Clear Filters
Clear Filters

Question about the Matlab Wasserstein GAN example

35 views (last 30 days)
Mohammed
Mohammed on 21 May 2024 at 14:44
Edited: Malay Agarwal on 22 May 2024 at 9:20
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?

Answers (1)

Malay Agarwal
Malay Agarwal on 22 May 2024 at 9:20
Edited: Malay Agarwal on 22 May 2024 at 9:20
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
Hope this helps!

Categories

Find more on Statistics and Machine Learning Toolbox in Help Center and File Exchange

Community Treasure Hunt

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

Start Hunting!