1 / 20

What Are GANs? | Generative Adversarial Networks Tutorial | Deep Learning Tutorial | Simplilearn

Generative Adversarial Network are very popular in the field of Deep Learning. In this video, you will learn what GANs are and understand about Generators and Discriminators. You will understand how GANs works and look at the mathematical equation of GAN. Finally, you will learn the types od GANs and see the different applications of GANs. Let's begin.<br><br><br><br>This Deep Learning course with Tensorflow certification training is developed by industry leaders and aligned with the latest best practices. Youu2019ll master deep learning concepts and models using Keras and TensorFlow frameworks and implement deep learning algorithms, preparing you for a career as Deep Learning Engineer.<br><br>In this Deep Learning course with Keras and Tensorflow certification training, you will become familiar with the language and fundamental concepts of artificial neural networks, PyTorch, autoencoders, and more. Upon completion, you will be able to build deep learning models, interpret results, and build your own deep learning project.<br><br>Key features:<br>- 34 hours of Blended Learning<br>- Real-life industry-based projects<br>- 24/7 support with dedicated project mentoring sessions<br>- Flexibility to choose classes<br> - Dedicated mentoring session from our Industry expert faculties<br><br>Learn more at: https://bit.ly/2QbgDJu

Simplilearn
Download Presentation

What Are GANs? | Generative Adversarial Networks Tutorial | Deep Learning Tutorial | Simplilearn

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. What’s in it for you? • What are Generative Adversarial Networks • Generator • Discriminator • How GANs work? • Types of GANs • Applications of GANs

  2. What are Generative Adversarial Networks? Generative Adversarial Networks consist of two models that compete with each other to analyze, capture and copy the variations within a dataset Real Discriminator Fake Generator

  3. Click here to watch the video

  4. Generator The Generator in GAN learns to create fake data by incorporating feedback from the discriminator Generator network Fake Image Random Input

  5. Generator Training Discriminator Loss Real Images Sample Discriminator Generator Loss Generator Sample Random Input Backpropagation

  6. Discriminator The Discriminator in GAN is a classifier that identifies real data from the fake data created by the Generator Real Images Discriminator Network Fake Image

  7. Discriminator Training Backpropagation Discriminator Discriminator Loss Real Images Sample Generator Loss Generator Sample Random Input

  8. How GANs Work? GANs consist of 2 networks, a Generator G(x) and a Discriminator D(x) Real Images Discriminator Network Predicted Labels Real / Fake notes Generator Network Noise vector Fakes images

  9. How GANs Work? The Generator learn the distribution of data and is trained to increase the probability of the Discriminator network to make mistakes Real Images Discriminator Network Predicted Labels Real / Fake notes Generator Network Noise vector Fakes images

  10. How GANs Work? The Discriminator estimates the probability that the sample it got is from the training data and not from the Generator Real Images Discriminator Network Predicted Labels Real / Fake notes Generator Network Noise vector Fakes images

  11. How GANs Work? The mathematical formula for working on GANs can be represented as: V(D, G) = Ex~Pdata(x) [logD(x)] + Ez~p(z) [log(1 – D(G(z))] Where, G = Generator D = Discriminator Pdata(x) = distribution of real data p(z) = distribution of generator x = sample from Pdata(x) z = sample from P(z)D(x) = Discriminator networkG(z) = Generator network

  12. How GANs Work? Steps for training GAN • Define the problem • Choose the architecture of GAN • Train Discriminator on real data • Generate fake data for Generator • Train Discriminator on fake data • Train Generator with the output of Discriminator

  13. Types of GANs Deep Convolutional GANs (DCGANs) Vanilla GANs Simplest type of GAN where the Generator and Discriminator are simple multi-layer perceptrons DCGANs comprise of ConvNets and are more stable and generate higher quality images

  14. Types of GANs Conditional GANs (CGANs) Super Resolution GAN (SRGAN) SRGANs generate a photorealistic high-resolution image when given a low-resolution image CGANs use extra label information to generate better results

  15. Applications of GANs 1 Generating Cartoon Characters Using DCGANs, you can create faces of anime and Pokemon characters

  16. Applications of GANs 2 Generating Human Faces GANs can be trained on the images of humans to generate realistic faces

  17. Applications of GANs 3 Text to image translation GANs can build realistic images from textual descriptions of simple objects like birds Bird with a black head, yellow body and a short beak

  18. Applications of GANs 4 3-D Object Generation GANs can generate 3-D models using 2-D pictures of objects from multiple perspectives

  19. 1 VB. NET Reasons For Decline: • The language is seen to be bulky and clumsy • Work nowadays usually involves maintaining legacy applications or migrating to C# • Capabilities are limited to the Windows platform • Harsh declaration syntax and requirements, a rigid development environment and a lack of libraries

More Related