I have taken the following piece of code from the OpenAI code of GitHub from the following link:


def discretized_logistic(mean, logscale, binsize=1 / 256.0, sample=None):
      scale = tf.exp(logscale)
      sample = (tf.floor(sample / binsize) * binsize - mean) / scale
      logp = tf.log(tf.sigmoid(sample + binsize / scale) - tf.sigmoid(sample) + 1e-7)
      return tf.reduce_sum(logp, [1, 2, 3])

I am unable to understand mathematical intuition or explanation of the above code. Even, I am unable to find the reference for this. Could you please explain?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.