PyTorch ecosystem overview - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the main PyTorch library.

PyTorch

import [1]

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

Atorch

Bnumpy

Ctensorflow

Dsklearn

Attempts:

3 left

💡 Hint

Common Mistakes

Importing TensorFlow instead of PyTorch.

Importing numpy which is for arrays but not PyTorch.

The main PyTorch library is imported using import torch.

2fill in blank

medium

Complete the code to create a tensor filled with zeros of size 3x3.

PyTorch

x = torch.[1]((3, 3))

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

Aones

Bempty

Crand

Dzeros

Attempts:

3 left

💡 Hint

Common Mistakes

Using torch.ones which creates a tensor of ones.

Using torch.rand which creates random values.

Use torch.zeros to create a tensor filled with zeros.

3fill in blank

hard

Fix the error in the code to move a tensor to GPU if available.

PyTorch

device = torch.device('cuda' if torch.cuda.[1]() else 'cpu')

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

AisAvailable

Bis_available

Cavailable

Dhas_cuda

Attempts:

3 left

💡 Hint

Common Mistakes

Using incorrect method names like 'available' or 'has_cuda'.

Using camelCase instead of snake_case.

The correct method to check if CUDA is available is torch.cuda.is_available().

4fill in blank

hard

Fill both blanks to define a simple neural network layer using PyTorch.

PyTorch

layer = torch.nn.[1](in_features=10, [2]=5)

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

ALinear

BConv2d

Cout_features

Din_channels

Attempts:

3 left

💡 Hint

Common Mistakes

Using Conv2d which requires different parameters.

Confusing in_features with out_features.

Use torch.nn.Linear for a fully connected layer. The parameter out_features defines the output size.

5fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps layer names to their output sizes if size is greater than 5.

PyTorch

layer_sizes = {name: size for name, size in layers.items() if size [1] [2]

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

A>

B5

C<

D==

Attempts:

3 left

💡 Hint

Common Mistakes

Using < instead of > causing wrong filtering.

Using == which checks equality, not greater than.

The comprehension filters layers with size greater than 5 using size > 5.