Bidirectional RNNs in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a Bidirectional RNN?

A Bidirectional RNN is a type of recurrent neural network that processes data in both forward and backward directions. This helps the model understand context from past and future inputs, improving sequence learning.

beginner

How does a Bidirectional RNN differ from a standard RNN?

A standard RNN processes the sequence only from start to end (forward). A Bidirectional RNN processes the sequence twice: once forward and once backward, then combines both outputs for better context understanding.

beginner

In PyTorch, how do you enable bidirectionality in an RNN layer?

You set the argument `bidirectional=True` when creating the RNN, LSTM, or GRU layer. For example: `nn.LSTM(input_size, hidden_size, bidirectional=True)`.

intermediate

What is the shape of the output from a bidirectional RNN layer in PyTorch?

The output shape is `(seq_len, batch, num_directions * hidden_size)`. Since `num_directions` is 2 for bidirectional, the hidden size doubles in the output dimension.

intermediate

Why might bidirectional RNNs improve performance on tasks like speech recognition or text analysis?

Because they consider both past and future context in the sequence, bidirectional RNNs can better understand dependencies and meaning, leading to more accurate predictions.

What does setting `bidirectional=True` do in a PyTorch RNN layer?

A Processes the sequence forwards and backwards

B Processes the sequence only forwards

C Processes the sequence only backwards

D Disables the RNN layer

Setting `bidirectional=True` makes the RNN process the input sequence in both forward and backward directions.

If a unidirectional LSTM has hidden size 128, what is the hidden size of a bidirectional LSTM output?

A 128

B 512

C 64

D 256

Bidirectional LSTM doubles the hidden size in output because it concatenates forward and backward outputs: 128 * 2 = 256.

Which of these tasks benefits most from bidirectional RNNs?

A Image classification

B Sequence labeling like named entity recognition

C Sorting numbers

D Simple linear regression

Sequence labeling tasks benefit from understanding context before and after each element, which bidirectional RNNs provide.

In PyTorch, what is the output shape of a bidirectional RNN given input shape (seq_len, batch, input_size)?

A (seq_len, batch, hidden_size)

B (batch, seq_len, hidden_size)

C (seq_len, batch, 2 * hidden_size)

D (seq_len, 2 * batch, hidden_size)

The output shape is (seq_len, batch, 2 * hidden_size) because of concatenation of forward and backward outputs.

What is a key advantage of using bidirectional RNNs?

A Better context understanding from both past and future

B Uses less memory

C Faster training time

D Simpler model architecture

Bidirectional RNNs improve context understanding by looking at both past and future inputs.

Explain how a bidirectional RNN processes a sequence differently than a standard RNN.

Think about reading a sentence forwards and backwards.

Describe how to implement a bidirectional LSTM in PyTorch and what changes in the output shape.

Check the PyTorch LSTM parameters and output dimensions.

Practice

1. What is the main advantage of using a bidirectional RNN compared to a standard RNN?

easy

A. It processes the input sequence in both forward and backward directions to capture full context.

B. It uses fewer parameters to reduce model size.

C. It only processes sequences backward for faster training.

D. It replaces recurrent layers with convolutional layers.

Solution

1. Step 1: Understand standard RNN processing

   Standard RNNs process sequences only in the forward direction, so they only see past context.

2. Step 2: Analyze bidirectional RNN behavior

   Bidirectional RNNs process sequences both forward and backward, capturing past and future context.

3. Final Answer:

   It processes the input sequence in both forward and backward directions to capture full context. -> Option A

4. Quick Check:

   Bidirectional = forward + backward context [OK]

Hint: Bidirectional means reading sequence both ways [OK]

Common Mistakes:

• Thinking bidirectional reduces parameters
• Assuming it only reads backward
• Confusing with convolutional layers

2. Which of the following is the correct way to create a bidirectional GRU layer in PyTorch?

easy

A. torch.nn.GRU(input_size=10, hidden_size=20, direction='both')

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

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

D. torch.nn.GRU(input_size=10, hidden_size=20, two_directions=True)

Solution

1. Step 1: Recall PyTorch GRU parameters

   The bidirectional parameter is a boolean that enables bidirectional processing.

2. Step 2: Identify correct syntax

   Only torch.nn.GRU(input_size=10, hidden_size=20, bidirectional=True) uses bidirectional=True, which is the correct PyTorch syntax.

3. Final Answer:

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

4. Quick Check:

   bidirectional=True enables two directions [OK]

Hint: Use bidirectional=True to enable both directions [OK]

Common Mistakes:

• Using invalid parameter names like 'direction' or 'two_directions'
• Setting bidirectional=False by mistake
• Confusing input_size and hidden_size

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

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

medium

A. [4, 7, 3]

B. [7, 4, 6]

C. [4, 7, 6]

D. [4, 3, 7]

Solution

1. Step 1: Understand output shape of bidirectional RNN

   Output shape is (batch_size, seq_len, hidden_size * num_directions). Here, num_directions=2.

2. Step 2: Calculate output shape

   hidden_size=3, so output last dimension = 3 * 2 = 6. Batch=4, seq_len=7, so output shape = [4, 7, 6].

3. Final Answer:

   [4, 7, 6] -> Option C

4. Quick Check:

   Output last dim = hidden_size * 2 [OK]

Hint: Output last dim doubles with bidirectional=True [OK]

Common Mistakes:

• Forgetting to multiply hidden_size by 2
• Mixing batch and sequence dimensions
• Assuming output shape matches input exactly

4. You wrote this code but get a runtime error:

rnn = torch.nn.RNN(input_size=8, hidden_size=4, bidirectional=True)
input = torch.randn(5, 10, 8)
output, hidden = rnn(input)

What is the likely cause of the error?

medium

A. Input tensor shape should have batch_first=True or be transposed to (seq_len, batch, input_size).

B. hidden_size must be equal to input_size for bidirectional RNNs.

C. bidirectional=True is not supported for RNN layers.

D. The input tensor must be 2D, not 3D.

Solution

1. Step 1: Check default input shape for PyTorch RNN

   By default, PyTorch RNN expects input shape (seq_len, batch, input_size) unless batch_first=True is set.

2. Step 2: Analyze given input shape

   Input shape is (5, 10, 8) which is (batch, seq_len, input_size), but batch_first=True is not set, causing mismatch.

3. Final Answer:

   Input tensor shape should have batch_first=True or be transposed to (seq_len, batch, input_size). -> Option A

4. Quick Check:

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

Hint: Set batch_first=True if input shape is (batch, seq_len, input_size) [OK]

Common Mistakes:

• Assuming bidirectional disables shape rules
• Thinking hidden_size must match input_size
• Passing 2D input instead of 3D

5. You want to build a sentiment analysis model using a bidirectional LSTM in PyTorch. The input sequences have variable lengths. Which approach correctly handles variable-length sequences with a bidirectional LSTM?

hard

A. Manually reverse sequences and concatenate outputs without using bidirectional=True.

B. Pad sequences to max length and feed directly without packing, with bidirectional=False.

C. Use only forward LSTM and ignore sequence lengths.

D. Use pack_padded_sequence before the LSTM and pad_packed_sequence after, with batch_first=True and bidirectional=True set.

Solution

1. Step 1: Understand variable-length sequence handling

   PyTorch requires packing padded sequences to efficiently process variable-length inputs in RNNs.

2. Step 2: Apply packing with bidirectional LSTM

   Use pack_padded_sequence before feeding to LSTM with bidirectional=True, then unpack with pad_packed_sequence.

3. Final Answer:

   Use pack_padded_sequence before the LSTM and pad_packed_sequence after, with batch_first=True and bidirectional=True set. -> Option D

4. Quick Check:

   Pack sequences for variable length + bidirectional LSTM [OK]

Hint: Pack sequences to handle variable lengths with bidirectional LSTM [OK]

Common Mistakes:

• Ignoring packing and feeding padded sequences directly
• Disabling bidirectional for variable lengths
• Manually reversing sequences instead of using bidirectional flag