Skip to main content
Course/Module 5/Topic 4 of 4Beginner

Transfer Learning

Learn how to use pre-trained models for efficient deep learning.

60 minBy Priygop TeamLast updated: Feb 2026

What is Transfer Learning?

Transfer Learning involves using a pre-trained neural network model on a new task, leveraging learned features to improve performance and reduce training time.

Key Concepts

  • Pre-trained Models: Models trained on large datasets like ImageNet
  • Fine-tuning: Adjusting pre-trained weights for a specific task
  • Feature Extraction: Using pre-trained layers as feature extractors
  • Domain Adaptation: Applying models to related but different domains

Implementation

Example
import tensorflow as tf
from tensorflow import keras
import numpy as np

# Load a pre-trained model (e.g., MobileNetV2)
base_model = keras.applications.MobileNetV2(
    input_shape=(224, 224, 3),
    include_top=False,
    weights='imagenet'
)

# Freeze the base model
base_model.trainable = False

# Generate sample image data
np.random.seed(42)
X = np.random.randn(100, 224, 224, 3)  # 100 images, 224x224 pixels, 3 channels
y = np.random.randint(0, 5, 100)  # 5 classes
y = tf.keras.utils.to_categorical(y, 5)

# Split the data
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Create the model
model = keras.Sequential([
    base_model,
    keras.layers.GlobalAveragePooling2D(),
    keras.layers.Dense(128, activation='relu'),
    keras.layers.Dropout(0.2),
    keras.layers.Dense(5, activation='softmax')
])

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

# Train the model
history = model.fit(X_train, y_train,
                    epochs=5,
                    batch_size=32,
                    validation_split=0.2,
                    verbose=1)

# Evaluate the model
test_loss, test_accuracy = model.evaluate(X_test, y_test, verbose=0)
print(f"Test accuracy: {test_accuracy:.4f}")

Try It Yourself — Deep Learning & Neural Networks

Try It Yourself — Deep Learning & Neural NetworksHTML
HTML Editor
✓ ValidTab = 2 spaces
HTML|32 lines|1574 chars|✓ Valid syntax
UTF-8

Quick Quiz — Deep Learning & Neural Networks

Additional Resources

Recommended Reading

  • Deep Learning by Ian Goodfellow
  • Neural Networks and Deep Learning by Michael Nielsen
  • TensorFlow and Keras Documentation

Online Resources

  • TensorFlow Tutorials
  • Keras Documentation
  • CNN Architecture Guide
Chat on WhatsApp
Priygop - Leading Professional Development Platform | Expert Courses & Interview Prep