Open 51N84D opened 3 years ago
Current approach just adds bit-conditioning to the latent vector, and determines which (simulated) ground truth mask to compute losses with.
Is that up to date? What's keeping us from merging?
Alright it's finally ready to review. Try running it before approving, just to make sure nothing is broken...
How about this PR, is it ready @51N84D ?
Current approach just adds bit-conditioning to the latent vector, and determines which (simulated) ground truth mask to compute losses with.