New answers tagged

1 vote

What is the meaning of $p_{\text {data }}(y)$ in the CycleGAN?

I interpret $p_{data}(y)$ as the empirical probability of seeing an image $y$ in the training data. For example, in a typical training run, each training image is shown to the network the same number ...
user avatar
2 votes
Accepted

PPO: policy loss becomes nan

You might want to try substituting the exponentiation with a piecewise-defined function that uses a numerical approximation that is more numerically stable for low values of the exponent, such as ...
user avatar
  • 66

Top 50 recent answers are included