|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/apply-generative-adversarial-networks-gans
课程评论：没有评论
课程名称：应用生成对抗网络（GANs） 概述：在本课程中，您将： - 探讨GANs的应用，重点关注数据增强、隐私和匿名性 - 利用图像到图像的转换框架，识别与图像以外的其他模式相关的应用 - 实现Pix2Pix，一种配对图像到图像的转换GAN，将卫星图像转换为地图路线（反之亦然） - 比较配对图像到图像转换与非配对图像到图像转换，识别其关键差异并理解不同的GAN架构 - 实现CycleGAN，一种非配对图像到图像转换模型，将马转变为斑马（反之亦然），并使用两个GANs DeepLearning.AI生成对抗网络（GANs）专业课程为图像生成提供了激动人心的介绍，从基础概念到高级技术，通过易于理解的方式进行阐述。课程还涵盖社会影响，包括机器学习中的偏见及其检测方法、隐私保护等。 建立全面的知识基础并获得GANs的实践经验。使用PyTorch训练自己的模型，创建图像，并评估各种先进的GAN。 该专业课程为所有希望进入GAN领域或将GAN应用于自己项目的学习者提供了一个易于接近的途径，即使没有高级数学和机器学习研究的先前经验。 大纲： - 第一部分：第1周：用于数据增强和隐私的GANs 描述：学习GANs的不同应用，了解使用它们进行数据增强的利弊，以及它们如何改善下游AI模型！ - 第二部分：第2周：使用Pix2Pix进行图像到图像的转换 描述：理解图像到图像的转换，了解该框架的不同应用，实现U-Net生成器和Pix2Pix（配对图像到图像转换GAN）！ - 第三部分：第3周：使用CycleGAN进行非配对转换 描述：理解非配对图像到图像的转换与配对转换的不同，了解CycleGAN如何使用两个GAN实现该模型，并实现CycleGAN以转化马和斑马之间的形象！
Part: 1
Title:Week 1: GANs for Data Augmentation and Privacy
Description:Learn different applications of GANs, understand the pros/cons of using them for data augmentation, and see how they can improve downstream AI models!
Part: 2
Title:Week 2: Image-to-Image Translation with Pix2Pix
Description:Understand image-to-image translation, learn about different applications of this framework, and implement a U-Net generator and Pix2Pix, a paired image-to-image translation GAN!
Part: 3
Title:Week 3: Unpaired Translation with CycleGAN
Description:Understand how unpaired image-to-image translation differs from paired translation, learn how CycleGAN implements this model using two GANs, and implement a CycleGAN to transform between horses and zebras!
In this course, you will: - Explore the applications of GANs and examine them wrt data augmentation, privacy, and anonymity - Leverage the image-to-image translation framework and identify applications to modalities beyond images - Implement Pix2Pix, a paired image-to-image translation GAN, to adapt satellite images into map routes (and vice versa) - Compare paired image-to-image translation to unpaired image-to-image translation and identify how their key difference necessitates different GAN architectures - Implement CycleGAN, an unpaired image-to-image translation model, to adapt horses to zebras (and vice versa) with two GANs in one The DeepLearning.AI Generative Adversarial Networks (GANs) Specialization provides an exciting introduction to image generation with GANs, charting a path from foundational concepts to advanced techniques through an easy-to-understand approach. It also covers social implications, including bias in ML and the ways to detect it, privacy preservation, and more. Build a comprehensive knowledge base and gain hands-on experience in GANs. Train your own model using PyTorch, use it to create images, and evaluate a variety of advanced GANs. This Specialization provides an accessible pathway for all levels of learners looking to break into the GANs space or apply GANs to their own projects, even without prior familiarity with advanced math and machine learning research.
