Bidirectional RNNs in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a bidirectional RNN layer in PyTorch.

PyTorch

import torch.nn as nn

rnn = nn.RNN(input_size=10, hidden_size=20, num_layers=1, bidirectional=[1])

Drag options to blanks, or click blank then click option'

ANone

BTrue

CFalse

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Setting bidirectional to False or 0 will create a unidirectional RNN.

Using None will cause an error because bidirectional expects a boolean.

Setting bidirectional=True creates a bidirectional RNN layer that processes input sequences in both forward and backward directions.

2fill in blank

medium

Complete the code to get the output shape of a bidirectional RNN layer.

PyTorch

output, hidden = rnn(input_seq)
output_shape = output.shape  # (seq_len, batch, [1] * hidden_size)

Drag options to blanks, or click blank then click option'

A1

Bnum_layers

C2

Dinput_size

Attempts:

3 left

💡 Hint

Common Mistakes

Using 1 instead of 2 will give incorrect output shape.

Confusing num_layers with bidirectionality factor.

For a bidirectional RNN, the output's last dimension is 2 * hidden_size because it concatenates forward and backward outputs.

3fill in blank

hard

Fix the error in the code to correctly initialize a bidirectional LSTM.

PyTorch

lstm = nn.LSTM(input_size=15, hidden_size=30, num_layers=2, bidirectional=[1])

Drag options to blanks, or click blank then click option'

ATrue

BFalse

CNone

D2

Attempts:

3 left

💡 Hint

Common Mistakes

Using integer 2 instead of boolean True causes an error.

Setting bidirectional to False disables bidirectionality.

The bidirectional parameter must be a boolean. Setting it to True enables bidirectional LSTM.

4fill in blank

hard

Complete the code to slice the forward and backward outputs from a bidirectional RNN.

PyTorch

forward_out = output[:, :, :[1]]
backward_out = output[:, :, [1]:[2]]

Drag options to blanks, or click blank then click option'

Ahidden_size

B2 * hidden_size

Cnum_layers

Dinput_size

Attempts:

3 left

💡 Hint

Common Mistakes

Using 2 * hidden_size for the forward slice.

Forgetting the end slice for backward output.

Confusing output slicing with hidden state slicing.

Forward output is the first hidden_size features; backward is from hidden_size to 2 * hidden_size.

5fill in blank

hard

Fill all three blanks to extract forward and backward hidden states using slicing.

PyTorch

forward_hn = hn[[1]::[2]]
backward_hn = hn[[3]::[2]]

Drag options to blanks, or click blank then click option'

A0

B1

C2

Dnum_layers

Attempts:

3 left

💡 Hint

Common Mistakes

Swapping start indices (using 1::2 for forward).

Using step=1 or other values instead of 2.

Using contiguous view instead of simple slicing.

forward_hn = hn[0::2] and backward_hn = hn[1::2] separate forward (even indices) and backward (odd indices) across all layers.

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