Building Generative Adversarial Networks

Starting at USD 399.00
4 weeks duration

Learn how to build and train different generative adversarial network architectures to generate new images.

and gradient penalties. The course Building Generative Adversarial Networks on Udacity covers the fundamentals of GANs, including building generators and discriminators using fully connected and convolutional layers. It also teaches how to train GAN models on various datasets, such as MNIST, CIFAR10, and summer2winter Yosemite. Additionally, the course explores advanced topics like implementing Wasserstein loss, gradient penalties, and StyleGAN components. The final project involves building and training a custom GAN architecture on the CelebA dataset, incorporating different loss functions and stabilization techniques.

About Provider

Online Education Provider ยท 302 courses
Udacity is an online learning platform that offers a wide range of courses and programs in various fields such as technology, business, data science, and artificial intelligence. It was founded in 2012 by Sebastian Thrun, David Stavens, and Mike Sokolsky with the aim of providing accessible and affordable education to individuals worldwide. Udacity's courses are designed in collaboration with industry experts and leading companies, ensuring that the content is relevant and up-to-date. The platform offers both self-paced courses and guided programs, allowing learners to choose the learning style that suits them best. Udacity also provides career services and support, including resume reviews, interview preparation, and job placement assistance, to help learners transition into their desired careers.
You need to login in order to be able to rate the course.
Register Login


This course has not been reviewed by the community yet.