bits_per_dim
hjzhang-forward opened this issue · comments
HI! Thank you very much for your code. I have a question about the function bits_per_dim: Why do you want to add an 8?
def bits_per_dim(logpx, inputs):
return -logpx / float(np.log(2.) * np.prod(inputs.shape[1:])) + 8.
Sincerely look forward to your reply!
Add noise ~ U(0, 1/256), log 256 = 8