Deep Learning with PyTorch : Generative Adversarial Network

Offered By
Coursera Project Network
In this Guided Project, you will:

Create Discriminator and Generator Network

Create a training loop to train GAN model

Clock2 hours
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

In this two hour project-based course, you will implement Deep Convolutional Generative Adversarial Network using PyTorch to generate handwritten digits. You will create a generator that will learn to generate images that look real and a discriminator that will learn to tell real images apart from fakes. This hands-on-project will provide you the detail information on how to implement such network and train to generate handwritten digit images. In order to be successful in this project, you will need to have a theoretical understanding on convolutional neural network and optimization algorithm like Adam or gradient descent. This project will focus more on the practical aspect of DCGAN and less on theoretical aspect. Note: 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.

Skills you will develop

Convolutional Neural NetworkPython ProgrammingpytorchGenrative Adversarial Network

Learn step-by-step

In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:

  1. Setup Google Runtime

  2. Configurations

  3. Load MNIST Handwritten Dataset

  4. Load Dataset into Batches

  5. Create Discriminator Network

  6. Create Generator Network

  7. Create Loss Function and Load Optimizers

  8. Training GAN

How Guided Projects work

Your workspace is a cloud desktop right in your browser, no download required

In a split-screen video, your instructor guides you step-by-step

Frequently asked questions

Frequently Asked Questions

More questions? Visit the Learner Help Center.