nn.GRU layer in PyTorch

Introduction

The nn.GRU layer helps a model remember information from sequences, like words in a sentence, to make better predictions.

When you want to understand sentences or speech over time.

When predicting the next word in a sentence.

When analyzing time series data like stock prices.

When building chatbots that remember past messages.

When processing sequences of sensor data for predictions.

Syntax

PyTorch

torch.nn.GRU(input_size, hidden_size, num_layers=1, batch_first=False, dropout=0, bidirectional=False)

input_size: Number of features in each input step.

hidden_size: Number of features in the hidden state (memory size).

Examples

Creates a GRU layer that takes inputs with 10 features and outputs hidden states with 20 features.

PyTorch

gru = torch.nn.GRU(input_size=10, hidden_size=20)

Creates a 2-layer GRU where input and output tensors have batch size as the first dimension.

PyTorch

gru = torch.nn.GRU(input_size=5, hidden_size=15, num_layers=2, batch_first=True)

Sample Model

This code creates a simple GRU layer and passes a random input through it. It prints the shapes and values of the output and hidden state tensors.

PyTorch

import torch
import torch.nn as nn

# Create a GRU layer
input_size = 3
hidden_size = 5
num_layers = 1
batch_size = 2
seq_length = 4

gru = nn.GRU(input_size, hidden_size, num_layers, batch_first=True)

# Random input: batch_size sequences, each with seq_length steps, each step with input_size features
input_tensor = torch.randn(batch_size, seq_length, input_size)

# Initial hidden state (num_layers, batch_size, hidden_size)
h0 = torch.zeros(num_layers, batch_size, hidden_size)

# Forward pass through GRU
output, hn = gru(input_tensor, h0)

print("Output shape:", output.shape)
print("Hidden state shape:", hn.shape)
print("Output tensor:", output)
print("Hidden state tensor:", hn)

Important Notes

The GRU remembers information from previous steps to help with sequence data.

Setting batch_first=True makes input and output shapes easier to work with (batch size first).

You can stack multiple GRU layers by increasing num_layers.

Summary

The nn.GRU layer helps models learn from sequences by keeping memory of past inputs.

It takes input size and hidden size as main settings.

Use it when working with time or sequence data like text, speech, or sensor readings.

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