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).