how to fulfill GAN (Generative Adversarial Networks ) or DCGAN in matlab?

Question

Jack Xiao 2018-7-13

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/410141-how-to-fulfill-gan-generative-adversarial-networks-or-dcgan-in-matlab

评论： Walter Roberson 2020-4-13

I find that there is no example demo for GAN (Generative Adversarial Networks ) or DCGAN. I wonder how to fulfill GAN in matlab? if for GAN, is the last output of the generator RegressionOutputLayer or others?

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Kenta 2020-4-13

Please check the file below. This is an example of conditional GAN.

https://jp.mathworks.com/matlabcentral/fileexchange/74921-conditional-gan-generative-adversarial-network-with-mnist

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Muhammad Usama Sharaf SAAFI 2020-1-7

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/410141-how-to-fulfill-gan-generative-adversarial-networks-or-dcgan-in-matlab#answer_409050

编辑：Muhammad Usama Sharaf SAAFI 2020-1-7

Only MATLAB 2019b has demo example of GAN.Example code also works on GPU but you should have CUDA 10.1 driver installed in your system However you can also look below link if you donot have Matlab 2019b.

https://github.com/JZhaoCH/GAN-Base-on-Matlab

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

Answer 2

Walter Roberson 2018-7-13

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/410141-how-to-fulfill-gan-generative-adversarial-networks-or-dcgan-in-matlab#answer_328673

Generative Adversarial Neural Networks are not available in any Mathworks product. They are not supported by the Neural Network toolbox.

2 个评论
显示无隐藏无

Jack Xiao 2018-7-13

what a pity! looking forward to the supporting!

Jony Castagna 2019-9-27

Just looked at version 2019b: they support GANs now!

请先登录，再进行评论。

Answer 3

mohammed mahmoud 2018-7-29

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/410141-how-to-fulfill-gan-generative-adversarial-networks-or-dcgan-in-matlab#answer_330785

View this link dcgan-matconvnet

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

Answer 4

azad 2018-9-17

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/410141-how-to-fulfill-gan-generative-adversarial-networks-or-dcgan-in-matlab#answer_337112

still no GAN support !

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Jack Xiao 2019-1-13

Yes, so sad... hope coming soon...

请先登录，再进行评论。

Answer 5

Niklas 2019-7-7

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/410141-how-to-fulfill-gan-generative-adversarial-networks-or-dcgan-in-matlab#answer_382246

In our team we realize GANs with regression layers as output layer. Works fine in our cases.

You also have the possibility to define own layers: See this doc https://de.mathworks.com/help/deeplearning/ug/define-custom-deep-learning-layers.html for further Informations.

Best wishes, Niklas

2 个评论
显示无隐藏无

Jack Xiao 2019-7-8

thank you, i wonder how do you train discriminator as there are still no demos for training multiple nets simultaneously at present?

can you release your project or any detailed information?

Niklas 2019-7-8

Unfortunately I can not upload the code.

We use a RBM for our generator model. This we pretrain with own code but this part is very similar to the code snippets from Geoffrey Hinton. We also train a CNN for the descriminator part before we stick both models together. So after pretraining the CNN is very good in decisions whether an image is generated or a real one.

Afterwards we use some tricks. First we created a custom layer for the input where we are able to insert the seed for the generator and a real image. We pass the real image around the RBM. (Please note that you need a custom Sigmoid Activation Layer for RBMs). Afterwards we use custom layers in the CNN to identify both images simultaneously with the same weights as from the pretraining. You can just copy the Matlab Layers for that and modify them a bit. Finally we created an output layer for this custom CNN. There we track the differences between both classification probabilities. Note that you have to think about a correct Loss Function there. We train the whole model by inserting real images with different random seeds and a final result of 0 difference between both classifications.

Just a note on "easyness". We only do that because we need MATLAB Code at the end to export them on our embedded systems. If you just want to discover what GANs can do, you should for now stick to TensorFlow as its much easier. They have a good example on their website. But maybe Mathworks add native support for GANs in a future release?!

请先登录，再进行评论。