Explore

Convolutional Neural Networks in TensorFlow

Approx. 26 hours to complete

Save Course

Go to Course

Course Summary

Learn how to build Convolutional Neural Networks using TensorFlow. This course covers the basics of CNNs and how to implement them in TensorFlow.

Key Learning Points

Understand the basics of CNNs and how they work
Implement CNNs in TensorFlow
Learn how to use transfer learning to improve CNN performance

Learning Outcomes

Ability to understand and implement CNNs using TensorFlow
Understanding of transfer learning and its application to CNNs
Improved ability to build and train deep learning models

Prerequisites or good to have knowledge before taking this course

Basic understanding of Python programming
Familiarity with linear algebra and calculus

Course Difficulty Level

Intermediate

Course Format

Self-paced
Online
Video lectures
Programming assignments

Similar Courses

Applied Data Science with Python
Deep Learning Specialization
Natural Language Processing with TensorFlow

Related Education Paths

Related Books

Description

If you are a software developer who wants to build scalable AI-powered algorithms, you need to understand how to use the tools to build them. This course is part of the upcoming Machine Learning in Tensorflow Specialization and will teach you best practices for using TensorFlow, a popular open-source framework for machine learning.

In Course 2 of the deeplearning.ai TensorFlow Specialization, you will learn advanced techniques to improve the computer vision model you built in Course 1. You will explore how to work with real-world images in different shapes and sizes, visualize the journey of an image through convolutions to understand how a computer “sees” information, plot loss and accuracy, and explore strategies to prevent overfitting, including augmentation and dropout. Finally, Course 2 will introduce you to transfer learning and how learned features can be extracted from models. The Machine Learning course and Deep Learning Specialization from Andrew Ng teach the most important and foundational principles of Machine Learning and Deep Learning. This new deeplearning.ai TensorFlow Specialization teaches you how to use TensorFlow to implement those principles so that you can start building and applying scalable models to real-world problems. To develop a deeper understanding of how neural networks work, we recommend that you take the Deep Learning Specialization.

Knowledge

Handle real-world image data
Plot loss and accuracy
Explore strategies to prevent overfitting, including augmentation and dropout
Learn transfer learning and how learned features can be extracted from models

Outline

Exploring a Larger Dataset
Introduction, A conversation with Andrew Ng
A conversation with Andrew Ng
Training with the cats vs. dogs dataset
Working through the notebook
Fixing through cropping
Visualizing the effect of the convolutions
Looking at accuracy and loss
Week 1 Wrap up
Before you Begin: TensorFlow 2.0 and this Course
The cats vs dogs dataset
Looking at the notebook
What you'll see next
What have we seen so far?
Week 1 Quiz

Augmentation: A technique to avoid overfitting
A conversation with Andrew Ng
Introducing augmentation
Coding augmentation with ImageDataGenerator
Demonstrating overfitting in cats vs. dogs
Adding augmentation to cats vs. dogs
Exploring augmentation with horses vs. humans
Week 2 Wrap up
Image Augmentation
Start Coding...
Looking at the notebook
The impact of augmentation on Cats vs. Dogs
Try it for yourself!
What have we seen so far?
Week 2 Quiz

Transfer Learning
A conversation with Andrew Ng
Understanding transfer learning: the concepts
Coding transfer learning from the inception mode
Coding your own model with transferred features
Exploring dropouts
Exploring Transfer Learning with Inception
Week 3 Wrap up
Start coding!
Adding your DNN
Using dropouts!
Applying Transfer Learning to Cats v Dogs
What have we seen so far?
Week 3 Quiz

Multiclass Classifications
A conversation with Andrew Ng
Moving from binary to multi-class classification
Explore multi-class with Rock Paper Scissors dataset
Train a classifier with Rock Paper Scissors
Test the Rock Paper Scissors classifier
A conversation with Andrew Ng
Introducing the Rock-Paper-Scissors dataset
Check out the code!
Try testing the classifier
What have we seen so far?
Wrap up
Week 4 Quiz

Summary of User Reviews

Learn about Convolutional Neural Networks using TensorFlow on Coursera. This course has received positive reviews from users.

Key Aspect Users Liked About This Course

Many users found the course content to be engaging and informative.

Pros from User Reviews

The course provides a comprehensive understanding of CNNs and their applications
The instructors are knowledgeable and explain the concepts clearly
The programming assignments help in applying the concepts learned in the course
The course is well-structured and easy to follow
The quizzes and final project provide a good assessment of the understanding gained

Cons from User Reviews

Some users found the course to be too fast-paced and difficult to keep up with
The programming assignments can be time-consuming and challenging
The course requires prior knowledge of Python programming and machine learning concepts
Some users experienced technical issues with the platform during the course
The course may not be suitable for beginners in machine learning

Recommended for you

The Complete Self-Driving Car Course - Applied Deep Learning

Learn to use Deep Learning, Computer Vision and Machine Learning techniques to Build an Autonomous Car with Python   This course will show you how to:...

Save Course

Deep Learning with Tensorflow

Much of theworld's data is unstructured. Think images, sound, and textual data. Learn how to apply Deep Learning with TensorFlow to this type of data to solve real-world problems....

Save Course

Hands on Google cloud platform(GCP) - Data Engineer

Data Engineer Certification This course is exclusively designed by NoTEZ to teach about GCP in most simplest way possible.    ...

Save Course

Natural Language Processing

This course covers a wide range of tasks in Natural Language Processing from basic to advanced: sentiment analysis, summarization, dialogue state tracking, to name a few....

Save Course