Expand your skill set and master TensorFlow. Customize your machine learning models through four hands-on courses!

4.8

étoiles

918 évaluations

Laurence Moroney +1 enseignant de plus

14 636 déjà inscrits

Offert par

Spécialisation TensorFlow: Advanced Techniquesdeeplearning.ai

Ce que vous allez apprendre

Understand the underlying basis of the Functional API and build exotic non-sequential model types, custom loss functions, and layers.

Learn optimization and how to use GradientTape & Autograph, optimize training in different environments with multiple processors and chip types.

Practice object detection, image segmentation, and visual interpretation of convolutions.

Explore generative deep learning, and how AIs can create new content, from Style Transfer through Auto Encoding and VAEs to GANs.

Compétences que vous acquerrez

Model Interpretability
Custom Training Loops
Custom and Exotic Models
Generative Machine Learning
Object Detection
Functional API
Custom Layers
Custom and Exotic Models with Functional API
Custom Loss Functions
Distribution Strategies
Basic Tensor Functionality
GradientTape for Optimization

À propos de ce Spécialisation

16 575 consultations récentes

About TensorFlow TensorFlow is an end-to-end open-source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries, and community resources that lets researchers push the state-of-the-art in ML, and developers easily build and deploy ML-powered applications. TensorFlow is commonly used for machine learning applications such as voice recognition and detection, Google Translate, image recognition, and natural language processing. About this Specialization Expand your knowledge of the Functional API and build exotic non-sequential model types. Learn how to optimize training in different environments with multiple processors and chip types and get introduced to advanced computer vision scenarios such as object detection, image segmentation, and interpreting convolutions. Explore generative deep learning including the ways AIs can create new content from Style Transfer to Auto Encoding, VAEs, and GANs. About you This Specialization is for software and machine learning engineers with a foundational understanding of TensorFlow who are looking to expand their knowledge and skill set by learning advanced TensorFlow features to build powerful models. Looking for a place to start? Master foundational basics with the DeepLearning.AI TensorFlow Developer Professional Certificate. Ready to deploy your models to the world? Learn how to go live with the TensorFlow: Data and Deployment Specialization.

Projet d'apprentissage appliqué

In this Specialization, you will gain practical knowledge of and hands-on training in advanced TensorFlow techniques such as style transfer, object detection, and generative machine learning.

Course 1: Understand the underlying basis of the Functional API and build exotic non-sequential model types, custom loss functions, and layers.

Course 2: Learn how optimization works and how to use GradientTape and Autograph. Optimize training in different environments with multiple processors and chip types.

Course 3: Practice object detection, image segmentation, and visual interpretation of convolutions.

Course 4: Explore generative deep learning and how AIs can create new content, from Style Transfer through Auto Encoding and VAEs to Generative Adversarial Networks.

Certificat partageable

Obtenez un Certificat lorsque vous terminez

Cours en ligne à 100 %

Commencez dès maintenant et apprenez aux horaires qui vous conviennent.

Planning flexible

Définissez et respectez des dates limites flexibles.

Niveau intermédiaire

Basic calculus, linear algebra, stats
Knowledge of AI, deep learning
Experience with Python, TF/Keras/PyTorch framework, decorator, context manager

Approximativement 5 mois pour terminer

Rythme recommandé de 7 heures/semaine

Anglais

Sous-titres : Anglais

Certificat partageable

Obtenez un Certificat lorsque vous terminez

Cours en ligne à 100 %

Commencez dès maintenant et apprenez aux horaires qui vous conviennent.

Planning flexible

Définissez et respectez des dates limites flexibles.

Niveau intermédiaire

Basic calculus, linear algebra, stats
Knowledge of AI, deep learning
Experience with Python, TF/Keras/PyTorch framework, decorator, context manager

Approximativement 5 mois pour terminer

Rythme recommandé de 7 heures/semaine

Anglais

Sous-titres : Anglais

Comment fonctionne la Spécialisation

Suivez les cours

Une Spécialisation Coursera est une série de cours axés sur la maîtrise d'une compétence. Pour commencer, inscrivez-vous directement à la Spécialisation ou passez en revue ses cours et choisissez celui par lequel vous souhaitez commencer. Lorsque vous vous abonnez à un cours faisant partie d'une Spécialisation, vous êtes automatiquement abonné(e) à la Spécialisation complète. Il est possible de terminer seulement un cours : vous pouvez suspendre votre formation ou résilier votre abonnement à tout moment. Rendez-vous sur votre tableau de bord d'étudiant pour suivre vos inscriptions aux cours et vos progrès.

Projet pratique

Chaque Spécialisation inclut un projet pratique. Vous devez réussir le(s) projet(s) pour terminer la Spécialisation et obtenir votre Certificat. Si la Spécialisation inclut un cours dédié au projet pratique, vous devrez terminer tous les autres cours avant de pouvoir le commencer.

Obtenir un Certificat

Lorsque vous aurez terminé tous les cours et le projet pratique, vous obtiendrez un Certificat que vous pourrez partager avec des employeurs éventuels et votre réseau professionnel.

Cette Spécialisation compte 4 cours

Cours1

Cours 1

Custom Models, Layers, and Loss Functions with TensorFlow

4.9

étoiles

696 évaluations

•

151 avis

In this course, you will:

• Compare Functional and Sequential APIs, discover new models you can build with the Functional API, and build a model that produces multiple outputs including a Siamese network. • Build custom loss functions (including the contrastive loss function used in a Siamese network) in order to measure how well a model is doing and help your neural network learn from training data. • Build off of existing standard layers to create custom layers for your models, customize a network layer with a lambda layer, understand the differences between them, learn what makes up a custom layer, and explore activation functions. • Build off of existing models to add custom functionality, learn how to define your own custom class instead of using the Functional or Sequential APIs, build models that can be inherited from the TensorFlow Model class, and build a residual network (ResNet) through defining a custom model class. The DeepLearning.AI TensorFlow: Advanced Techniques Specialization introduces the features of TensorFlow that provide learners with more control over their model architecture and tools that help them create and train advanced ML models. This Specialization is for early and mid-career software and machine learning engineers with a foundational understanding of TensorFlow who are looking to expand their knowledge and skill set by learning advanced TensorFlow features to build powerful models.

Cours2

Cours 2

Custom and Distributed Training with TensorFlow

4.8

étoiles

287 évaluations

•

41 avis

In this course, you will:

• Learn about Tensor objects, the fundamental building blocks of TensorFlow, understand the difference between the eager and graph modes in TensorFlow, and learn how to use a TensorFlow tool to calculate gradients. • Build your own custom training loops using GradientTape and TensorFlow Datasets to gain more flexibility and visibility with your model training. • Learn about the benefits of generating code that runs in graph mode, take a peek at what graph code looks like, and practice generating this more efficient code automatically with TensorFlow’s tools. • Harness the power of distributed training to process more data and train larger models, faster, get an overview of various distributed training strategies, and practice working with a strategy that trains on multiple GPU cores, and another that trains on multiple TPU cores. The DeepLearning.AI TensorFlow: Advanced Techniques Specialization introduces the features of TensorFlow that provide learners with more control over their model architecture and tools that help them create and train advanced ML models. This Specialization is for early and mid-career software and machine learning engineers with a foundational understanding of TensorFlow who are looking to expand their knowledge and skill set by learning advanced TensorFlow features to build powerful models.

Cours3

Cours 3

Advanced Computer Vision with TensorFlow

4.8

étoiles

322 évaluations

•

53 avis

In this course, you will:

a) Explore image classification, image segmentation, object localization, and object detection. Apply transfer learning to object localization and detection. b) Apply object detection models such as regional-CNN and ResNet-50, customize existing models, and build your own models to detect, localize, and label your own rubber duck images. c) Implement image segmentation using variations of the fully convolutional network (FCN) including U-Net and d) Mask-RCNN to identify and detect numbers, pets, zombies, and more. d) Identify which parts of an image are being used by your model to make its predictions using class activation maps and saliency maps and apply these ML interpretation methods to inspect and improve the design of a famous network, AlexNet. The DeepLearning.AI TensorFlow: Advanced Techniques Specialization introduces the features of TensorFlow that provide learners with more control over their model architecture and tools that help them create and train advanced ML models. This Specialization is for early and mid-career software and machine learning engineers with a foundational understanding of TensorFlow who are looking to expand their knowledge and skill set by learning advanced TensorFlow features to build powerful models.

Cours4

Cours 4

Generative Deep Learning with TensorFlow

4.8

étoiles

175 évaluations

•

28 avis

In this course, you will:

a) Learn neural style transfer using transfer learning: extract the content of an image (eg. swan), and the style of a painting (eg. cubist or impressionist), and combine the content and style into a new image. b) Build simple AutoEncoders on the familiar MNIST dataset, and more complex deep and convolutional architectures on the Fashion MNIST dataset, understand the difference in results of the DNN and CNN AutoEncoder models, identify ways to de-noise noisy images, and build a CNN AutoEncoder using TensorFlow to output a clean image from a noisy one. c) Explore Variational AutoEncoders (VAEs) to generate entirely new data, and generate anime faces to compare them against reference images. d) Learn about GANs; their invention, properties, architecture, and how they vary from VAEs, understand the function of the generator and the discriminator within the model, the concept of 2 training phases and the role of introduced noise, and build your own GAN that can generate faces. The DeepLearning.AI TensorFlow: Advanced Techniques Specialization introduces the features of TensorFlow that provide learners with more control over their model architecture, and gives them the tools to create and train advanced ML models. This Specialization is for early and mid-career software and machine learning engineers with a foundational understanding of TensorFlow who are looking to expand their knowledge and skill set by learning advanced TensorFlow features to build powerful models.

Enseignants

Laurence Moroney

Instructor

Lead AI Advocate, Google

364 912 étudiants

15 cours

Eddy Shyu

Senior Curriculum Developer

Product Lead, DeepLearning.AI

176 537 étudiants

11 cours

Offert par

deeplearning.ai

DeepLearning.AI is an education technology company that develops a global community of AI talent.

Foire Aux Questions

Quelle est la politique de remboursement ?
Si vous vous abonnez, vous bénéficiez d'une période d'essai gratuite de 7 jours, durant laquelle vous pouvez annuler votre abonnement sans pénalité. Ensuite, nous n'accordons plus de remboursements, mais vous pouvez annuler votre abonnement à tout instant. Consultez notre politique de remboursement complète.
Puis-je m'inscrire à un seul cours ?
Oui ! Pour commencer, cliquez sur la carte du cours qui vous intéresse et inscrivez-vous. Vous pouvez vous inscrire et terminer le cours pour obtenir un Certificat partageable, ou vous pouvez accéder au cours en auditeur libre afin d'en visualiser gratuitement le contenu. Si vous vous abonnez à un cours faisant partie d'une Spécialisation, vous êtes automatiquement abonné(e) à la Spécialisation complète. Visitez votre tableau de bord d'étudiant(e) pour suivre vos progrès.
Une aide financière est-elle possible ?
Oui. Dans certains programmes d’apprentissage, vous pouvez demander une aide financière ou une bourse d’études si vous ne pouvez pas payer les frais d’inscription. Si une aide financière ou une bourse d’études est disponible pour le programme d’apprentissage choisi, vous trouverez un lien pour faire une demande sur la page de description.
Puis-je suivre le cours gratuitement ?
Si vous vous inscrivez au cours, vous pouvez accéder à tous les cours de la Spécialisation et obtenir un Certificat lorsque vous terminez le travail. Si vous souhaitez seulement lire et examiner le contenu du cours, vous pouvez accéder gratuitement au cours en auditeur libre. Si vous n'avez pas les moyens d'acquitter les frais, vous pouvez faire une demande d'Aide Financière.
Ce cours est-il vraiment accessible en ligne à 100 % ? Dois-je assister à certaines activités en personne ?
Ce cours est entièrement en ligne : vous n'avez donc pas besoin de vous présenter physiquement dans une salle de classe. Vous pouvez accéder à vos vidéos de cours, lectures et devoirs en tout temps et en tout lieu, par l'intermédiaire du Web ou de votre appareil mobile.
What is TensorFlow?
TensorFlow is an end-to-end opensource platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries, and community resources that lets researchers push the state-of-the-art in ML, and developers easily build and deploy ML-powered applications.
What are the applications of TensorFlow?
TensorFlow is commonly used for machine learning applications such as voice recognition and detection, Google Translate, image recognition, and natural language processing.
Why is TensorFlow important?
TensorFlow is one of the most commonly used open-source libraries used for building and deploying ML models.
What is the TensorFlow specialization about?
The DeepLearning.AI TensorFlow: Advanced Techniques Specialization introduces the features of TensorFlow that provide learners with more control over their model architecture and tools that help them create and train advanced ML models.
In this Specialization, you will expand your knowledge of the Functional API and build exotic non-sequential model types. You will learn how to optimize training in different environments with multiple processors and chip types and get introduced to advanced computer vision scenarios such as object detection, image segmentation, and interpreting convolutions. You will also explore generative deep learning including the ways AIs can create new content from Style Transfer to Auto Encoding, VAEs, and GANs.
I’ve already completed the DeepLearning.AI TensorFlow Developer Professional Certificate. What else will I learn in this Specialization?
The DeepLearning.AI TensorFlow Developer Professional Certificate equips you with the foundational knowledge to create entry-level TensorFlow models using the Sequential API and prepares you for the Google TensorFlow Developer Certificate exam.
In this new TensorFlow Specialization, you will expand your skill set and take your understanding of TensorFlow techniques to the next level. You will learn how to use the Functional API for custom training, custom layers, and custom models. You will be equipped to master TensorFlow in order to build powerful applications for complex scenarios.
What will I learn in this Specialization?
Specialization: Gain practical knowledge of and hands-on training in advanced TensorFlow techniques such as style transfer (paint one picture in the style of another), object detection (detect where an object is in a picture), and generative machine learning (generating new images from scratch).
Course 1: Understand the underlying basis of the Functional API and build exotic non-sequential model types, custom loss functions, and layers.
Course 2: Learn how optimization works and how to use GradientTape and Autograph. Optimize training in different environments with multiple processors and chip types.
Course 3: Practice object detection, image segmentation, and visual interpretation of convolutions.
Course 4: Explore generative deep learning and how AIs can create new content, from Style Transfer through Auto Encoding and VAEs to Generative Adversarial Networks.
Who is the TensorFlow Specialization for?
The TensorFlow: Advanced Techniques Specialization provides an accessible pathway for early and mid-career software and machine learning engineers with a foundational knowledge of TensorFlow looking to master TensorFlow by teaching them how to use advanced features in order to expand their skill set and build powerful models.
What background knowledge is necessary?
Learners should have a working knowledge of AI and deep learning. They should have intermediate Python skills (understanding of decorators and context managers is preferred) as well as some experience with any deep learning framework (TensorFlow, Keras, or PyTorch). Learners should be proficient in basic calculus, linear algebra, and statistics.
We highly recommend that you complete the Deep Learning Specialization prior to starting this Specialization.
What will I be able to do upon completing the Specialization?
After completing this Specialization, you will gain practical knowledge and hands-on training in advanced TensorFlow techniques such as style transfer, object detection, and generative machine learning.
Who created the TensorFlow Specialization?
This Specialization was created by Laurence Moroney.
Laurence leads AI Advocacy at Google, with a vision to make AI easy for developers and to widen access to ML careers for everyone. He’s written dozens of programming books, the most recent being ‘AI and ML for Coders’ at O’Reilly. Laurence believes that MOOCs are one of the greatest ways to learn, and is excited to create TensorFlow Specializations with DeepLearning.AI on Coursera.
When not working with technology, he’s an active member of the Science Fiction Writers of America and has authored several sci-fi novels and comics books and a produced screenplay. Laurence is based in Washington state, where he drinks way too much coffee.
Is this a standalone course or a Specialization?
This is a Specialization made up of 4 courses.
Do I need to take the courses in a specific order?
We recommend taking the courses in the prescribed order for a logical and thorough learning experience.
Can I audit this Specialization?
You can audit the courses in the Specialization for free. You will not receive a certificate at the end if you choose to audit it for free instead of purchasing it.
Quelle est la durée nécessaire pour terminer la Spécialisation ?
This Specialization consists of four courses. At the rate of 5 hours a week, it typically takes 3-4 weeks to complete each course.
Puis-je obtenir des crédits universitaires si je réussis la Spécialisation ?
No

D'autres questions ? Visitez le Centre d'Aide pour les Étudiants.