Why RNNs handle sequences in PyTorch - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a simple RNN layer in PyTorch.

PyTorch

rnn = torch.nn.RNN(input_size=10, hidden_size=20, num_layers=[1])

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

A1

B0

C-1

D2

Attempts:

3 left

💡 Hint

Common Mistakes

Setting num_layers to 0 or negative values causes errors.

The num_layers parameter specifies how many stacked RNN layers to use. A value of 1 creates a single RNN layer.

2fill in blank

medium

Complete the code to initialize the hidden state for an RNN with batch size 5 and hidden size 20.

PyTorch

hidden = torch.zeros([1], 5, 20)

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

A1

B0

C2

D20

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up batch size and hidden size dimensions.

The first dimension is the number of layers, here 1. The batch size is 5 and hidden size is 20.

3fill in blank

hard

Fix the error in the code to process a sequence input through the RNN.

PyTorch

output, hidden = rnn([1], hidden)

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

Aoutput

Binput_seq

Chidden

Drnn

Attempts:

3 left

💡 Hint

Common Mistakes

Passing hidden state as first argument causes errors.

The RNN expects the input sequence tensor as the first argument, followed by the hidden state.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps each word to its length if the length is greater than 3.

PyTorch

{word: [1] for word in words if len(word) [2] 3}

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

Alen(word)

B>

C<

Dword

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong comparison operator or mapping to the word itself.

The dictionary maps each word to its length, but only if the length is greater than 3.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps each uppercase word to its length if the length is greater than 4.

PyTorch

result = [1]: [2] for word in words if len(word) [3] 4

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

Aword.upper()

Blen(word)

C>

Dword

Attempts:

3 left

💡 Hint

Common Mistakes

Using the original word as key or wrong comparison operator.

This comprehension creates a dictionary where keys are uppercase words and values are their lengths, but only for words longer than 4 characters.