

   It computes gradients of the loss with respect to model parameters. -> Option A

4. Quick Check:

   Backward pass = compute gradients [OK]

Hint: Remember: backward() computes gradients, optimizer updates weights [OK]

Common Mistakes:

• Confusing backward() with optimizer step
• Thinking backward() calculates loss value
• Assuming backward() initializes parameters

2. Which of the following is the correct way to call the backward pass on a loss tensor named loss in PyTorch?

easy

A. loss.backwards()

B. loss.backward()

C. loss.backwarded()

D. loss.backward_pass()

Solution

1. Step 1: Recall PyTorch syntax for backward pass

   The correct method to compute gradients is loss.backward().

2. Step 2: Identify incorrect method names

   Other options are invalid method names and will cause errors.

3. Final Answer:

   loss.backward() -> Option B

4. Quick Check:

   Correct method name = backward() [OK]

Hint: Use exact method name: backward() with no extra letters [OK]

Common Mistakes:

• Adding extra letters or suffixes to backward
• Using plural form backwards
• Confusing method name with optimizer step

3. Consider the following PyTorch code snippet:

import torch
x = torch.tensor(2.0, requires_grad=True)
y = x ** 3
loss = y
loss.backward()
print(x.grad)

What will be the output of print(x.grad)?

medium

A. tensor(0.)

B. tensor(8.)

C. tensor(6.)

D. tensor(12.)

Solution

1. Step 1: Compute the derivative of y = x^3 at x=2

   The derivative dy/dx = 3 * x^2. At x=2, this is 3 * 4 = 12.

2. Step 2: Understand backward() computes this gradient

   Calling loss.backward() computes and stores this gradient in x.grad.

3. Final Answer:

   tensor(12.) -> Option D

4. Quick Check:

   Derivative of x^3 at 2 = 12 [OK]

Hint: Derivative of x^3 is 3x^2; plug in x=2 [OK]

Common Mistakes:

• Calculating derivative incorrectly as 8 or 6
• Forgetting to set requires_grad=True
• Not calling loss.backward() before accessing grad

4. What is the error in the following PyTorch code snippet?

import torch
x = torch.tensor(3.0, requires_grad=True)
y = x * 2
loss = y
# Missing backward call
print(x.grad)

medium

A. x.grad will be zero tensor automatically.

B. SyntaxError because backward() is missing.

C. x.grad will be None because backward() was not called.

D. RuntimeError because loss is not scalar.

Solution

1. Step 1: Identify missing backward() call

   The code does not call loss.backward(), so gradients are not computed.

2. Step 2: Understand gradient attribute behavior

   Without backward(), x.grad remains None, not zero or error.

3. Final Answer:

   x.grad will be None because backward() was not called. -> Option C

4. Quick Check:

   No backward() means no gradients [OK]

Hint: Always call loss.backward() before checking .grad [OK]

Common Mistakes:

• Expecting zero tensor instead of None
• Thinking missing backward() causes syntax error
• Assuming RuntimeError for non-scalar loss here

5. You have a model with parameters and a loss computed. You call loss.backward() twice in a row without zeroing gradients in between. What will happen to the gradients stored in the parameters?

hard

A. Gradients will accumulate, doubling the values from one backward call.

B. Gradients will reset to zero before the second backward call.

C. An error will be raised because backward() cannot be called twice.

D. Gradients will be overwritten by the second backward call.

Solution

1. Step 1: Understand gradient accumulation in PyTorch

   By default, gradients accumulate in the .grad attribute when backward() is called multiple times.

2. Step 2: Effect of calling backward() twice without zeroing

   Calling backward() twice adds gradients twice, effectively doubling them.

3. Final Answer:

   Gradients will accumulate, doubling the values from one backward call. -> Option A

4. Quick Check:

   Multiple backward calls add gradients [OK]

Hint: Call optimizer.zero_grad() to reset gradients before backward() [OK]

Common Mistakes:

• Assuming gradients reset automatically
• Expecting an error on second backward call
• Thinking gradients overwrite instead of accumulate