Azzera filtri
Azzera filtri

Matlab does not currently support Generative Adversarial Neural Networks

4 visualizzazioni (ultimi 30 giorni)
I searched a lot to see if Matlab supports GAN but unfortunately it does not. I just found deconvolution layer. does anybody know how I can use that for designing a GAN. I am gonna integrate a GAN block within a DAG network and I am not sure if it is possible. I found also another open source lib 'MatConvNet'. is is possible to use it within DAG? Thank you very much I hope it is not wasting time working on deep learning with Matlab.
web address of matconvnet:
web address of DAG :
  9 Commenti
Walter Roberson
Walter Roberson il 18 Lug 2018
ashkan dashtban comments to me:
Exactly and we hopefuly expect it to be available in near future!

Accedi per commentare.

Risposta accettata

Yui Chun Leung
Yui Chun Leung il 4 Apr 2020
I implemented different types of GANs with Matlab, including DCGAN, cGAN, CycleGAN and more.
You can find my files in FileExchange or Github (
  2 Commenti
Atallah Baydoun
Atallah Baydoun il 4 Apr 2020
Thanks Yui,
I will take a look and see if I can adapt pix2pix to read .mat files instead of jpg and png.
Yui Chun Leung
Yui Chun Leung il 4 Apr 2020
Here is the code used for transforming jpg and png to mat.
But if you want a dataloader like in pytorch, you have to rewrite the for loop and put the jpg loader in it.

Accedi per commentare.

Più risposte (6)

Shounak Mitra
Shounak Mitra il 6 Giu 2019
In the next release, we're going to provide some flexbilities to design advanced networks such as GANs, Siamese Networks etc. Hang on :)
  2 Commenti
ashkan dashtban
ashkan dashtban il 8 Giu 2019
  • we hope Matlab will provide more flexibility in new release to enable us to build hybrid dynamic networks by combining different components of neural networks. Also, If we could add customized metric funciotions, say precision instead of accuracy.! such capability makes MatLab much more powerfull and handy than python!

Accedi per commentare.

KH TOHIDUL ISLAM il 19 Set 2019
It is avilabel now, please check this out. Train Generative Adversarial Network (GAN)

Atallah Baydoun
Atallah Baydoun il 7 Giu 2019
Thanks Mitra for the info.
But when is the next release going to be ?
  5 Commenti
Shounak Mitra
Shounak Mitra il 10 Giu 2019
Let's think of it in terms of what important features you need to create GANs - autodifferentiation, custom training loops, and may be custom layers too (if you're curious!). All those things are planned to be supported. And of course, the deep learning layer support will be there.
Atallah Baydoun
Atallah Baydoun il 10 Giu 2019
Hopefully then Matlab will include an example on GAN generation also.

Accedi per commentare.

Wonho Song
Wonho Song il 28 Mag 2020
Thanks for these nice codes.
Normally we do have checkpoints and model to save to a file.
  1. I want to know how to save the model.Is it good to save the paramGen and paramDis? and if it is then how to use as a model.
  2. 2 .And also I want to know how to test pix2pix.m to a specific image file.Thanks in advance.
  1 Commento
Atallah Baydoun
Atallah Baydoun il 28 Mag 2020
Hey Wonho,
I ended up by using pix2pix from this link.
It automatically saves the model. You can se from the link that many troubleshooting issues were resolved.

Accedi per commentare.

David Willingham
David Willingham il 27 Ago 2020
Since R2019b, MATLAB has supported the implementation of GAN's.
More information on this can be found here.
David Willingham
Deep Learning Product Manager, MathWorks

anbarasi l
anbarasi l il 30 Nov 2022
MATLAB has supported the implementation of CGAN.
You can find information on this in the below link
Train Conditional Generative Adversarial Network (CGAN)

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by