no_grad context manager in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of code using no_grad context manager

What is the output of this PyTorch code snippet?

PyTorch

import torch
x = torch.tensor([2.0], requires_grad=True)
with torch.no_grad():
    y = x * 3
print(y.requires_grad)

A None

B True

C Raises RuntimeError

D False

💡 Hint

Think about what no_grad does to the computation graph.

Inside the no_grad block, PyTorch does not track operations for gradients, so y.requires_grad is False.

🧠 Conceptual

intermediate

Purpose of no_grad context manager

What is the main purpose of using the no_grad context manager in PyTorch?

A To speed up computations by disabling gradient tracking

B To save the model parameters to disk

C To reset all gradients to zero

D To enable gradient tracking for all operations inside the block

💡 Hint

Think about when you do not need to update model weights.

no_grad disables gradient tracking, which reduces memory use and speeds up computations during inference.

❓ Metrics

advanced

Effect of no_grad on backward pass

Consider the following code. What happens when calling backward() on y inside the no_grad block?

PyTorch

import torch
x = torch.tensor([1.0], requires_grad=True)
with torch.no_grad():
    y = x * 2
    y.backward()

A Raises TypeError due to no_grad

B Computes gradients normally

C Raises RuntimeError because gradients are not tracked

D Returns None without error

💡 Hint

Can you call backward on a tensor that does not require gradients?

Inside no_grad, y does not track gradients, so calling backward() raises RuntimeError.

🔧 Debug

advanced

Why does this code raise an error?

This code raises an error. What is the cause?

PyTorch

import torch
x = torch.tensor([3.0], requires_grad=True)
with torch.no_grad():
    y = x * 4
z = y + 2
y.backward()

A y does not require grad, so backward() raises RuntimeError

B z is computed outside no_grad, causing error

C x does not require grad, causing error

D No error is raised

💡 Hint

Check if y requires gradients after no_grad block.

y was computed inside no_grad, so it does not track gradients. Calling backward() on y raises RuntimeError.

❓ Model Choice

expert

Choosing when to use no_grad in model evaluation

You want to evaluate a trained PyTorch model on test data without updating weights. Which is the best practice?

A Set requires_grad=True for all model parameters during evaluation

B Wrap the evaluation code with torch.no_grad() to disable gradient tracking

C Call model.train() before evaluation

D Manually zero gradients before evaluation

💡 Hint

Think about saving memory and speeding up inference.

Using torch.no_grad() during evaluation disables gradient tracking, saving memory and computation.