About this Course
143,829 recent views

100% online

Start instantly and learn at your own schedule.

Flexible deadlines

Reset deadlines in accordance to your schedule.

Intermediate Level

Course 1 of the TensorFlow Specialization, Python coding, and high-school level math are required. ML/DL experience is helpful but not required.

English

Subtitles: English

What you will learn

  • Check

    Handle real-world image data

  • Check

    Plot loss and accuracy

  • Check

    Explore strategies to prevent overfitting, including augmentation and dropout

  • Check

    Learn transfer learning and how learned features can be extracted from models

Skills you will gain

Inductive TransferAugmentationDropoutsMachine LearningTensorflow

100% online

Start instantly and learn at your own schedule.

Flexible deadlines

Reset deadlines in accordance to your schedule.

Intermediate Level

Course 1 of the TensorFlow Specialization, Python coding, and high-school level math are required. ML/DL experience is helpful but not required.

English

Subtitles: English

Syllabus - What you will learn from this course

Week
1
4 hours to complete

Exploring a Larger Dataset

In the first course in this specialization, you had an introduction to TensorFlow, and how, with its high level APIs you could do basic image classification, an you learned a little bit about Convolutional Neural Networks (ConvNets). In this course you'll go deeper into using ConvNets will real-world data, and learn about techniques that you can use to improve your ConvNet performance, particularly when doing image classification! In Week 1, this week, you'll get started by looking at a much larger dataset than you've been using thus far: The Cats and Dogs dataset which had been a Kaggle Challenge in image classification!

...
8 videos (Total 18 min), 5 readings, 3 quizzes
8 videos
A conversation with Andrew Ng1m
Training with the cats vs. dogs dataset2m
Working through the notebook4m
Fixing through cropping49s
Visualizing the effect of the convolutions1m
Looking at accuracy and loss1m
Week 1 Outro33s
5 readings
Before you Begin: TensorFlow 2.0 and this Course10m
The cats vs dogs dataset10m
Looking at the notebook10m
What you'll see next10m
What have we seen so far?10m
1 practice exercise
Week 1 Quiz30m
Week
2
4 hours to complete

Augmentation: A technique to avoid overfitting

You've heard the term overfitting a number of times to this point. Overfitting is simply the concept of being over specialized in training -- namely that your model is very good at classifying what it is trained for, but not so good at classifying things that it hasn't seen. In order to generalize your model more effectively, you will of course need a greater breadth of samples to train it on. That's not always possible, but a nice potential shortcut to this is Image Augmentation, where you tweak the training set to potentially increase the diversity of subjects it covers. You'll learn all about that this week!

...
7 videos (Total 14 min), 6 readings, 3 quizzes
7 videos
Introducing augmentation2m
Coding augmentation with ImageDataGenerator3m
Demonstrating overfitting in cats vs. dogs1m
Adding augmentation to cats vs. dogs1m
Exploring augmentation with horses vs. humans1m
Week 2 Outro37s
6 readings
Image Augmentation10m
Start Coding...10m
Looking at the notebook10m
The impact of augmentation on Cats vs. Dogs10m
Try it for yourself!10m
What have we seen so far?10m
1 practice exercise
Week 2 Quiz30m
Week
3
4 hours to complete

Transfer Learning

Building models for yourself is great, and can be very powerful. But, as you've seen, you can be limited by the data you have on hand. Not everybody has access to massive datasets or the compute power that's needed to train them effectively. Transfer learning can help solve this -- where people with models trained on large datasets train them, so that you can either use them directly, or, you can use the features that they have learned and apply them to your scenario. This is Transfer learning, and you'll look into that this week!

...
7 videos (Total 14 min), 5 readings, 3 quizzes
7 videos
Understanding transfer learning: the concepts2m
Coding transfer learning from the inception mode1m
Coding your own model with transferred features2m
Exploring dropouts1m
Exploring Transfer Learning with Inception1m
Week 3 Outro36s
5 readings
Start coding!10m
Adding your DNN10m
Using dropouts!10m
Applying Transfer Learning to Cats v Dogs10m
What have we seen so far?10m
1 practice exercise
Week 3 Quiz30m
Week
4
4 hours to complete

Multiclass Classifications

You've come a long way, Congratulations! One more thing to do before we move off of ConvNets to the next module, and that's to go beyond binary classification. Each of the examples you've done so far involved classifying one thing or another -- horse or human, cat or dog. When moving beyond binary into Categorical classification there are some coding considerations you need to take into account. You'll look at them this week!

...
6 videos (Total 12 min), 5 readings, 3 quizzes
6 videos
Moving from binary to multi-class classification44s
Explore multi-class with Rock Paper Scissors dataset2m
Train a classifier with Rock Paper Scissors1m
Test the Rock Paper Scissors classifier2m
Outro, A conversation with Andrew Ng1m
5 readings
Introducing the Rock-Paper-Scissors dataset10m
Check out the code!10m
Try testing the classifier10m
What have we seen so far?10m
Outro10m
1 practice exercise
Week 4 Quiz30m
4.7
39 ReviewsChevron Right

Top reviews from Convolutional Neural Networks in TensorFlow

By MHMay 24th 2019

A very comprehensive and easy to learn course on Tensor Flow. I am really impressed by the Instructor ability to teach difficult concept with ease. I will look forward another course of this series.

By CMMay 1st 2019

A patient and coherent introduction. At the end, you have good working code you can use elsewhere. Remarkably, the primary lecturer, Laurence Moroney, responds fairly quickly to posts in the forum.

Instructor

Avatar

Laurence Moroney

AI Advocate
Google Brain

About deeplearning.ai

deeplearning.ai is Andrew Ng's new venture which amongst others, strives for providing comprehensive AI education beyond borders....

About the TensorFlow in Practice Specialization

Discover the tools software developers use to build scalable AI-powered algorithms in TensorFlow, a popular open-source machine learning framework. In this four-course Specialization, you’ll explore exciting opportunities for AI applications. Begin by developing an understanding of how to build and train neural networks. Improve a network’s performance using convolutions as you train it to identify real-world images. You’ll teach machines to understand, analyze, and respond to human speech with natural language processing systems. Learn to process text, represent sentences as vectors, and input data to a neural network. You’ll even train an AI to create original poetry! AI is already transforming industries across the world. After finishing this Specialization, you’ll be able to apply your new TensorFlow skills to a wide range of problems and projects. Courses 1-3 are available now, with Course 4 launching in July....
TensorFlow in Practice

Frequently Asked Questions

  • Once you enroll for a Certificate, you’ll have access to all videos, quizzes, and programming assignments (if applicable). Peer review assignments can only be submitted and reviewed once your session has begun. If you choose to explore the course without purchasing, you may not be able to access certain assignments.

  • When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile. If you only want to read and view the course content, you can audit the course for free.

More questions? Visit the Learner Help Center.