GRU layer in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output shape of a GRU layer

What is the output shape of the following GRU layer when input shape is (batch_size=32, timesteps=10, features=8)?

TensorFlow

import tensorflow as tf
layer = tf.keras.layers.GRU(16)
input_shape = (32, 10, 8)
import numpy as np
x = np.random.random(input_shape).astype('float32')
out = layer(x)
print(out.shape)

A (32, 10, 16)

B (32, 16)

C (10, 16)

D (32, 8)

💡 Hint

By default, GRU returns the last output for each sample, not the full sequence.

The GRU layer with default settings returns the last output for each sample, so the output shape is (batch_size, units) which is (32, 16).

❓ Model Choice

intermediate

Choosing GRU for sequence data

You want to build a model to predict the next word in a sentence using a recurrent neural network. Which layer is best suited for capturing long-term dependencies efficiently?

A SimpleRNN layer

B Conv2D layer

C Dense layer

D GRU layer

💡 Hint

GRU is designed to handle long-term dependencies better than SimpleRNN.

GRU layers are designed to capture long-term dependencies in sequences more efficiently than SimpleRNN layers, making them suitable for language modeling.

❓ Hyperparameter

advanced

Effect of return_sequences in GRU

What is the effect of setting return_sequences=True in a GRU layer?

A The GRU disables the reset gate.

B The GRU returns only the last output, producing a 2D tensor.

C The GRU returns output for each timestep, producing a 3D tensor.

D The GRU output shape becomes (batch_size, features).

💡 Hint

Think about whether the output includes all timesteps or just the last one.

Setting return_sequences=True makes the GRU return the output at every timestep, resulting in a 3D tensor of shape (batch_size, timesteps, units).

🔧 Debug

advanced

Identifying error in GRU input shape

What error will this code raise and why? import tensorflow as tf layer = tf.keras.layers.GRU(10) x = tf.random.uniform((5, 10)) out = layer(x)

TensorFlow

import tensorflow as tf
layer = tf.keras.layers.GRU(10)
x = tf.random.uniform((5, 10))
out = layer(x)

A ValueError: Input 0 of layer 'gru' is incompatible with the layer: expected 3D tensor, got 2D tensor instead.

B RuntimeError: GRU layer cannot be called without batch size.

C No error, outputs shape (5, 10).

D TypeError: GRU layer requires integer units argument.

💡 Hint

Check the input tensor dimensions expected by GRU layers.

GRU layers expect 3D input tensors (batch_size, timesteps, features). The input here is 2D, causing a ValueError.

❓ Metrics

expert

Interpreting GRU training loss and accuracy

A GRU model for binary classification is trained for 10 epochs. The training loss steadily decreases, but training accuracy remains around 50%. What is the most likely explanation?

A The model is not learning; output layer or loss function might be incorrect.

B The model is overfitting the training data.

C The learning rate is too high causing unstable training.

D The dataset is perfectly balanced and the model is performing well.

💡 Hint

If loss decreases but accuracy stays at chance level, what could be wrong?

If loss decreases but accuracy stays near 50%, the model might be outputting probabilities but the final classification or loss function is misconfigured.

Practice

1. What is the main purpose of a GRU layer in TensorFlow?

easy

A. To remember important information from sequences over time

B. To perform image classification

C. To reduce the size of input data

D. To generate random numbers

Solution

1. Step 1: Understand the role of GRU layers

   GRU layers are designed to process sequences and keep track of important information over time.

2. Step 2: Compare options with GRU purpose

   Only To remember important information from sequences over time correctly describes the memory function of GRU layers in sequence data.

3. Final Answer:

   To remember important information from sequences over time -> Option A

4. Quick Check:

   GRU = sequence memory [OK]

Hint: GRU remembers sequence info, not unrelated tasks [OK]

Common Mistakes:

• Confusing GRU with image layers
• Thinking GRU reduces data size
• Assuming GRU generates random data

2. Which of the following is the correct way to create a GRU layer with 32 units in TensorFlow?

easy

A. tf.keras.layers.GRU(32, return_sequences='True')

B. tf.keras.layers.GRU(size=32)

C. tf.keras.layers.GRU(units=32)

D. tf.keras.layers.GRU(32, activation='relu')

Solution

1. Step 1: Recall GRU layer syntax

   The GRU layer requires the number of units as a named argument: units=32.

2. Step 2: Check options for correct syntax

   tf.keras.layers.GRU(units=32) uses the correct named argument units=32. tf.keras.layers.GRU(size=32) uses invalid keyword size. tf.keras.layers.GRU(32, return_sequences='True') passes invalid string 'True' instead of boolean. tf.keras.layers.GRU(32, activation='relu') uses an invalid activation for GRU.

3. Final Answer:

   tf.keras.layers.GRU(units=32) -> Option C

4. Quick Check:

   Use units=number for GRU [OK]

Hint: Use units=number for clarity when creating GRU [OK]

Common Mistakes:

• Using invalid keyword arguments like 'size'
• Passing strings instead of booleans for parameters
• Adding unsupported activation functions

3. What will be the shape of the output from this GRU layer?

gru = tf.keras.layers.GRU(units=10, return_sequences=False)
input_data = tf.random.uniform((5, 7, 8))
output = gru(input_data)

medium

A. (5, 10)

B. (5, 7, 10)

C. (7, 10)

D. (5, 8)

Solution

1. Step 1: Understand input and GRU parameters

   Input shape is (batch=5, time=7, features=8). GRU has 10 units and return_sequences=False.

2. Step 2: Determine output shape with return_sequences=False

   When return_sequences=False, GRU returns only the last output for each batch, shape (batch_size, units) = (5, 10).

3. Final Answer:

   (5, 10) -> Option A

4. Quick Check:

   return_sequences=False output shape = (batch, units) [OK]

Hint: return_sequences=False means output shape is (batch, units) [OK]

Common Mistakes:

• Confusing output shape with input time steps
• Assuming output keeps time dimension
• Mixing batch and feature dimensions

4. Identify the error in this code snippet using a GRU layer:

model = tf.keras.Sequential([
  tf.keras.layers.GRU(16, input_shape=(10, 5)),
  tf.keras.layers.Dense(1)
])
model.compile(optimizer='adam', loss='mse')
model.fit(tf.random.uniform((32, 10, 5)), tf.random.uniform((32, 1)), epochs=3)

medium

A. Input shape should be (5, 10) instead of (10, 5)

B. No error, code runs correctly

C. Missing return_sequences=True in GRU layer

D. Loss function 'mse' is invalid

Solution

1. Step 1: Check GRU layer input shape and parameters

   Input shape (10, 5) means 10 time steps and 5 features, which matches input data shape (32, 10, 5).

2. Step 2: Verify model compilation and training

   Loss 'mse' is valid for regression. return_sequences defaults to False, which is fine for this model.

3. Final Answer:

   No error, code runs correctly -> Option B

4. Quick Check:

   Input shape and loss are correct [OK]

Hint: Check input shapes and loss names carefully [OK]

Common Mistakes:

• Assuming return_sequences must be True always
• Mixing up time steps and feature dimensions
• Thinking 'mse' is invalid loss

5. You want to build a model that outputs a sequence of the same length as the input using a GRU layer. Which configuration is correct?

model = tf.keras.Sequential([
  tf.keras.layers.GRU(20, ???, input_shape=(15, 10)),
  tf.keras.layers.Dense(5)
])

hard

A. activation='relu'

B. return_sequences=False

C. use_bias=False

D. return_sequences=True

Solution

1. Step 1: Understand output sequence length requirement

   To output a sequence matching input length (15 time steps), the GRU must return output at each time step.

2. Step 2: Identify correct GRU parameter

   return_sequences=True makes GRU output a sequence for every time step, shape (batch, time, units).

3. Final Answer:

   return_sequences=True -> Option D

4. Quick Check:

   Sequence output needs return_sequences=True [OK]

Hint: Use return_sequences=True for sequence output [OK]

Common Mistakes:

• Using return_sequences=False loses time dimension
• Confusing activation or bias with output shape
• Ignoring input_shape importance