TensorFlow architecture (eager vs graph execution) - Practice Questions

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding TensorFlow Execution Modes

Which of the following statements correctly describes TensorFlow's eager execution mode?

A Eager execution builds a static computation graph that must be compiled before running.

B Eager execution runs operations immediately and returns concrete values, making debugging easier.

C Eager execution requires manual session management to run operations.

D Eager execution disables automatic differentiation in TensorFlow.

💡 Hint

Think about how TensorFlow runs operations step-by-step versus building a graph.

Eager execution runs operations immediately and returns actual values, which helps with debugging and interactive development. The graph mode builds a static graph first.

❓ Predict Output

intermediate

Output of TensorFlow Eager Execution Code

What is the output of this TensorFlow code snippet when eager execution is enabled?

TensorFlow

import tensorflow as tf
x = tf.constant(3)
y = tf.constant(4)
z = x * y
print(z)

A tf.Tensor(12, shape=(), dtype=int32)

B <tf.Tensor 'Mul:0' shape=() dtype=int32>

C 12

D Error: TensorFlow graph not initialized

💡 Hint

Eager execution returns a Tensor object with value and metadata.

With eager execution, operations return tf.Tensor objects showing the value, shape, and type immediately.

❓ Model Choice

advanced

Choosing Execution Mode for Performance

You want to train a large neural network model efficiently in TensorFlow. Which execution mode should you choose to maximize performance?

A Eager execution mode, because it runs operations immediately for faster debugging.

B Graph execution mode, because it disables automatic differentiation.

C Graph execution mode, because it compiles the computation graph for optimized performance.

D Eager execution mode, because it disables GPU acceleration.

💡 Hint

Consider which mode allows TensorFlow to optimize and parallelize computations.

Graph execution mode builds a static graph that TensorFlow can optimize and run efficiently, especially for large models.

❓ Hyperparameter

advanced

Effect of tf.function on Execution Mode

What does the @tf.function decorator do to a Python function in TensorFlow?

A It converts the function into a TensorFlow graph for faster execution.

B It disables TensorFlow's automatic differentiation inside the function.

C It forces the function to run eagerly without building a graph.

D It converts all tensors inside the function to NumPy arrays.

💡 Hint

Think about how TensorFlow can speed up Python code by changing its execution style.

@tf.function compiles a Python function into a TensorFlow graph, improving performance by optimizing and running it as a graph.

🔧 Debug

expert

Identifying Error in Mixed Execution Code

What error will this TensorFlow code raise when eager execution is enabled by default?

TensorFlow

import tensorflow as tf
@tf.function
def add_tensors(x, y):
    return x + y

result = add_tensors(tf.constant(2), 3)
print(result)

A RuntimeError: Eager execution must be disabled to use tf.function

B ValueError: tf.function cannot accept Python integers as arguments

C TypeError: Unsupported operand type(s) for +: 'Tensor' and 'int'

D No error, prints tf.Tensor(5, shape=(), dtype=int32)

💡 Hint

Consider the types of inputs and how TensorFlow operations handle them inside tf.function.

tf.function automatically converts Python scalars like integers to tf.constant tensors during tracing. No error occurs, and it prints tf.Tensor(5, shape=(), dtype=int32).

Practice

1. What is the main difference between eager execution and graph execution in TensorFlow?

easy

A. Eager execution requires a GPU, graph execution runs only on CPU.

B. Eager execution uses less memory than graph execution in all cases.

C. Graph execution is only for training, eager execution is only for inference.

D. Eager execution runs operations immediately, while graph execution builds a computation plan first.

Solution

1. Step 1: Understand eager execution behavior

   Eager execution runs TensorFlow operations immediately as they are called, making it easy to debug and understand.

2. Step 2: Understand graph execution behavior

   Graph execution builds a computation graph first, then runs it for better performance and optimization.

3. Final Answer:

   Eager execution runs operations immediately, while graph execution builds a computation plan first. -> Option D

4. Quick Check:

   Eager vs Graph = Immediate vs Plan [OK]

Hint: Eager means now, graph means plan first [OK]

Common Mistakes:

• Thinking graph execution runs immediately
• Confusing hardware requirements
• Assuming eager is only for inference

2. Which of the following is the correct way to convert a Python function to a TensorFlow graph function?

easy

A. Use @tf.function decorator above the function definition.

B. Call tf.convert_to_graph(function) before running it.

C. Wrap the function inside tf.Graph() and call it.

D. Set tf.enable_graph_mode(True) before defining the function.

Solution

1. Step 1: Recall TensorFlow's method to switch execution modes

   TensorFlow uses the @tf.function decorator to convert a Python function into a graph function.

2. Step 2: Evaluate other options for correctness

   tf.convert_to_graph and tf.enable_graph_mode do not exist; wrapping in tf.Graph() is not the standard way.

3. Final Answer:

   Use @tf.function decorator above the function definition. -> Option A

4. Quick Check:

   @tf.function converts to graph [OK]

Hint: Remember @tf.function for graph conversion [OK]

Common Mistakes:

• Using non-existent TensorFlow functions
• Trying to enable graph mode globally
• Confusing tf.Graph() usage

3. Consider the following code snippet:

import tensorflow as tf

@tf.function
def add(a, b):
    print('Running add')
    return a + b

result1 = add(1, 2)
result2 = add(3, 4)

What will be printed when this code runs?

medium

A. Running add
Running add

B. Running add

C. No output printed

D. Error due to print inside @tf.function

Solution

1. Step 1: Understand print behavior inside @tf.function

   When a function is decorated with @tf.function, it runs as a graph. Python print runs only once during graph tracing, not on every call.

2. Step 2: Analyze the calls to add()

   The first call triggers tracing and prints 'Running add'. The second call uses the compiled graph and does not print again.

3. Final Answer:

   Running add -> Option B

4. Quick Check:

   Print runs once during tracing [OK]

Hint: Print inside @tf.function runs once [OK]

Common Mistakes:

• Expecting print every call
• Thinking print is disabled
• Assuming error from print usage

4. You wrote this code:

import tensorflow as tf

def multiply(a, b):
    return a * b

@tf.function
def call_multiply(x, y):
    return multiply(x, y)

print(call_multiply(2, 3))

But the output is a Tensor object, not a number. How can you fix it to print the actual number?

medium

A. Wrap multiply inside tf.function as well

B. Remove @tf.function decorator from call_multiply

C. Add .numpy() to the print call: print(call_multiply(2, 3).numpy())

D. Change multiply to use tf.multiply instead of * operator

Solution

1. Step 1: Understand output type of @tf.function

   Functions decorated with @tf.function return TensorFlow tensors, not plain Python numbers.

2. Step 2: Convert tensor to number for printing

   Use the .numpy() method on the tensor to get the actual number value for printing.

3. Final Answer:

   Add .numpy() to the print call: print(call_multiply(2, 3).numpy()) -> Option C

4. Quick Check:

   Tensor to number: use .numpy() [OK]

Hint: Use .numpy() to get number from tensor [OK]

Common Mistakes:

• Expecting tensor to print as number
• Removing @tf.function unnecessarily
• Changing multiply without need

5. You want to speed up a TensorFlow model training loop by switching from eager to graph execution. Which approach correctly applies this change while keeping eager mode for debugging?

hard

A. Decorate the training step function with @tf.function and run training normally.

B. Set tf.config.experimental_run_functions_eagerly(True) before training.

C. Rewrite the entire model using tf.Graph() and tf.Session().

D. Disable eager execution globally using tf.compat.v1.disable_eager_execution().

Solution

1. Step 1: Identify how to switch to graph execution selectively

   Using @tf.function on the training step compiles it to a graph, speeding execution while keeping eager mode elsewhere.

2. Step 2: Evaluate other options for drawbacks

   Setting experimental_run_functions_eagerly(True) forces eager mode (slower). Rewriting with tf.Graph() and tf.Session() is outdated. Disabling eager globally removes debugging ease.

3. Final Answer:

   Decorate the training step function with @tf.function and run training normally. -> Option A

4. Quick Check:

   @tf.function speeds training, keeps eager debugging [OK]

Hint: Use @tf.function on training step for speed [OK]

Common Mistakes:

• Forcing eager mode instead of graph
• Using old TensorFlow 1.x APIs
• Disabling eager globally losing debugging