Bidirectional RNNs in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding Bidirectional RNN Outputs

In a bidirectional RNN, what does the output at each time step represent?

A The output is the sum of all hidden states across all time steps.

B The output only contains information from past time steps up to the current step.

C The output only contains information from future time steps after the current step.

D The output combines information from past and future time steps relative to the current step.

💡 Hint

Think about how information flows in both directions in a bidirectional RNN.

Bidirectional RNNs process sequences forward and backward, so the output at each time step includes context from both past and future relative to that step.

❓ Predict Output

intermediate

Output Shape of a Bidirectional RNN in PyTorch

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

PyTorch

import torch
import torch.nn as nn

rnn = nn.RNN(input_size=10, hidden_size=20, num_layers=1, bidirectional=True)
input_seq = torch.randn(5, 3, 10)  # seq_len=5, batch=3, input_size=10
output, hidden = rnn(input_seq)
print(output.shape)

A torch.Size([3, 5, 40])

B torch.Size([5, 3, 20])

C torch.Size([5, 3, 40])

D torch.Size([3, 5, 20])

💡 Hint

Remember the output shape is (seq_len, batch, num_directions * hidden_size).

Since the RNN is bidirectional, the output hidden size doubles (20 * 2 = 40). The output shape is (5, 3, 40).

❓ Model Choice

advanced

Choosing Bidirectional RNN for Sequence Tasks

For which of the following tasks is using a bidirectional RNN most beneficial?

A Classifying the sentiment of a complete sentence after reading it entirely.

B Predicting the next word in a sentence given only previous words.

C Generating text one character at a time from left to right.

D Real-time speech recognition where future audio frames are not available.

💡 Hint

Consider if future context is available when making predictions.

Bidirectional RNNs use both past and future context, so they work best when the entire sequence is available, like sentence classification.

❓ Hyperparameter

advanced

Effect of Bidirectionality on Hidden State Size

If you set hidden_size=50 in a bidirectional RNN with num_layers=1, what is the size of the hidden state tensor h_n returned by PyTorch?

A torch.Size([2, batch_size, 50])

B torch.Size([1, batch_size, 100])

C torch.Size([1, batch_size, 50])

D torch.Size([2, batch_size, 100])

💡 Hint

Remember the first dimension of h_n is num_layers * num_directions.

With 1 layer and 2 directions, the first dimension is 2. Hidden size per direction is 50, so shape is (2, batch_size, 50).

🔧 Debug

expert

Identifying Error in Bidirectional RNN Output Usage

Consider this PyTorch code snippet:

import torch
import torch.nn as nn

rnn = nn.RNN(input_size=8, hidden_size=16, bidirectional=True)
input_seq = torch.randn(7, 4, 8)
output, hidden = rnn(input_seq)
last_output = output[-1]
print(last_output.shape)

What is the shape of last_output and why might using it directly be problematic for sequence classification?

A torch.Size([4, 16]); It only contains forward direction output, missing backward context.

B torch.Size([4, 32]); It combines forward and backward outputs at the last time step, but backward output corresponds to the first input step, so it may not represent the full sequence context.

C torch.Size([7, 4, 32]); It is the full output sequence, so no problem using it directly.

D torch.Size([4, 16]); It only contains backward direction output, missing forward context.

💡 Hint

Think about what the last time step output means in a bidirectional RNN.

The output at the last time step concatenates forward output at last step and backward output at first step. Using it directly may not capture full sequence meaning for classification.

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