Dynamic computation graph advantage in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a tensor with gradient tracking enabled.

PyTorch

import torch
x = torch.tensor([1.0, 2.0, 3.0], requires_grad=[1])

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

ANone

BTrue

CFalse

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Setting requires_grad to False will not track gradients.

Using None or 0 will cause errors or no gradient tracking.

Setting requires_grad=True tells PyTorch to track operations on the tensor for automatic differentiation.

2fill in blank

medium

Complete the code to perform a dynamic computation where the number of operations depends on input size.

PyTorch

import torch
x = torch.tensor([1.0, 2.0, 3.0], requires_grad=True)
result = 0
for i in range(x.size(0)):
    result += x[i] * [1]

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

A2

Bx

Ci

Dresult

Attempts:

3 left

💡 Hint

Common Mistakes

Using a fixed number like 2 makes the graph static.

Using the whole tensor x or result causes errors or wrong calculations.

Using i inside the loop makes the computation graph dynamic, changing with input size.

3fill in blank

hard

Fix the error in the code to correctly compute gradients with a dynamic graph.

PyTorch

import torch
x = torch.tensor([1.0, 2.0, 3.0], requires_grad=True)
result = 0
for i in range(x.size(0)):
    result += x[i] * i
result.[1]()

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

Abackward

Bbackprop

Cgrad

Dcompute_grad

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'grad' or 'backprop' are not valid PyTorch methods.

Not calling backward() means gradients won't be computed.

The backward() function computes gradients for tensors with requires_grad=True.

4fill in blank

hard

Fill both blanks to create a dynamic computation graph that sums squares of input elements greater than 2.

PyTorch

import torch
x = torch.tensor([1.0, 3.0, 4.0], requires_grad=True)
result = 0
for val in x:
    if val [1] 2:
        result += val [2] 2
result.backward()

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

A>

B**

C*

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' instead of '>' changes the condition.

Using '*' instead of '**' multiplies by 2 instead of squaring.

The condition val > 2 selects elements greater than 2, and val ** 2 squares them.

5fill in blank

hard

Fill all three blanks to build a dynamic graph that creates a dictionary of squares for even numbers in a list.

PyTorch

numbers = [1, 2, 3, 4, 5]
squares = { [1]: [2] for [3] in numbers if [3] % 2 == 0 }

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

Anum

Bnum ** 2

Dn

Attempts:

3 left

💡 Hint

Common Mistakes

Using different variable names inconsistently causes errors.

Using multiplication instead of exponentiation changes the result.

We use num as the key and num ** 2 as the value for even numbers iterated by num.