About this course

Get ready to showcase your deep learning expertise with this portfolio-worthy capstone project. This course is ideal for aspiring AI engineers who want to gain hands-on experience designing and training deep learning models with Keras, PyTorch, and vision transformers that they can highlight in interviews.

You will :

Get hands-on building deep learning models using Keras and PyTorch for real-world image classification tasks
Demonstrate you can design and implement a complete deep learning pipeline, including data loading, augmentation, model training, and validation
Practice using techniques to apply convolutional neural networks (CNNs) and vision transformers to specialized domains such as geospatial land classification
Evaluate and communicate project outcomes effectively through a model evaluation

Course Overview

During this project, you’ll dive into working with tools like Keras and PyTorch to develop and compare deep learning models. You’ll follow a complete workflow from data preparation and augmentation to training, validation, and deployment. Plus, you’ll gain hands-on experience applying convolutional neural networks (CNNs) and vision transformers to address domain-specific challenges and then assess your models using performance metrics like accuracy and inference time.

By the end of the project, you’ll have a fully developed, real-world AI solution that clearly demonstrates your technical expertise and readiness for advanced roles in AI and deep learning.

Enroll today to put your capabilities into practice and take the final step in your AI engineering journey!

What you will learn:

After completing this course, you will be able to:

Demonstrate mastery in deep learning.
Describe the process of loading data into PyTorch and Keras, and the methods available for preprocessing data.
Apply data loading and preprocessing techniques in PyTorch and Keras to prepare datasets for machine learning tasks.
Analyze and compare the performance of models trained in PyTorch and Keras, evaluating the impact of different architectures and preprocessing methods.
Evaluate pre-trained models and assess their performance for real-world machine learning tasks.
Create workflows to train, compare, and assess models using PyTorch and Keras.

Course Syllabus

Syllabus

Welcome

Video: Course Introduction
General Information
Learning Objectives and Syllabus
Reading: Grading Scheme
Reading: Capstone Project Overview
Video: Overview of the Capstone Project
Reading: Helpful Tips for Course Completion

Module 1: Data Handling

Module Introduction and Learning Objectives
Reading: Overview of Data Loading
Reading: Assignment Overview: Compare Memory-Based versus Generator-Based Data Loading
Lab: Compare Memory-Based versus Generator-Based Data Loading
Graded Quiz: Checklist: Data Loading
Reading: Assignment Overview: Data Loading and Augmentation Using Keras
Lab: Data Loading and Augmentation Using Keras
Graded Quiz: Checklist: Data Loading and Augmentation Using Keras
Reading: Assignment Overview: Data Loading and Augmentation Using PyTorch
Lab: Data Loading and Augmentation Using PyTorch
Graded Quiz: Checklist: Data Loading and Augmentation Using PyTorch
Module 1 Graded Quiz: Data Handling

Module 2: Convolutional Neural Network (CNN) Model Development

Module Introduction and Learning Objectives
Reading: Assignment Overview: Agricultural Land Classifier
Video: Building a CNN Classifier
Reading: Assignment Overview: Keras-Based Agricultural Land Classifier
Lab: Train and Evaluate a Keras-Based Classifier
Graded Quiz: Checklist: Keras-Based Agricultural Land Classifier
Reading: Assignment Overview: PyTorch-Based Agricultural Land Classifier
Lab: Implement and Test a PyTorch-Based Classifier
Graded Quiz: Checklist: PyTorch-Based Agricultural Land Classifier
Reading: Assignment Overview: Comparative Analysis of Keras and PyTorch Models
Reading: Comparative Analysis of Keras and PyTorch Models
Lab: Comparative Analysis of Keras and PyTorch Models
Graded Quiz: Checklist: Pre-trained Model Loading and Evaluation
Module 2 Graded Quiz: Convolutional Neural Network Model Development

Module 3: CNN - Vision Transformer Integration

Module Introduction and Learning Objectives
Reading: Assignment Overview: Vision Transformers and Transfer Learning
Reading: Assignment Overview: Vision Transformers in Keras
Lab: Vision Transformers Using Keras
Graded Quiz: Checklist: Vision Transformers Using Keras
Reading: Assignment Overview: Vision Transformers Using PyTorch
Lab: Vision Transformers Using PyTorch
Graded Quiz: Checklist: Vision Transformers Using PyTorch
Reading: Assignment Overview: Comparing ViTs: Keras versus PyTorch
Lab: Land Classification: CNN-Transformer Integration evaluation
Graded Quiz: Checklist: CNN-Transformer Integration Evaluation
Module 3 Graded Quiz: CNN - Vision Transformer Integration

Module 4: Final Project Submission

Module Introduction and Learning Objectives
Reading: Project Recap
Reading: Preparing Your Project Submission
Final Project: Submission and Evaluation

Course Wrap-Up

Congratulations and Next Steps
Team and Acknowledgments
Copyright and Trademarks

Course Rating and Feedback

Course Rating and Feedback

Badge

How to Claim Your Certificate
Claim Your Badge

Recommended Skills Prior to Taking this Course

During this project, you’ll work with the deep learning skills you’ve acquired throughout the IBM AI Engineering Professional Certificate. To get the most from this project, therefore, you need to have successfully completed the courses in this Professional Certificate before starting this capstone project.

Deep Learning Capstone Project

Language

Topic

Skills You Will Learn

Offered By

Estimated Effort

Platform

Last Update