Convolutional Neural Networks in TensorFlow

About this Course

In case you are a software program developer who needs to construct scalable AI-powered algorithms, you want to perceive tips on how to use the instruments to construct them. This course is a part of the upcoming Machine Studying in Tensorflow Specialization and can train you greatest practices for utilizing TensorFlow, a preferred open-source framework for machine studying.

In Course 2 of the deeplearning.ai TensorFlow Specialization, you’ll be taught superior methods to enhance the pc imaginative and prescient mannequin you inbuilt Course 1. You’ll discover tips on how to work with real-world pictures in numerous styles and sizes, visualize the journey of a picture by means of convolutions to grasp how a pc “sees” data, plot loss and accuracy, and discover methods to forestall overfitting, together with augmentation and dropout. Lastly, Course 2 will introduce you to switch studying and the way realized options might be extracted from fashions. The Machine Studying course and Deep Studying Specialization from Andrew Ng train an important and foundational ideas of Machine Studying and Deep Studying. This new deeplearning.ai TensorFlow Specialization teaches you tips on how to use TensorFlow to implement these ideas so that you could begin constructing and making use of scalable fashions to real-world issues. To develop a deeper understanding of how neural networks work, we suggest that you just take the Deep Studying Specialization.

WHAT YOU WILL LEARN

• Deal with real-world picture knowledge

• Plot loss and accuracy

• Discover methods to forestall overfitting, together with augmentation and dropout

• Study switch studying and the way realized options might be extracted from fashions

   

SKILLS YOU WILL GAIN

• Inductive Switch
• Augmentation
• Dropouts
• Machine Studying
• Tensorflow

Syllabus – What you’ll be taught from this course

Content material Score96%(13,017 scores)

WEEK

1

6 hours to finish

Exploring a Bigger Dataset

Within the first course on this specialization, you had an introduction to TensorFlow, and the way, with its excessive degree APIs you could possibly do fundamental picture classification, and also you realized just a little bit about Convolutional Neural Networks (ConvNets). On this course you’ll go deeper into utilizing ConvNets will real-world knowledge, and study methods that you should use to enhance your ConvNet efficiency, significantly when doing picture classification!In Week 1, this week, you’ll get began by taking a look at a a lot bigger dataset than you’ve been utilizing so far: The Cats and Canine dataset which had been a Kaggle Problem in picture classification!

WEEK

2

5 hours to finish

Augmentation: A method to keep away from overfitting

You’ve heard the time period overfitting various instances up to now. Overfitting is solely the idea of being over specialised in coaching — particularly that your mannequin is excellent at classifying what it’s skilled for, however not so good at classifying issues that it hasn’t seen. With a purpose to generalize your mannequin extra successfully, you’ll after all want a larger breadth of samples to coach it on. That’s not at all times doable, however a pleasant potential shortcut to that is Picture Augmentation, the place you tweak the coaching set to doubtlessly improve the variety of topics it covers. You’ll be taught all about that this week!

WEEK

3

3 hours to finish

Switch Studying

Constructing fashions for your self is nice, and might be very highly effective. However, as you’ve seen, you might be restricted by the info you will have available. Not all people has entry to large datasets or the compute energy that’s wanted to coach them successfully. Switch studying can assist clear up this — the place individuals with fashions skilled on massive datasets prepare them, so that you could both use them instantly, or, you should use the options that they’ve realized and apply them to your situation. That is Switch studying, and also you’ll look into that this week!

WEEK

4

4 hours to finish

Multiclass Classifications

You’ve come a great distance, Congratulations! Yet one more factor to do earlier than we transfer off of ConvNets to the following module, and that’s to transcend binary classification. Every of the examples you’ve accomplished thus far concerned classifying one factor or one other — horse or human, cat or canine. When shifting past binary into Categorical classification there are some coding issues you want to consider. You’ll have a look at them this week!