In the GAN example of the documentation, did we update D several times before updating G?

Question

SC 2019-11-6

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/489473-in-the-gan-example-of-the-documentation-did-we-update-d-several-times-before-updating-g

评论： SC 2020-4-11

Hi,

In the following example of GAN for the deep learning toolbox ( https://www.mathworks.com/help/deeplearning/examples/train-generative-adversarial-network.html ), did we update Discriminator D several times before updating the generator G?

As per the GAN algorithm (say the original paper of Goodfellow 2014), we would update D k-times before updating G.

But I don't think the value of k is mentioned in the example. It looks like D and G are updated together in every loops.

The relevant codes:

        % Update the discriminator network parameters.
        [dlnetDiscriminator.Learnables,trailingAvgDiscriminator,trailingAvgSqDiscriminator] = ...
            adamupdate(dlnetDiscriminator.Learnables, gradientsDiscriminator, ...
            trailingAvgDiscriminator, trailingAvgSqDiscriminator, iteration, ...
            learnRateDiscriminator, gradientDecayFactor, squaredGradientDecayFactor);
        
        % Update the generator network parameters.
        [dlnetGenerator.Learnables,trailingAvgGenerator,trailingAvgSqGenerator] = ...
            adamupdate(dlnetGenerator.Learnables, gradientsGenerator, ...
            trailingAvgGenerator, trailingAvgSqGenerator, iteration, ...
            learnRateGenerator, gradientDecayFactor, squaredGradientDecayFactor);

Thanks!

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。

请先登录，再回答此问题。

Answer 1

Sourav Bairagya 2020-1-10

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/489473-in-the-gan-example-of-the-documentation-did-we-update-d-several-times-before-updating-g#answer_409539

GANs can be trained in many fashions. Here, discriminator, D is updated once before updating generator, G. Hence, first, discriminator, D is updated and then the generator, G is updated in every iteration.

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

SC 2020-4-11

So, to follow the original training fashion (i.e. update (D k-times and G 1-time) n times), we need to add one more inner loop to achieve that?

请先登录，再进行评论。

In the GAN example of the documentation, did we update D several times before updating G?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

回答（1 个）

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

另请参阅

类别

标签

产品

版本

Community Treasure Hunt

In the GAN example of the documentation, did we update D several times before updating G?

0 个评论 显示 -2更早的评论隐藏 -2更早的评论

回答（1 个）

1 个评论 显示 -1更早的评论隐藏 -1更早的评论

另请参阅

类别

标签

产品

版本

Community Treasure Hunt

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

1 个评论
显示 -1更早的评论隐藏 -1更早的评论