TensorFlow architecture (eager vs graph execution)

Introduction

TensorFlow can run your code in two ways: step-by-step (eager) or by building a plan first (graph). This helps you choose speed or easy debugging.

When you want to quickly test ideas and see results immediately.

When you need to debug your model step-by-step.

When you want to optimize your model for faster training and deployment.

When you want to save and share your model efficiently.

When running on devices with limited resources where speed matters.

Syntax

TensorFlow

import tensorflow as tf

# Eager execution is enabled by default
x = tf.constant(3)
y = tf.constant(4)
sum = x + y
print(sum)

# To use graph execution, decorate a function
@tf.function
def add(a, b):
    return a + b

result = add(x, y)
print(result)

Eager execution runs operations immediately and returns results.

Graph execution builds a computation graph and runs it later for speed.

Examples

This runs immediately and prints 35.

TensorFlow

import tensorflow as tf

# Eager execution example
x = tf.constant(5)
y = tf.constant(7)
print(x * y)

This builds a graph for multiply and runs it, printing 35.

TensorFlow

import tensorflow as tf

@tf.function
def multiply(a, b):
    return a * b

result = multiply(tf.constant(5), tf.constant(7))
print(result)

Shows eager addition and graph function for add and square.

TensorFlow

import tensorflow as tf

# Mixing eager and graph
print(tf.constant(2) + tf.constant(3))

@tf.function
def add_and_square(a, b):
    c = a + b
    return c * c

print(add_and_square(tf.constant(2), tf.constant(3)))

Sample Model

This program shows how TensorFlow runs operations eagerly and with graph execution, printing results for both.

TensorFlow

import tensorflow as tf

# Eager execution example
print('Eager execution:')
x = tf.constant(10)
y = tf.constant(20)
sum_eager = x + y
print('Sum:', sum_eager)

# Graph execution example
@tf.function
def compute_sum(a, b):
    return a + b

print('\nGraph execution:')
sum_graph = compute_sum(x, y)
print('Sum:', sum_graph)

# Check if eager is enabled
print('\nIs eager execution enabled?', tf.executing_eagerly())

Important Notes

Time complexity: Both eager and graph execution have similar operation costs, but graph execution can optimize and run faster overall.

Space complexity: Graph execution may use more memory to store the computation graph.

Common mistake: Forgetting to use @tf.function for graph execution or expecting eager behavior inside graph functions.

When to use: Use eager for easy debugging and quick tests; use graph for production and speed.

Summary

TensorFlow runs code eagerly by default for simplicity.

Graph execution builds a plan for faster, optimized runs.

You can switch between them using @tf.function decorator.

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