Question about the Matlab Wasserstein GAN example

Question

Mohammed 2024-5-21

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2121121-question-about-the-matlab-wasserstein-gan-example

编辑： Malay Agarwal 2024-5-22

The original Wasserstein gan paper suggest removing the Critic's last dense layer activation function(sigmoid) such that the output value is not limited to fake or real. The posted example still uses sigmoid layer, am I right?

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

Malay Agarwal 2024-5-22

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2121121-question-about-the-matlab-wasserstein-gan-example#answer_1461571

编辑：Malay Agarwal 2024-5-22

在 MATLAB Online 中打开

Hi @Mohammed,

The diagram of the Discriminator model in the example (https://www.mathworks.com/help/deeplearning/ug/trainwasserstein-gan-with-gradient-penalty-wgan-gp.html) shows that the model does have a “sigmoid” layer at the end:

This can also be confirmed by looking at how the Discriminator model is defined:

layersD = [
    imageInputLayer(inputSize,Normalization="none")
    convolution2dLayer(filterSize,numFilters,Stride=2,Padding="same")
    leakyReluLayer(scale)
    convolution2dLayer(filterSize,2*numFilters,Stride=2,Padding="same")
    layerNormalizationLayer
    leakyReluLayer(scale)
    convolution2dLayer(filterSize,4*numFilters,Stride=2,Padding="same")
    layerNormalizationLayer
    leakyReluLayer(scale)
    convolution2dLayer(filterSize,8*numFilters,Stride=2,Padding="same")
    layerNormalizationLayer
    leakyReluLayer(scale)
    convolution2dLayer(4,1)
    sigmoidLayer]; % Notice the sigmoid layer at the end