Closed robinsloan closed 6 years ago
Thanks! I know this error and I'm sure I fixed it somewhere, but apparently not in the master branch. I'm not great at version control (yet), sorry!
You are absolutely right, the input of mu_law_expansion
should be between -1. and 1., the values are actually scaled in the code but then never used. So the fix is exactly one letter in wavelet_model.py
line 299:
From
o = (x / self.classes) * 2. - 1
generated = np.append(generated, x)
to
o = (x / self.classes) * 2. - 1
generated = np.append(generated, o)
Now the fast generation should work fine.
Ah that's terrific! Thanks, Vincent.
Hi there! I'm running into an error and I'm not sure if it's particular to my setup or something deeper.
When I run
generate_script.py
, everything seems to go fine until I get to the finalmu_law_expansion
step, at which point I get firstand then a fatal
It's the
np.exp
that blows up into enormous numbers.The
data
coming into themu_law_expansion
function is all in the range 0-255…and then after
np.abs(data) * np.log(mu +1)
it looks like this…which
np.exp
blows up:Looking at the code, I have some suspicions about what might be happening, but before I get too far into fiddling with it, I want to confirm that
generate_script.py
works on your end.Thanks for sharing this codebase and the accompanying documentation—it's super impressive.