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

Recall & Review

beginner

What is the purpose of the nn.RNN layer in PyTorch?

The nn.RNN layer processes sequences of data by passing information from one time step to the next, allowing the model to learn patterns over time.

beginner

What are the main inputs to an nn.RNN layer?

The main inputs are the sequence data (shape: seq_len, batch_size, input_size) and an optional initial hidden state (shape: num_layers * num_directions, batch_size, hidden_size).

beginner

What does the 'hidden_size' parameter control in nn.RNN?

It controls the size of the hidden state vector, which stores information from previous time steps and affects the model's capacity to learn patterns.

intermediate

How does nn.RNN handle multiple layers and directions?

You can set 'num_layers' to stack multiple RNN layers, and 'bidirectional=True' to process sequences forwards and backwards, doubling the output size.

beginner

What are the outputs of nn.RNN layer?

It outputs 'output' (all hidden states for each time step) and 'hidden' (the last hidden state for each layer and direction).

What shape should the input sequence to nn.RNN have?

A batch_size, seq_len, input_size

B seq_len, batch_size, input_size

C input_size, seq_len, batch_size

D batch_size, input_size, seq_len

The nn.RNN expects input with shape (seq_len, batch_size, input_size).

What does setting 'bidirectional=True' do in nn.RNN?

A Processes the sequence forwards and backwards

B Stacks multiple RNN layers

C Changes the activation function

D Disables the hidden state

Bidirectional RNN processes the input sequence in both forward and backward directions.

Which of these is NOT an output of nn.RNN?

A Output for all time steps

B Last hidden state

C Predicted class labels

D None of the above

nn.RNN outputs hidden states, not direct class predictions.

What does the 'hidden_size' parameter affect?

A Size of the hidden state vector

B Length of the input sequence

C Number of layers

D Batch size

'hidden_size' controls the size of the hidden state vector in the RNN.

How can you provide an initial hidden state to nn.RNN?

A By setting a parameter during initialization

B You cannot provide an initial hidden state

C By modifying the input sequence

D By passing it as the second argument to the forward method

You can pass the initial hidden state as the second argument when calling the RNN layer.

Explain how the nn.RNN layer processes a sequence of data step-by-step.

Think about how information flows through time steps in the RNN.

Describe the difference between a unidirectional and bidirectional nn.RNN layer.

Consider how reading the sequence backwards adds information.

Practice

1. What does the nn.RNN layer in PyTorch primarily do?

easy

A. Processes sequences step by step, keeping track of past information

B. Sorts input data in ascending order

C. Generates random numbers for initialization

D. Performs matrix multiplication without memory

Solution

1. Step 1: Understand the purpose of RNN

   The RNN layer is designed to handle sequential data by processing one step at a time and remembering previous steps.

2. Step 2: Compare options with RNN behavior

   Only Processes sequences step by step, keeping track of past information describes this behavior correctly; others describe unrelated functions.

3. Final Answer:

   Processes sequences step by step, keeping track of past information -> Option A

4. Quick Check:

   RNN remembers past inputs = A [OK]

Hint: RNNs remember past steps in sequences [OK]

Common Mistakes:

• Thinking RNN sorts data
• Confusing RNN with random number generators
• Assuming RNN does simple matrix multiplication only

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

easy

A. nn.RNN(20, 10)

B. nn.RNN(10)

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

D. nn.RNN(hidden_size=10, input_size=20)

Solution

1. Step 1: Recall nn.RNN constructor parameters

   The constructor requires input_size first, then hidden_size, e.g., nn.RNN(input_size=10, hidden_size=20).

2. Step 2: Check each option

   Only nn.RNN(input_size=10, hidden_size=20) matches the correct parameter order and names; the others reverse sizes, omit hidden_size, or swap parameters.

3. Final Answer:

   nn.RNN(input_size=10, hidden_size=20) -> Option C

4. Quick Check:

   Input size first, hidden size second = D [OK]

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

Common Mistakes:

• Swapping input_size and hidden_size
• Omitting hidden_size parameter
• Using positional args in wrong order

3. Given the code below, what is the shape of output after running the RNN?

import torch
import torch.nn as nn
rnn = nn.RNN(input_size=5, hidden_size=3, batch_first=True)
input = torch.randn(4, 7, 5)  # batch=4, seq_len=7, input_size=5
output, hn = rnn(input)

medium

A. (7, 4, 3)

B. (3, 4, 7)

C. (4, 3, 7)

D. (4, 7, 3)

Solution

1. Step 1: Understand batch_first=True effect

   With batch_first=True, input shape is (batch, seq_len, input_size), so output shape is (batch, seq_len, hidden_size).

2. Step 2: Apply shapes to given input

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

3. Final Answer:

   (4, 7, 3) -> Option D

4. Quick Check:

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

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

Common Mistakes:

• Confusing batch and sequence length order
• Ignoring batch_first parameter
• Mixing hidden_size with input_size in output shape

4. What is wrong with this code snippet using nn.RNN?

rnn = nn.RNN(input_size=8, hidden_size=4)
input = torch.randn(3, 5, 10)  # batch=3, seq_len=5, input_size=10
output, hn = rnn(input)

medium

A. RNN requires input to be 2D tensor

B. Input size does not match the RNN's input_size parameter

C. Batch size should be last dimension

D. Hidden size must be equal to input size

Solution

1. Step 1: Check input_size parameter vs input tensor

   The RNN expects input_size=8, but input tensor's last dimension is 10, causing mismatch.

2. Step 2: Validate tensor shape requirements

   Input shape (3, 5, 10) means batch=3, seq_len=5, input_size=10, which conflicts with RNN's input_size=8.

3. Final Answer:

   Input size does not match the RNN's input_size parameter -> Option B

4. Quick Check:

   Input last dim must match input_size = C [OK]

Hint: Input last dimension must match RNN input_size [OK]

Common Mistakes:

• Ignoring input_size mismatch
• Thinking batch size is last dimension
• Assuming RNN input is 2D tensor

5. You want to process a batch of sequences with varying lengths using nn.RNN. Which approach correctly handles this in PyTorch?

hard

A. Pad sequences to the same length and use pack_padded_sequence before the RNN

B. Feed sequences directly without padding or packing

C. Use a for loop to process each sequence separately without padding

D. Set hidden_size equal to the longest sequence length

Solution

1. Step 1: Understand handling variable-length sequences

   PyTorch recommends padding sequences to equal length and using pack_padded_sequence to inform RNN about actual lengths.

2. Step 2: Evaluate options for best practice

   Pad sequences to the same length and use pack_padded_sequence before the RNN correctly describes this approach. Options B and C ignore padding/packing, causing errors or inefficiency. Set hidden_size equal to the longest sequence length is unrelated to sequence length handling.

3. Final Answer:

   Pad sequences to the same length and use pack_padded_sequence before the RNN -> Option A

4. Quick Check:

   Use padding + pack_padded_sequence for variable lengths = A [OK]

Hint: Pad and pack sequences before RNN for variable lengths [OK]

Common Mistakes:

• Feeding raw variable-length sequences directly
• Ignoring packing after padding
• Misusing hidden_size for sequence length