search

HSinger04 / VOGUE-Reimplementation

A reimplementation of the VOGUE paper for the IANNwTF WS20/21 course at the University of Osnabrück
1 stars 0 forks source link

Learn try-on #11

Closed HSinger04 closed 3 years ago

HSinger04 commented 3 years ago
  1. Have a 2-layer MLP map from w to sigma. Only a single one is needed, as w_latent stays the same for all styles / resolutions.
  2. Have p as a trainable vector, q = sigmoid(p) and Q = DiagonalMatrix(q) for each style.
  3. Calculate losses and optimize.
HSinger04 commented 3 years ago

Check if restore works

HSinger04 commented 3 years ago

Create appropriate function in generator