Generate Synthetic Images with DCGANs in Keras
Understand Deep Convolutional Generative Adversarial Networks (DCGANs and GANs)
Design and train DCGANs using the Keras API in Python
In this hands-on project, you will learn about Generative Adversarial Networks (GANs) and you will build and train a Deep Convolutional GAN (DCGAN) with Keras to generate images of fashionable clothes. We will be using the Keras Sequential API with Tensorflow 2 as the backend. In our GAN setup, we want to be able to sample from a complex, high-dimensional training distribution of the Fashion MNIST images. However, there is no direct way to sample from this distribution. The solution is to sample from a simpler distribution, such as Gaussian noise. We want the model to use the power of neural networks to learn a transformation from the simple distribution directly to the training distribution that we care about. The GAN consists of two adversarial players: a discriminator and a generator. We’re going to train the two players jointly in a minimax game theoretic formulation. This course runs on Coursera's hands-on project platform called Rhyme. On Rhyme, you do projects in a hands-on manner in your browser. You will get instant access to pre-configured cloud desktops containing all of the software and data you need for the project. Everything is already set up directly in your internet browser so you can just focus on learning. For this project, you’ll get instant access to a cloud desktop with Python, Jupyter, and Keras pre-installed. Notes: - You will be able to access the cloud desktop 5 times. However, you will be able to access instructions videos as many times as you want. - This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.
Kompetenzen, die Sie erwerben werden
- Deep Learning
- Machine Learning
- Tensorflow
- Computer Vision
- keras
Schritt für Schritt lernen
In einem Video, das auf einer Hälfte Ihres Arbeitsbereichs abgespielt wird, führt Sie Ihr Dozent durch diese Schritte:
Project Overview and Import Libraries
Load and Preprocess the Data
Create Batches of Training Data
Build the Generator Network for DCGAN
Build the Discriminator Network for DCGAN
Compile the Deep Convolutional Generative Adversarial Network (DCGAN)
Define the Training Procedure
Train DCGAN
Generate Synthetic Images with DCGAN
Ablauf angeleiteter Projekte
Ihr Arbeitsbereich ist ein Cloud-Desktop direkt in Ihrem Browser, kein Download erforderlich
Ihr Dozent leitet Sie in einem Video mit geteiltem Bildschirm Schritt für Schritt an.
Bewertungen
Top-Bewertungen von GENERATE SYNTHETIC IMAGES WITH DCGANS IN KERAS
The course was well equipped. It gave me the basic idea of how GAN works and how to implement it. If you want to get started with GAN then it can be a better course to lead you.
Everything was well explained and a very good project to get a good knowledge about GAN networks and its applications. Looking for more such projects.
In this course, you will learn about a lot of different ways to join ideas to make more complex and interesting knowledge of keras
The course was good but the cloud server had some issues initially but later that worked fine. Kudos to the Instructor!
Häufig gestellte Fragen
Häufig gestellte Fragen
Was bekomme ich, wenn ich ein angeleitetes Projekt kaufe?
Sind angeleitete Projekte auf dem Desktop und auf Mobilgeräten verfügbar?
Wer sind die Dozenten bei angeleiteten Projekten?
Kann ich die Arbeit aus meinem angeleiteten Projekt herunterladen, nachdem ich sie abgeschlossen habe?
Wie erfolgen Rückerstattungen?
Ist finanzielle Unterstützung möglich?
Kann ich ein angeleitetes Projekt auditieren und den Videoteil kostenlos anschauen?
Wie viel Erfahrung brauche ich für dieses angeleitete Projekt?
Kann ich dieses angeleitete Projekt direkt über meinen Webbrowser abschließen, anstatt spezielle Software zu installieren?
Wie ist die Lernerfahrung bei angeleiteten Projekten?
Haben Sie weitere Fragen? Besuchen Sie das Learner Help Center.
Coursera Footer
