Forward pass, loss, backward, step in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to perform a forward pass using the model.

PyTorch

outputs = model([1])

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

Aloss

Blabels

Coptimizer

Dinputs

Attempts:

3 left

💡 Hint

Common Mistakes

Using labels instead of inputs for the forward pass.

Passing the optimizer to the model.

The forward pass uses the input data to get predictions from the model.

2fill in blank

medium

Complete the code to calculate the loss between outputs and labels.

PyTorch

loss = criterion(outputs, [1])

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

Alabels

Binputs

Coptimizer

Dmodel

Attempts:

3 left

💡 Hint

Common Mistakes

Using inputs instead of labels for loss calculation.

Passing the model or optimizer instead of labels.

Loss compares the model's outputs to the true labels to measure error.

3fill in blank

hard

Fix the error in the code to perform backpropagation.

PyTorch

loss.[1]()

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

Astep

Bbackward

Cforward

Dzero_grad

Attempts:

3 left

💡 Hint

Common Mistakes

Calling step() on loss instead of optimizer.

Calling zero_grad() on loss.

Calling backward() computes gradients for backpropagation.

4fill in blank

hard

Fill both blanks to reset gradients and update model parameters.

PyTorch

optimizer.[1]()
optimizer.[2]()

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

Azero_grad

Bstep

Cbackward

Dforward

Attempts:

3 left

💡 Hint

Common Mistakes

Calling backward() or forward() on optimizer.

Not clearing gradients before the step.

First, gradients are cleared with zero_grad(). Then, step() updates the model weights.

5fill in blank

hard

Fill all three blanks to complete a training step: forward pass, loss calculation, and backward pass.

PyTorch

outputs = model([1])
loss = criterion(outputs, [2])
loss.[3]()

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

Ainputs

Blabels

Cbackward

Doptimizer

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up inputs and labels in loss calculation.

Forgetting to call backward on loss.

The training step starts with inputs to get outputs, then calculates loss with labels, and finally calls backward() to compute gradients.