Chevron Left
Вернуться к Generate Synthetic Images with DCGANs in Keras

Отзывы учащихся о курсе Generate Synthetic Images with DCGANs in Keras от партнера Coursera Project Network

Оценки: 53
Рецензии: 13

О курсе

In this hands-on project, you will learn about Generative Adversarial Networks (GANs) and you will build and train a Deep Convolutional GAN (DCGAN) with Keras to generate images of fashionable clothes. We will be using the Keras Sequential API with Tensorflow 2 as the backend. In our GAN setup, we want to be able to sample from a complex, high-dimensional training distribution of the Fashion MNIST images. However, there is no direct way to sample from this distribution. The solution is to sample from a simpler distribution, such as Gaussian noise. We want the model to use the power of neural networks to learn a transformation from the simple distribution directly to the training distribution that we care about. The GAN consists of two adversarial players: a discriminator and a generator. We’re going to train the two players jointly in a minimax game theoretic formulation. 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 Keras 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....

Лучшие рецензии

Фильтр по:

1–13 из 13 отзывов о курсе Generate Synthetic Images with DCGANs in Keras

автор: Paras V

Jun 01, 2020

The course was good but the cloud server had some issues initially but later that worked fine. Kudos to the Instructor!

автор: Krishna V D

May 29, 2020

This course honestly felt like a joke, you're probably better off reading a medium article about GANs. Sure, It provides a very minimal objective, there are initially no instructions so there's nothing to explore, soon enough as you get into writing code, the more of a medium article it turns into except in video format.

автор: Andrea R

May 13, 2020

It does not really check what you did

автор: Abrar I A

May 27, 2020

The course was well equipped. It gave me the basic idea of how GAN works and how to implement it. If you want to get started with GAN then it can be a better course to lead you.

автор: Ahmed A

May 22, 2020

It's a very good start to know more about GANs

автор: Mayank S

May 01, 2020

Great Course, Learned a lot. Thanks Snehan.

автор: Saida M D C

May 25, 2020

I learned, now I understand. Thank you

автор: Rishabh R

May 17, 2020

Mostly likeable project & good

автор: Javier F B

Apr 24, 2020

Excellent course.

автор: Rajasinghe R

May 28, 2020

very goood

автор: Svitlana Z

May 05, 2020

This course helped me to start developing GANs. I would like to hear more theoretical explanations.

автор: Deep G

May 21, 2020

Good way to start out implementing DCGANS!!

автор: Krishnakanth A

Jun 04, 2020

Not recommended. The instructor uses his hidden functions in the project and never shows its code or let's us download it. So basically, this project can only be done on his cloud desktop but cannot be done anywhere else because of chucks of hidden code. This makes the project practically useless as it's not reproducible. Also, the instructors never reply to queries. The discussion forum is full of questions with zero responses.