Question about the Matlab Wasserstein GAN example
2 views (last 30 days)
Show older comments
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 Comments
Answers (1)
Malay Agarwal
on 22 May 2024
Edited: Malay Agarwal
on 22 May 2024
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!
0 Comments
See Also
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!