nn.GRU layer in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a GRU layer with input size 10 and hidden size 20.

PyTorch

gru = nn.GRU(input_size=[1], hidden_size=20)

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

A10

B20

C5

D15

Attempts:

3 left

💡 Hint

Common Mistakes

Confusing input_size with hidden_size.

Using hidden_size value for input_size.

The input_size parameter defines the number of expected features in the input. Here, it should be 10.

2fill in blank

medium

Complete the code to pass an input tensor of shape (5, 3, 10) through the GRU layer.

PyTorch

output, hidden = gru([1])

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

Adata

Binput

Cinput_tensor

Dx

Attempts:

3 left

💡 Hint

Common Mistakes

Using undefined variable names.

Passing the wrong tensor shape.

The variable holding the input tensor is named input_tensor, which matches the expected input shape.

3fill in blank

hard

Fix the error in the code by completing the missing argument to initialize the hidden state for batch size 3 and hidden size 20.

PyTorch

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

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

A1

B3

C20

D5

Attempts:

3 left

💡 Hint

Common Mistakes

Using hidden size instead of batch size.

Using number of layers instead of batch size.

The hidden state shape is (num_layers * num_directions, batch_size, hidden_size). Here batch_size is 3.

4fill in blank

hard

Fill both blanks to create a GRU layer with 2 layers and batch_first=True.

PyTorch

gru = nn.GRU(input_size=10, hidden_size=20, num_layers=[1], batch_first=[2])

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

A2

BTrue

CFalse

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Confusing num_layers with hidden_size.

Setting batch_first to False by mistake.

num_layers=2 sets two stacked GRU layers. batch_first=True makes input shape (batch, seq, feature).

5fill in blank

hard

Fill both blanks to extract the last output from the GRU output tensor of shape (5, 3, 20).

PyTorch

last_output = output[[1], [2], :]

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

A4

B2

C:

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong sequence index.

Using wrong batch index.

Not selecting all features.

The last output is at sequence index 4 (0-based), batch index 0, and all features (:).