Implement a Deep Convolutional Generative Adversarial Network (DCGAN).
Train a DCGAN to synthesize realistic looking images.
In this 2-hour long project-based course, you will learn to implement DCGAN or Deep Convolutional Generative Adversarial Network, and you will train the network to generate realistic looking synthesized images. The term Deepfake is typically associated with synthetic data generated by Neural Networks which is similar to real-world, observed data - often with synthesized images, videos or audio. Through this hands-on project, we will go through the details of how such a network is structured, trained, and will ultimately generate synthetic images similar to hand-written digit 0 from the MNIST dataset. Since this is a practical, project-based course, you will need to have a theoretical understanding of Neural Networks, Convolutional Neural Networks, and optimization algorithms like Gradient Descent. We will focus on the practical aspect of implementing and training DCGAN, but not too much on the theoretical aspect. You will also need some prior experience with Python programming. This course runs on Coursera's hands-on project platform called Rhyme. On Rhyme, you do projects in a hands-on manner in your browser. You will get instant access to pre-configured cloud desktops containing all of the software and data you need for the project. Everything is already set up directly in your internet browser so you can just focus on learning. For this project, you’ll get instant access to a cloud desktop with Python, Jupyter, and Tensorflow pre-installed. Notes: - You will be able to access the cloud desktop 5 times. However, you will be able to access instructions videos as many times as you want. - 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.
Importing and Plotting the Data
Generative Adversarial Network
Training the GAN
I had a very nice experience taking this project .The instructor simplifies the concepts and makes them easy to understand and a very nice introduction of Generative Adversarial Networks.
Very good course and way of explaining stuff. Technically from the scratch. Maybe inclusion of explanation of why the selected layers are selected on the first place.
This really helped me a lot. One should definitely try his (Amit Yadav) projects. Actually, all of it. Gonna be exploring more. I really loved it.
Its really helpful to start from here, I got some insights about how to proceed further.
购买指导项目后，您将获得完成指导项目所需的一切，包括通过 Web 浏览器访问云桌面工作空间，工作空间中包含您需要了解的文件和软件，以及特定领域的专家提供的分步视频说明。
我能直接通过 Web 浏览器来完成此指导项目，而不必安装特殊软件吗？