Bringing a machine learning model into the real world involves a lot more than just modeling. This Specialization will teach you how to navigate various deployment scenarios and use data more effectively to train your model.
Этот курс входит в специализацию ''Специализация TensorFlow: Data and Deployment'
Device-based Models with TensorFlow Lite
от партнера
Об этом курсе
Недавно просмотрено: 57,158
Чему вы научитесь
Prepare models for battery-operated devices
Execute models on Android and iOS platforms
Deploy models on embedded systems like Raspberry Pi and microcontrollers
Приобретаемые навыки
TensorFlow LiteMathematical OptimizationMachine LearningTensorflowObject Detection
100% онлайн
Начните сейчас и учитесь по собственному графику.
Курс 2 из 4 в программе
Гибкие сроки
Назначьте сроки сдачи в соответствии со своим графиком.
Промежуточный уровень
Basic understanding of Kotlin and/or Swift
Прибл. 11 часов на выполнение
Предполагаемая нагрузка: 4 weeks of study, 4-5 hours/week
Английский
Субтитры: Английский
Программа курса: что вы изучите
6 ч. на завершение
Device-based models with TensorFlow Lite
Welcome to this course on TensorFlow Lite, an exciting technology that allows you to put your models directly and literally into people's hands. You'll start with a deep dive into the technology, and how it works, learning about how you can optimize your models for mobile use -- where battery power and processing power become an important factor. You'll then look at building applications on Android and iOS that use models, and you'll see how to use the TensorFlow Lite Interpreter in these environments. You'll wrap up the course with a look at embedded systems and microcontrollers, running your models on Raspberry Pi and SparkFun Edge boards.
6 ч. на завершение
14 видео ((всего 40 мин.)), 6 материалов для самостоятельного изучения, 2 тестов
14 видео
A few words from Laurence55
Features and components of mobile AI2мин
Architecture and performance3мин
Optimization Techniques2мин
Saving, converting, and optimizing a model3мин
Examples2мин
Quantization3мин
TF-Select1мин
Paths in Optimization1мин
Running the models1мин
Transfer learning3мин
Converting a model to TFLite1мин
Transfer learning with TFLite5мин
6 материалов для самостоятельного изучения
Prerequisites10мин
Downloading the Coding Examples and Exercises10мин
GPU delegates10мин
Learn about supported ops and TF-Select10мин
Week 1 Wrap up10мин
Exercise Description10мин
1 практическое упражнение
Week 1 Quiz
1 ч. на завершение
Running a TF model in an Android App
Last week you learned about TensorFlow Lite and you saw how to convert your models from TensorFlow to TensorFlow Lite format. You also learned about the standalone TensorFlow Lite Interpreter which could be used to test these models. You wrapped with an exercise that converted a Fashion MNIST based model to TensorFlow Lite and then tested it with the interpreter.
1 ч. на завершение
15 видео ((всего 36 мин.)), 3 материалов для самостоятельного изучения, 1 тест
15 видео
Installation and resources2мин
Architecture of a model1мин
Initializing the Interpreter2мин
Preparing the Input1мин
Inference and results1мин
Code walkthrough3мин
Run the App2мин
Classifying camera images55
Initialize and prepare input3мин
Demo of camera image classifier4мин
Initialize model and prepare inputs1мин
Inference and results3мин
Demo of the object detection App1мин
Code for the inference and results2мин
3 материала для самостоятельного изучения
Android fundamentals and installation10мин
Week 2 Wrap up10мин
Description10мин
1 практическое упражнение
Week 2 Quiz
2 ч. на завершение
Building the TensorFLow model on IOS
The other popular mobile operating system is, of course, iOS. So this week you'll do very similar tasks to last week -- learning how to take models and run them on iOS. You'll need some programming background with Swift for iOS to fully understand everything we go through, but even if you don't have this expertise, I think this weeks content is something you'll find fun to explore -- and you'll learn how to build a variety of ML applications that run on this important operating system!
2 ч. на завершение
22 видео ((всего 45 мин.)), 8 материалов для самостоятельного изучения, 1 тест
22 видео
A few words from Laurence1мин
What is Swift?45
TerserflowLiteSwift1мин
Cats vs Dogs App1мин
Taking the initial steps3мин
Scaling the image2мин
More steps in the process3мин
Looking at the App in Xcode5мин
What have we done so far and how do we continue?41
Using the App50
App architecture1мин
Model details1мин
Initial steps4мин
Final steps1мин
Looking at the code for the image classification App4мин
Object classification intro30
TFL detect App53
App architecture55
Initial steps58
Final steps3мин
Looking at the code for the object detection model3мин
8 материалов для самостоятельного изучения
Important links10мин
Apple’s developer's site 10мин
Apple's API10мин
More details10мин
Camera related functionalities10мин
The Coco dataset10мин
Week 3 Wrap up10мин
Description10мин
1 практическое упражнение
Week 3 Quiz
2 ч. на завершение
TensorFlow Lite on devices
Now that you've looked at TensorFlow Lite and explored building apps on Android and iOS that use it, the next and final step is to explore embedded systems like Raspberry Pi, and learn how to get your models running on that. The nice thing is that the Pi is a full Linux system, so it can run Python, allowing you to either use the full TensorFlow for Training and Inference, or just the Interpreter for Inference. I'd recommend the latter, as training on a Pi can be slow!
2 ч. на завершение
13 видео ((всего 29 мин.)), 7 материалов для самостоятельного изучения, 1 тест
13 видео
A few words from Laurence3мин
Devices3мин
Starting to work on a Raspberry Pi1мин
How do we start?2мин
Image classification1мин
The 4 step process2мин
Object detection1мин
Back to the 4 step process4мин
Raspberry Pi demo2мин
Microcontrollers2мин
Closing words by Laurence28
A conversation with Andrew Ng1мин
7 материалов для самостоятельного изучения
Edge TPU models10мин
Options to choose from10мин
Pre optimized mobileNet10мин
Object detection model trained on the coco10мин
Suggested links10мин
Description10мин
Wrap up10мин
1 практическое упражнение
Week 4 Quiz
Рецензии
4.6
Лучшие отзывы о курсе DEVICE-BASED MODELS WITH TENSORFLOW LITE
от партнера JTMar 30, 2020
One of the most useful and exciting courses I've ever done! Especially for the information available in the last (4th) week. Very interesting material and full of practical potential!
от партнера MMJan 11, 2020
Great course, very practical in the real world. It also balances and accommodates developers on what devices you have available. Looking forward to the next course
от партнера BCJan 16, 2020
Interesting course on how to use Tensorflow Lite on mobile phone or raspberry. More projects & sometimes more explanations about configuration would be necessary.
от партнера RSFeb 14, 2020
Just one recommendation, may be an exercise on a NLP Model deployment (Text or audio) could have been added rather than all 3 examples of computer vision
от партнера MEApr 1, 2020
Great course to teach a non-technical, non-cse person, with all basics to implement and use the AI models with all android, iOS and Raspberry devices.
от партнера APMar 30, 2020
Was a great course.Had some hands on experience on codes using Gcollabs.Additionally helped me complete my project of deploying ML on android.
от партнера FLMar 18, 2020
Same as the previous course of this specialization:\n\nThe assignments are not very challenging. But the exercises are really cool!!
от партнера SMFeb 4, 2020
excellent course with practical examples on using TensorFlow Lite on Raspberry, Android and iOS
от партнера BBMar 22, 2020
Nice Course! The course contents are awesome eager to use this in all my learning in future
от партнера MRJan 4, 2020
A great course to learn how to implement any Deep Learning models on edge devices.
от партнера CFFeb 8, 2020
Great course, a bit short of content and exercises but it was well designed.
от партнера IMMar 10, 2020
It could be more coding exercises, but as for the general info it's great.
О deeplearning.ai
deeplearning.ai is Andrew Ng's new venture which amongst others, strives for providing comprehensive AI education beyond borders.
Специализация TensorFlow: Data and Deployment: общие сведения
Continue developing your skills in TensorFlow as you learn to navigate through a wide range of deployment scenarios and discover new ways to use data more effectively when training your machine learning models.
In this four-course Specialization, you’ll learn how to get your machine learning models into the hands of real people on all kinds of devices. Start by understanding how to train and run machine learning models in browsers and in mobile applications. Learn how to leverage built-in datasets with just a few lines of code, learn about data pipelines with TensorFlow data services, use APIs to control data splitting, process all types of unstructured data and retrain deployed models with user data while maintaining data privacy. Apply your knowledge in various deployment scenarios and get introduced to TensorFlow Serving, TensorFlow, Hub, TensorBoard, and more.
Industries all around the world are adopting Artificial Intelligence. This Specialization from Laurence Moroney and Andrew Ng will help you develop and deploy machine learning models across any device or platform faster and more accurately than ever.
This Specialization builds upon skills learned in the TensorFlow in Practice Specialization. We recommend learners complete that Specialization prior to enrolling in TensorFlow: Data and Deployment.
Часто задаваемые вопросы
Когда я получу доступ к лекциям и заданиям?
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.
Что я получу, оформив подписку на специализацию?
Записавшись на курс, вы получите доступ ко всем курсам в специализации, а также возможность получить сертификат о его прохождении. 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.
Какие правила возврата средств?
Можно ли получить финансовую помощь?
Остались вопросы? Посетите Центр поддержки учащихся.
