Deep Learning with PyTorch : Generative Adversarial Network

提供方
Coursera Project Network
在此指导项目中,您将:

Create Discriminator and Generator Network

Create a training loop to train GAN model

Clock2 hours
Intermediate中级
Cloud无需下载
Video分屏视频
Comment Dots英语(English)
Laptop仅限桌面

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.

您要培养的技能

  • Convolutional Neural Network
  • Python Programming
  • pytorch
  • Genrative Adversarial Network

分步进行学习

在与您的工作区一起在分屏中播放的视频中,您的授课教师将指导您完成每个步骤:

  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

指导项目工作原理

您的工作空间就是浏览器中的云桌面,无需下载

在分屏视频中,您的授课教师会为您提供分步指导

常见问题

常见问题

还有其他问题吗?请访问 学生帮助中心