Compiling models (optimizer, loss, metrics) in TensorFlow

Introduction

Compiling a model sets up how it learns and measures success. It tells the model how to improve and how to check its progress.

When you finish building a neural network and want to train it.

When you want to choose how the model updates itself during learning.

When you want to decide how to measure the model's accuracy or error.

When you want to prepare the model for training with specific goals.

When you want to compare different training methods by changing settings.

Syntax

TensorFlow

model.compile(optimizer='optimizer_name_or_object', loss='loss_function_name_or_object', metrics=['metric1', 'metric2', ...])

optimizer controls how the model learns (e.g., 'adam', 'sgd').

loss is the function that measures how wrong the model is (e.g., 'sparse_categorical_crossentropy').

Examples

Use Adam optimizer, sparse categorical crossentropy loss, and track accuracy.

TensorFlow

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

Use SGD optimizer with a learning rate of 0.01, mean squared error loss, and track mse metric.

TensorFlow

model.compile(optimizer=tf.keras.optimizers.SGD(learning_rate=0.01), loss='mse', metrics=['mse'])

Use RMSprop optimizer, binary crossentropy loss, and track accuracy and precision.

TensorFlow

model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['accuracy', 'Precision'])

Sample Model

This code builds a small neural network, compiles it with Adam optimizer and sparse categorical crossentropy loss, then trains it on random data for 3 epochs. It prints the accuracy after each epoch.

TensorFlow

import tensorflow as tf

# Create a simple model
model = tf.keras.Sequential([
    tf.keras.layers.Dense(10, activation='relu', input_shape=(5,)),
    tf.keras.layers.Dense(3, activation='softmax')
])

# Compile the model with optimizer, loss, and metrics
model.compile(
    optimizer='adam',
    loss='sparse_categorical_crossentropy',
    metrics=['accuracy']
)

# Create some dummy data
import numpy as np
x_train = np.random.random((20, 5))
y_train = np.random.randint(0, 3, 20)

# Train the model
history = model.fit(x_train, y_train, epochs=3, verbose=0)

# Print training accuracy for each epoch
for i, acc in enumerate(history.history['accuracy'], 1):
    print(f'Epoch {i} accuracy: {acc:.4f}')

Important Notes

You must compile the model before training it.

Choosing the right optimizer and loss depends on your problem type (classification, regression, etc.).

Metrics help you understand how well the model is doing during training.

Summary

Compiling sets how the model learns and measures success.

Optimizer controls learning steps, loss measures error, metrics track performance.

Always compile before training your model.

Practice

1. What is the main purpose of the compile() method in a TensorFlow model?

easy

A. To set the optimizer, loss function, and metrics before training

B. To train the model on data

C. To save the model to disk

D. To make predictions on new data

Solution

1. Step 1: Understand the role of compile()

   The compile() method prepares the model for training by specifying how it learns and how performance is measured.

2. Step 2: Identify what compile() sets

   It sets the optimizer (how the model updates weights), the loss function (how error is calculated), and metrics (how performance is tracked).

3. Final Answer:

   To set the optimizer, loss function, and metrics before training -> Option A

4. Quick Check:

   Compile sets optimizer, loss, metrics = A [OK]

Hint: Compile sets learning rules and measurements before training [OK]

Common Mistakes:

• Confusing compile with training or prediction
• Thinking compile saves the model
• Assuming compile runs the training process

2. Which of the following is the correct way to compile a TensorFlow model with Adam optimizer, categorical crossentropy loss, and accuracy metric?

easy

A. model.compile(optimizer='adam', loss='mse', metrics='accuracy')

B. model.compile(optimizer='sgd', loss='mse', metrics=['accuracy'])

C. model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

D. model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

Solution

1. Step 1: Check optimizer and loss names

   The Adam optimizer is specified as 'adam' and categorical crossentropy loss as 'categorical_crossentropy'.

2. Step 2: Verify metrics format

   Metrics must be passed as a list, so ['accuracy'] is correct, not a string.

3. Final Answer:

   model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy']) -> Option C

4. Quick Check:

   Correct optimizer, loss, and metrics list = D [OK]

Hint: Use list for metrics and correct loss name [OK]

Common Mistakes:

• Passing metrics as a string instead of list
• Using wrong loss function for classification
• Choosing wrong optimizer name

3. Consider the code below:

model.compile(optimizer='sgd', loss='mse', metrics=['mae'])
history = model.fit(x_train, y_train, epochs=2)
print(history.history['mae'])

What will be printed?

medium

A. A single float value of mean absolute error after training

B. A list of mean squared error values for each epoch

C. An error because 'mae' is not a valid metric

D. A list of mean absolute error values for each epoch

Solution

1. Step 1: Understand metrics in compile and fit

   The model is compiled with 'mae' (mean absolute error) as a metric, so it will track this during training.

2. Step 2: Check what history.history['mae'] contains

   It stores a list of metric values for each epoch, so printing it shows a list of MAE values per epoch.

3. Final Answer:

   A list of mean absolute error values for each epoch -> Option D

4. Quick Check:

   Metrics list stores per-epoch values = B [OK]

Hint: history.history stores metric lists per epoch [OK]

Common Mistakes:

• Expecting a single float instead of list
• Confusing loss with metric values
• Thinking 'mae' is invalid metric

4. You wrote this code:

model.compile(optimizer='adam', loss='categorical_crossentropy', metrics='accuracy')

What is the problem?

medium

A. Metrics should be a list, not a string

B. Loss function name is incorrect

C. Optimizer name is invalid

D. Model must be compiled after training

Solution

1. Step 1: Check metrics argument type

   Metrics must be passed as a list or tuple, e.g., ['accuracy'], not a string.

2. Step 2: Confirm other arguments are correct

   Optimizer 'adam' and loss 'categorical_crossentropy' are valid names, so the issue is due to metrics format.

3. Final Answer:

   Metrics should be a list, not a string -> Option A

4. Quick Check:

   Metrics argument must be list = A [OK]

Hint: Always pass metrics as a list, even if one metric [OK]

Common Mistakes:

• Passing metrics as a string
• Misnaming loss or optimizer
• Compiling after training instead of before

5. You want to compile a model for a binary classification task. Which combination of optimizer, loss, and metrics is the best choice?

hard

A. optimizer='rmsprop', loss='mse', metrics=['mae']

B. optimizer='adam', loss='binary_crossentropy', metrics=['accuracy']

C. optimizer='sgd', loss='categorical_crossentropy', metrics=['accuracy']

D. optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']

Solution

1. Step 1: Identify task type

   Binary classification means two classes, so the loss should be 'binary_crossentropy'.

2. Step 2: Choose suitable optimizer and metrics

   Adam optimizer is widely used and effective; accuracy is a good metric for classification.

3. Step 3: Check other options

   Options B and D use categorical losses for multi-class, and A uses regression losses, so they are less suitable.

4. Final Answer:

   optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'] -> Option B

5. Quick Check:

   Binary task needs binary_crossentropy loss = C [OK]

Hint: Binary classification uses binary_crossentropy loss [OK]

Common Mistakes:

• Using categorical loss for binary tasks
• Choosing regression loss for classification
• Ignoring metric suitability