nn.GRU layer in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does the nn.GRU layer in PyTorch do?

The nn.GRU layer processes sequences by using Gated Recurrent Units to keep track of information over time, helping models understand order and context in data like sentences or time series.

intermediate

What are the main components inside a GRU cell?

A GRU cell has two gates: the update gate, which decides how much past information to keep, and the reset gate, which decides how to combine new input with past memory.

beginner

How do you create a simple nn.GRU layer in PyTorch for input size 10 and hidden size 20?

Use: nn.GRU(input_size=10, hidden_size=20). This sets the input feature size to 10 and the hidden state size to 20.

intermediate

What is the shape of the output from nn.GRU when batch_first=True and input shape is (batch, seq_len, input_size)?

The output shape is (batch, seq_len, num_directions * hidden_size). It gives the hidden states for each time step in the sequence.

intermediate

Why might you choose GRU over LSTM in a model?

GRUs are simpler and faster to train because they have fewer gates than LSTMs, but still handle sequence data well, making them good for smaller datasets or faster experiments.

What does the update gate in a GRU control?

A How much past information to keep

B How to reset the hidden state

C The input feature size

D The output sequence length

The update gate controls how much of the past information is kept in the current hidden state.

In PyTorch, what argument makes nn.GRU expect input shape as (batch, seq_len, input_size)?

A dropout=0.5

B bidirectional=True

C num_layers=2

D batch_first=True

Setting batch_first=True makes the input and output tensors have batch size as the first dimension.

Which of these is NOT a gate in a GRU cell?

A Forget gate

B Update gate

C Reset gate

D None of the above

Forget gate is part of LSTM, not GRU.

What is the main advantage of GRU compared to LSTM?

A Requires more memory

B Handles longer sequences better

C Simpler and faster to train

D Has more gates

GRUs have fewer gates, making them simpler and faster to train.

What does the hidden_size parameter in nn.GRU specify?

A The length of the input sequence

B The size of the hidden state vector

C The number of layers

D The batch size

hidden_size sets the dimension of the hidden state vector in the GRU.

Explain how a GRU layer processes sequence data and why it is useful.

Think about how GRU keeps important information from the past while reading new data.

Describe how to set up and use an nn.GRU layer in PyTorch including input and output shapes.

Consider the shape of input and output tensors and the key parameters.

Practice

1. What is the primary purpose of the nn.GRU layer in PyTorch?

easy

A. To reduce the dimensionality of data using PCA

B. To perform image classification using convolution

C. To process sequential data by remembering past information

D. To generate random numbers for initialization

Solution

1. Step 1: Understand the role of GRU

   The GRU (Gated Recurrent Unit) is designed to handle sequences by keeping track of past inputs, which helps in tasks like text or speech processing.

2. Step 2: Compare with other options

   The other options describe unrelated tasks: dimensionality reduction using PCA, image classification using convolution, and random number generation, which are not the purpose of GRU.

3. Final Answer:

   To process sequential data by remembering past information -> Option C

4. Quick Check:

   GRU = sequence memory [OK]

Hint: GRU remembers past inputs in sequences [OK]

Common Mistakes:

• Confusing GRU with convolution layers
• Thinking GRU reduces data dimensions like PCA
• Assuming GRU generates random values

2. Which of the following is the correct way to create a GRU layer with input size 10 and hidden size 20 in PyTorch?

easy

A. nn.GRU(20, 10)

B. nn.GRU(input_size=10, hidden_size=20)

C. nn.GRU(hidden_size=10, input_size=20)

D. nn.GRU(10)

Solution

1. Step 1: Recall GRU constructor parameters

   The correct order and names are input_size first, then hidden_size. So nn.GRU(input_size=10, hidden_size=20) is correct.

2. Step 2: Check other options

   nn.GRU(20, 10) reverses the sizes. nn.GRU(hidden_size=10, input_size=20) swaps parameter names incorrectly. nn.GRU(10) misses the hidden size parameter.

3. Final Answer:

   nn.GRU(input_size=10, hidden_size=20) -> Option B

4. Quick Check:

   Input size first, hidden size second [OK]

Hint: Remember: input_size before hidden_size in nn.GRU [OK]

Common Mistakes:

• Swapping input_size and hidden_size
• Omitting hidden_size parameter
• Using wrong parameter names

3. Given the following code, what is the shape of the output tensor out?

import torch
import torch.nn as nn

gru = nn.GRU(input_size=5, hidden_size=3, batch_first=True)
x = torch.randn(4, 7, 5)  # batch=4, seq_len=7, input_size=5
out, h_n = gru(x)
print(out.shape)

medium

A. (4, 7, 3)

B. (7, 4, 3)

C. (4, 3, 7)

D. (7, 3, 4)

Solution

1. Step 1: Understand batch_first=True effect

   With batch_first=True, input shape is (batch, seq_len, input_size). Output shape matches (batch, seq_len, hidden_size).

2. Step 2: Apply shapes from code

   Input is (4, 7, 5), hidden_size=3, so output out shape is (4, 7, 3).

3. Final Answer:

   (4, 7, 3) -> Option A

4. Quick Check:

   Output shape = (batch, seq_len, hidden_size) [OK]

Hint: batch_first=True means batch is first dimension [OK]

Common Mistakes:

• Confusing batch and sequence dimensions
• Ignoring batch_first parameter
• Mixing hidden_size with input_size

4. Which of the following correctly describes the execution of this code snippet?

import torch
import torch.nn as nn

gru = nn.GRU(input_size=8, hidden_size=4)
x = torch.randn(5, 10, 8)
out, h = gru(x)
print(out.shape)

medium

A. The code runs without errors and prints (5, 10, 4)

B. The hidden_size must be larger than input_size

C. The GRU layer requires batch_first=True for this input shape

D. The input tensor shape is incorrect for default GRU settings

Solution

1. Step 1: Check default GRU input expectations

   By default, GRU expects input shape (seq_len, batch, input_size). Here, input is (5, 10, 8), so seq_len=5, batch=10, input_size=8 which matches default.

2. Step 2: Verify output shape

   Output shape will be (seq_len, batch, hidden_size) = (5, 10, 4).

3. Step 3: Evaluate statements

   The code runs without errors and prints (5, 10, 4). Hidden_size can be smaller than input_size. batch_first=True is not required. Input shape is correct for default settings.

4. Final Answer:

   The code runs without errors and prints (5, 10, 4) -> Option A

5. Quick Check:

   Default GRU input shape = (seq_len, batch, input_size) [OK]

Hint: Default GRU expects seq_len first, batch second [OK]

Common Mistakes:

• Assuming batch is first dimension without batch_first=True
• Thinking hidden_size must be bigger than input_size
• Expecting output shape to swap batch and seq_len

5. You want to build a GRU-based model to process variable-length sequences in a batch. Which approach correctly handles this in PyTorch?

hard

A. Feed raw variable-length sequences directly to nn.GRU without padding

B. Manually truncate all sequences to the shortest length before input

C. Use nn.GRU with batch_first=False and ignore sequence lengths

D. Pad sequences to the same length and use pack_padded_sequence before feeding to nn.GRU

Solution

1. Step 1: Understand variable-length sequence handling

   PyTorch requires sequences in a batch to be the same length or packed. Padding sequences and using pack_padded_sequence allows GRU to ignore padded parts.

2. Step 2: Evaluate options

   Pad sequences to the same length and use pack_padded_sequence before feeding to nn.GRU correctly pads and packs sequences. Feed raw variable-length sequences directly to nn.GRU without padding is invalid because GRU cannot handle raw variable-length sequences. Use nn.GRU with batch_first=False and ignore sequence lengths ignores lengths, causing wrong results. Manually truncate all sequences to the shortest length before input loses data by truncation.

3. Final Answer:

   Pad sequences and use pack_padded_sequence before nn.GRU -> Option D

4. Quick Check:

   Use padding + packing for variable-length sequences [OK]

Hint: Pad then pack sequences before GRU [OK]

Common Mistakes:

• Feeding variable-length sequences without padding
• Ignoring sequence lengths in batch
• Truncating sequences losing data