Chevron Left
Voltar para Generate Synthetic Images with DCGANs in Keras

Comentários e feedback de alunos de Generate Synthetic Images with DCGANs in Keras da instituição Coursera Project Network

4.5
estrelas
241 classificações
47 avaliações

Sobre o curso

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....

Melhores avaliações

AA

26 de mai de 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.

AG

13 de jun de 2020

In this course, you will learn about a lot of different ways to join ideas to make more complex and interesting knowledge of keras

Filtrar por:

26 — 47 de 47 Avaliações para o Generate Synthetic Images with DCGANs in Keras

por SHANKAR

14 de jun de 2020

Trainer was awesome

por Gangone R

4 de jul de 2020

very useful course

por Javier F B

24 de abr de 2020

Excellent course.

por Ayush G

6 de out de 2020

nice project

por Umit K

9 de set de 2020

Thank you.

por Rajasinghe R

28 de mai de 2020

very goood

por Santiago G

22 de ago de 2020

Thanks!

por VETTORI F M

30 de ago de 2020

easy

por p s

23 de jun de 2020

Good

por tale p

16 de jun de 2020

good

por 321810306031 A C H

13 de jul de 2020

tx

por Ebin Z

9 de jun de 2020

Everything was well explained and a very good project to get a good knowledge about GAN networks and its applications. Looking for more such projects.

por Diego P P

10 de jun de 2020

I't's a good project, the theory should be more explained but in general was interesting to know about this network

por Svitlana Z

5 de mai de 2020

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

por Shakshi S

6 de ago de 2020

I tried this project and it is really good if you want to have idea about GANs and DCGANs.

por Srinadh R B

11 de set de 2020

Nice choice to start with the understanding of GANs.

por Deep G

21 de mai de 2020

Good way to start out implementing DCGANS!!

por sarithanakkala

23 de jun de 2020

Good

por vijayalode

24 de jun de 2020

na

por Akshita S

26 de jul de 2020

A bit overpriced for the amount of knowledge being shared.

por Simon S R

31 de ago de 2020

Still room for a lot of improvements, average material

por Zhiqiu L

10 de fev de 2022

The course spends too much time on the coding without explaining the model details.