Closed Xingtao closed 4 years ago
The VICE discriminator is given by \frac{p}{p + pi}. So, if I pass \log_p and \log_pi to the softmax for 1 and 0 labels accordingly, I get \frac{p}{p + pi} as the probability for the datapoint belonging to label 1 (softmax(x1, x2)[x1] = exp(x1) \ exp(x1) + exp(x2)). Please let me know if this makes sense.
Thanks for your explanation
Hi, I am confused with labels in vice classifer training.
Observations consist with
and the labels are assigned with
and arguments of 'softmax_cross_entropy' are
so, the negative sample has output 'log_pi' with label 1, the positive sample has output 'log_pi' with label 0; the negative sample has classifer 'log_p' with label 0, the positive sample has classifer 'log_p' with label 1;
Why 'log_pi' for negative sample is labelled 1?