Gradient access (.grad) in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does the .grad attribute in PyTorch represent?

The .grad attribute holds the gradient of a tensor after backpropagation. It shows how much the tensor affects the final output.

beginner

When is the .grad attribute populated in PyTorch?

The .grad attribute is filled after calling backward() on a tensor that is part of a computation graph with requires_grad=True.

beginner

How do you enable gradient tracking for a tensor in PyTorch?

Set requires_grad=True when creating the tensor, for example: torch.tensor([1.0, 2.0], requires_grad=True).

beginner

What happens if you try to access .grad before calling backward()?

The .grad attribute will be None because gradients have not been computed yet.

intermediate

How can you clear gradients stored in .grad before the next backward pass?

Use optimizer.zero_grad() or manually set tensor.grad.zero_() to reset gradients to zero.

What must be set to True for a tensor to track gradients in PyTorch?

A requires_grad

B track_grad

C grad_enabled

D enable_grad

The requires_grad flag enables gradient tracking for tensors.

When is the .grad attribute of a tensor updated?

A After calling <code>backward()</code>

B When the tensor is created

C After calling <code>forward()</code>

D When printing the tensor

Gradients are computed and stored in .grad after backward() is called.

What is the value of .grad before any backward pass?

A Same as the tensor

B Zero tensor

C Random values

D None

Before backward, .grad is None because no gradients are computed yet.

How do you reset gradients in PyTorch before a new training step?

A Set <code>requires_grad=False</code>

B Call <code>optimizer.zero_grad()</code>

C Call <code>tensor.backward()</code>

D Delete the tensor

Calling optimizer.zero_grad() clears gradients to avoid accumulation.

Which of these tensors will have a .grad attribute after backward?

A Tensor with <code>requires_grad=False</code>

B Tensor created with <code>torch.no_grad()</code>

C Tensor with <code>requires_grad=True</code>

D Tensor converted to numpy

Only tensors with requires_grad=True track gradients and have .grad populated.

Explain how to access and use the .grad attribute in PyTorch during training.

Think about the steps in a training loop involving gradients.

Describe what happens if you forget to reset gradients before the next backward pass in PyTorch.

Consider how gradients behave across multiple backward calls.

Practice

1. What does the .grad attribute of a PyTorch tensor represent?

easy

A. The shape of the tensor

B. The value of the tensor itself

C. The gradient of the tensor after backpropagation

D. The data type of the tensor

Solution

1. Step 1: Understand the role of .grad in PyTorch

   The .grad attribute stores the gradient of the tensor computed during backpropagation.

2. Step 2: Differentiate from other tensor properties

   The tensor's value, shape, and data type are stored in other attributes, not .grad.

3. Final Answer:

   The gradient of the tensor after backpropagation -> Option C

4. Quick Check:

   .grad = gradient after backward() [OK]

Hint: Remember: .grad holds gradients after backward() [OK]

Common Mistakes:

• Confusing .grad with the tensor's value
• Expecting .grad before calling backward()
• Mixing .grad with tensor shape or dtype

2. Which of the following code snippets correctly accesses the gradient of a tensor x after backpropagation?

easy

A. grad = x.grad

B. grad = x.gradient()

C. grad = x.get_grad()

D. grad = x.gradient

Solution

1. Step 1: Recall the correct attribute for gradients

   PyTorch stores gradients in the .grad attribute, accessed as x.grad.

2. Step 2: Identify incorrect syntax

   Methods like gradient() or get_grad() do not exist for tensors.

3. Final Answer:

   grad = x.grad -> Option A

4. Quick Check:

   Use .grad attribute, not methods [OK]

Hint: Use .grad attribute, not functions [OK]

Common Mistakes:

• Trying to call .grad as a function
• Using incorrect method names
• Accessing .gradient instead of .grad

3. Consider the following PyTorch code:

import torch
x = torch.tensor(2.0, requires_grad=True)
y = x ** 3
z = y + 4
z.backward()
print(x.grad)

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

medium

A. None

B. tensor(12.)

C. tensor(6.)

D. tensor(8.)

Solution

1. Step 1: Compute the derivative of z with respect to x

   Given y = x^3 and z = y + 4, the derivative is dz/dx = dy/dx = 3x^2.

2. Step 2: Calculate the gradient at x=2.0

   Plugging in x=2, 3 * (2)^2 = 3 * 4 = 12. So, x.grad will be tensor(12.).

3. Final Answer:

   tensor(12.) -> Option B

4. Quick Check:

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

Hint: Calculate derivative manually, then plug in x [OK]

Common Mistakes:

• Forgetting to call backward() before accessing .grad
• Calculating derivative incorrectly
• Confusing y and z derivatives

4. You run this code:

import torch
x = torch.tensor(3.0, requires_grad=True)
y = x ** 2
print(x.grad)

But the output is None. Why?

medium

A. You forgot to call y.backward() to compute gradients

B. The tensor x does not require gradients

C. You cannot access gradients of scalar tensors

D. The tensor x is not a float

Solution

1. Step 1: Check if backward() was called

   Gradients are computed only after calling backward() on the output tensor.

2. Step 2: Confirm requires_grad=True and missing backward()

   Since x has requires_grad=True, the missing step is calling y.backward().

3. Final Answer:

   You forgot to call y.backward() to compute gradients -> Option A

4. Quick Check:

   Call backward() before accessing .grad [OK]

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

Common Mistakes:

• Expecting .grad before backward()
• Confusing requires_grad flag
• Thinking .grad auto-updates without backward()

5. Given this code:

import torch
x = torch.tensor([1.0, 2.0, 3.0], requires_grad=True)
y = (x ** 2).sum()
y.backward()
print(x.grad)

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

hard

A. None

B. tensor([1., 2., 3.])

C. tensor([1., 4., 9.])

D. tensor([2., 4., 6.])

Solution

1. Step 1: Understand the function and gradient

   The function is y = sum(x_i^2). The gradient of y with respect to x_i is dy/dx_i = 2x_i.

2. Step 2: Calculate gradients for each element

   For x = [1, 2, 3], gradients are [2*1, 2*2, 2*3] = [2, 4, 6].

3. Final Answer:

   tensor([2., 4., 6.]) -> Option D

4. Quick Check:

   Gradient of x^2 is 2x element-wise [OK]

Hint: Gradient of x² is 2x for each element [OK]

Common Mistakes:

• Confusing sum of squares with squares of sums
• Forgetting element-wise gradient
• Expecting None without backward()