Supervised concrete autoencoder

[annalauralerede]

Hi,

I am looking through your code and I see that for the supersived implementation you use the MSE loss instead of the cross-entropy loss like you mentioned in the paper... There is no condition to use the cross-entropy loss when supervised and it always use the mse loss. Is it a mistake or is it done on purpose?

[mfbalin]

One is free to use any kind of loss function for supervised training. It might be an oversight in the implementation.