Bidirectional RNN in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding Bidirectional RNN Output Shape

Consider a bidirectional RNN layer in TensorFlow with units=32 and return_sequences=True. If the input shape is (batch_size, timesteps, features), what will be the output shape of this layer?

A (batch_size, 64)

B (batch_size, 32)

C (batch_size, timesteps, 32)

D (batch_size, timesteps, 64)

💡 Hint

Remember that a bidirectional RNN concatenates outputs from forward and backward passes.

A bidirectional RNN with 32 units runs two RNNs (forward and backward), each producing 32 outputs per timestep. These outputs are concatenated, resulting in 64 features per timestep. Since return_sequences=True, the output shape keeps the timesteps dimension.

❓ Predict Output

intermediate

Output of Bidirectional LSTM Layer

What is the output of the following TensorFlow code snippet?

TensorFlow

import tensorflow as tf
import numpy as np

inputs = tf.constant(np.random.random((1, 5, 10)), dtype=tf.float32)
layer = tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(4, return_sequences=False))
output = layer(inputs)
print(output.shape)

A (1, 4)

B (1, 8)

C (5, 8)

D (5, 4)

💡 Hint

Check the return_sequences parameter and how bidirectional layers concatenate outputs.

The LSTM has 4 units, and since return_sequences=False, it outputs the last timestep's output only. The bidirectional wrapper concatenates forward and backward outputs, doubling the feature size to 8. The batch size is 1, so the output shape is (1, 8).

❓ Model Choice

advanced

Choosing the Right Bidirectional RNN for Sequence Tagging

You want to build a model to tag each word in a sentence with its part of speech. Which bidirectional RNN layer configuration is best suited for this task?

A Simple RNN with <code>return_sequences=False</code>

B Bidirectional LSTM with <code>return_sequences=False</code>

C Bidirectional GRU with <code>return_sequences=True</code>

D Bidirectional LSTM with <code>return_sequences=False</code> and dropout=0.5

💡 Hint

Think about whether you need output for each timestep or just one output per sequence.

For sequence tagging, you need an output for every word (timestep). Using return_sequences=True ensures the model outputs a vector for each timestep. Bidirectional GRU is efficient and suitable. Options with return_sequences=False output only one vector per sequence, which is not suitable for tagging each word.

❓ Hyperparameter

advanced

Effect of Increasing Units in Bidirectional RNN

What is the most likely effect of doubling the number of units in a bidirectional RNN layer on model training?

A Training time increases and model capacity increases, possibly improving accuracy

B Training time decreases and model capacity decreases, reducing accuracy

C Training time stays the same but model capacity decreases

D Training time increases but model capacity stays the same

💡 Hint

More units mean more parameters to learn.

Doubling units increases the number of parameters, which increases model capacity and training time. This can improve accuracy if the model was underfitting, but may also risk overfitting.

🔧 Debug

expert

Identifying the Cause of Shape Mismatch in Bidirectional RNN

Given the following code, what is the cause of the error?

import tensorflow as tf
inputs = tf.keras.Input(shape=(10, 8))
# Bidirectional LSTM with 16 units
x = tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(16))(inputs)
outputs = tf.keras.layers.Dense(1)(x)
model = tf.keras.Model(inputs, outputs)
model.compile(optimizer='adam', loss='mse')

# Trying to train with input shape (32, 10, 8) and target shape (32, 10, 1)
x_train = tf.random.normal((32, 10, 8))
y_train = tf.random.normal((32, 10, 1))
model.fit(x_train, y_train, epochs=1)

A The LSTM layer should have return_sequences=True to output sequence for each timestep

B The input shape is incorrect; it should be (10, 1) instead of (10, 8)

C The Dense layer output units should be 10 instead of 1

D The model output shape is (32, 1) but target shape is (32, 10, 1), causing mismatch

💡 Hint

Check if the model output shape matches the target shape.

The bidirectional LSTM without return_sequences=True outputs only the last timestep's output, shape (batch_size, 32). The target has shape (batch_size, 10, 1), expecting output for each timestep. Setting return_sequences=True makes the LSTM output a sequence matching the target shape.

Practice

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

easy

A. It uses less memory by processing only half the sequence.

B. It trains faster because it skips some time steps.

C. It processes the input sequence in both forward and backward directions to capture more context.

D. It only works with fixed-length sequences.

Solution

1. Step 1: Understand how standard RNNs process sequences

   Standard RNNs read sequences only in one direction, usually forward, so they only capture past context.

2. Step 2: Recognize the bidirectional approach

   Bidirectional RNNs read sequences both forward and backward, allowing them to capture information from past and future context.

3. Final Answer:

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

4. Quick Check:

   Bidirectional RNN = forward + backward context [OK]

Hint: Bidirectional means reading sequence both ways [OK]

Common Mistakes:

• Thinking it reduces memory usage
• Assuming it skips time steps
• Believing it only works on fixed-length sequences

2. Which of the following is the correct way to create a Bidirectional LSTM layer in TensorFlow?

easy

A. tf.keras.layers.Bidirectional(units=64, layer=tf.keras.layers.LSTM())

B. tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(units=64))

C. tf.keras.layers.LSTM(units=64, bidirectional=True)

D. tf.keras.layers.LSTM(tf.keras.layers.Bidirectional(units=64))

Solution

1. Step 1: Recall the TensorFlow syntax for Bidirectional wrapper

   In TensorFlow, you wrap an RNN layer like LSTM inside tf.keras.layers.Bidirectional.

2. Step 2: Check each option

   tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(units=64)) correctly wraps LSTM with Bidirectional. Options A, B, and C misuse the syntax or parameters.

3. Final Answer:

   tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(units=64)) -> Option B

4. Quick Check:

   Bidirectional wraps RNN layer [OK]

Hint: Wrap RNN layer inside Bidirectional() [OK]

Common Mistakes:

• Passing bidirectional=True to LSTM directly
• Putting Bidirectional inside LSTM
• Incorrect parameter order

3. Consider the following TensorFlow code snippet:

import tensorflow as tf
model = tf.keras.Sequential([
  tf.keras.layers.Bidirectional(tf.keras.layers.SimpleRNN(4, return_sequences=True), input_shape=(5, 10)),
  tf.keras.layers.Dense(1)
])
output = model(tf.random.uniform((1, 5, 10)))
print(output.shape)

What will be the printed output shape?

medium

A. (1, 5, 1)

B. (1, 4, 1)

C. (1, 8, 1)

D. (5, 1)

Solution

1. Step 1: Analyze the Bidirectional SimpleRNN output shape

   SimpleRNN has 4 units, bidirectional doubles output units to 8. Since return_sequences=True, output shape is (batch, time_steps, 8).

2. Step 2: Check the Dense layer effect

   Dense(1) applies to last dimension, converting 8 features to 1, so output shape becomes (batch, time_steps, 1) = (1, 5, 1).

3. Final Answer:

   (1, 5, 1) -> Option A

4. Quick Check:

   Bidirectional doubles units, Dense changes features [OK]

Hint: Bidirectional doubles units; Dense changes last dim [OK]

Common Mistakes:

• Ignoring return_sequences=True effect
• Not doubling units for bidirectional
• Confusing batch and time dimensions

4. You wrote this code but get an error:

model = tf.keras.Sequential([
  tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(32), input_shape=(None, 10)),
  tf.keras.layers.Dense(1)
])

The error says: ValueError: input_shape must be a tuple of integers, not NoneType
What is the likely cause and fix?

medium

A. Add return_sequences=True to the LSTM layer.

B. Remove the Bidirectional wrapper to fix the error.

C. Change LSTM units from 32 to 10.

D. Replace input_shape=(None, 10) with input_shape=(5, 10) or a fixed integer for time steps.

Solution

1. Step 1: Understand input_shape requirements

   TensorFlow expects input_shape to be a tuple of integers without None for time steps in Sequential models.

2. Step 2: Fix input_shape

   Replace input_shape=(None, 10) with a fixed integer like (5, 10) to specify sequence length.

3. Final Answer:

   Replace input_shape=(None, 10) with input_shape=(5, 10) or fixed integer -> Option D

4. Quick Check:

   input_shape must have fixed integers [OK]

Hint: Use fixed integers in input_shape, not None [OK]

Common Mistakes:

• Leaving None in input_shape for Sequential
• Removing Bidirectional unnecessarily
• Changing units instead of input shape

5. You want to build a sentiment analysis model using a Bidirectional GRU in TensorFlow. The input sequences have variable length. Which approach correctly handles variable-length sequences and avoids processing padded parts?

hard

A. Use tf.keras.layers.Bidirectional(tf.keras.layers.GRU(64)) with masking layer before it to ignore padded tokens.

B. Set return_sequences=False in GRU and ignore padding.

C. Manually trim all sequences to the same length before feeding to the model.

D. Use Bidirectional GRU without masking and rely on Dense layer to fix padding.

Solution

1. Step 1: Understand variable-length sequence handling

   Variable-length sequences are padded to same length; masking tells RNN to ignore padded parts.

2. Step 2: Use masking with Bidirectional GRU

   Adding a tf.keras.layers.Masking layer before Bidirectional GRU ensures padded tokens are ignored during processing.

3. Final Answer:

   Use Bidirectional GRU with masking layer before it -> Option A

4. Quick Check:

   Masking ignores padding in variable-length sequences [OK]

Hint: Add Masking layer before Bidirectional RNN for padding [OK]

Common Mistakes:

• Ignoring masking and expecting model to handle padding
• Trimming sequences manually losing data
• Relying on Dense layer to fix padding