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.