Об этом курсе
292,110

100% онлайн

Начните сейчас и учитесь по собственному графику.

Гибкие сроки

Назначьте сроки сдачи в соответствии со своим графиком.

Промежуточный уровень

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

Прибл. 6 часа на выполнение

Предполагаемая нагрузка: 4 weeks of study, 4-5 hours/week...

Английский

Субтитры: Английский

Чему вы научитесь

  • 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

Приобретаемые навыки

Inductive TransferAugmentationDropoutsMachine LearningTensorflow

100% онлайн

Начните сейчас и учитесь по собственному графику.

Гибкие сроки

Назначьте сроки сдачи в соответствии со своим графиком.

Промежуточный уровень

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

Прибл. 6 часа на выполнение

Предполагаемая нагрузка: 4 weeks of study, 4-5 hours/week...

Английский

Субтитры: Английский

Программа курса: что вы изучите

Неделя
1
4 ч. на завершение

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 видео ((всего 18 мин.)), 6 материалов для самостоятельного изучения, 3 тестов
8 видео
A conversation with Andrew Ng1мин
Training with the cats vs. dogs dataset2мин
Working through the notebook4мин
Fixing through cropping49
Visualizing the effect of the convolutions1мин
Looking at accuracy and loss1мин
Week 1 Outro33
6 материала для самостоятельного изучения
Before you Begin: TensorFlow 2.0 and this Course10мин
The cats vs dogs dataset10мин
Looking at the notebook10мин
What you'll see next10мин
What have we seen so far?10мин
Getting ready for the exercise10мин
1 практическое упражнение
Week 1 Quiz30мин
Неделя
2
4 ч. на завершение

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 видео ((всего 14 мин.)), 7 материалов для самостоятельного изучения, 3 тестов
7 видео
Introducing augmentation2мин
Coding augmentation with ImageDataGenerator3мин
Demonstrating overfitting in cats vs. dogs1мин
Adding augmentation to cats vs. dogs1мин
Exploring augmentation with horses vs. humans1мин
Week 2 Outro37
7 материала для самостоятельного изучения
Image Augmentation10мин
Start Coding...10мин
Looking at the notebook10мин
The impact of augmentation on Cats vs. Dogs10мин
Try it for yourself!10мин
What have we seen so far?10мин
Getting ready for the exercise10мин
1 практическое упражнение
Week 2 Quiz30мин
Неделя
3
4 ч. на завершение

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 видео ((всего 14 мин.)), 6 материалов для самостоятельного изучения, 3 тестов
7 видео
Understanding transfer learning: the concepts2мин
Coding transfer learning from the inception mode1мин
Coding your own model with transferred features2мин
Exploring dropouts1мин
Exploring Transfer Learning with Inception1мин
Week 3 Outro36
6 материала для самостоятельного изучения
Start coding!10мин
Adding your DNN10мин
Using dropouts!10мин
Applying Transfer Learning to Cats v Dogs10мин
What have we seen so far?10мин
Getting ready for the exercise10мин
1 практическое упражнение
Week 3 Quiz30мин
Неделя
4
4 ч. на завершение

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 видео ((всего 12 мин.)), 6 материалов для самостоятельного изучения, 3 тестов
6 видео
Moving from binary to multi-class classification44
Explore multi-class with Rock Paper Scissors dataset2мин
Train a classifier with Rock Paper Scissors1мин
Test the Rock Paper Scissors classifier2мин
Outro, A conversation with Andrew Ng1мин
6 материала для самостоятельного изучения
Introducing the Rock-Paper-Scissors dataset10мин
Check out the code!10мин
Try testing the classifier10мин
What have we seen so far?10мин
Getting ready for the exercise10мин
Outro10мин
1 практическое упражнение
Week 4 Quiz30мин
4.8
Рецензии: 14Chevron Right

Лучшие рецензии

автор: 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.

автор: RCMay 15th 2019

Excellent material superbly presented by world-class experts.\n\nSorry if this sounds sycophantic, but this series contains some of the best courses I've encountered in50+ years of learning.

Преподаватели

Avatar

Laurence Moroney

AI Advocate
Google Brain

О deeplearning.ai

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

Часто задаваемые вопросы

  • Зарегистрировавшись на сертификацию, вы получите доступ ко всем видео, тестам и заданиям по программированию (если они предусмотрены). Задания по взаимной оценке сокурсниками можно сдавать и проверять только после начала сессии. Если вы проходите курс без оплаты, некоторые задания могут быть недоступны.

  • Оплатив сертификацию, вы получите доступ ко всем материалам курса, включая оцениваемые задания. После успешного прохождения курса на странице ваших достижений появится электронный сертификат. Оттуда его можно распечатать или прикрепить к профилю LinkedIn. Просто ознакомиться с содержанием курса можно бесплатно.

Остались вопросы? Посетите Центр поддержки учащихся.