Open JacobGlennAyers opened 1 year ago
Train a basic non-convex variational autoencoder. Once it is trained, remove the basic decoder, keep the encoder, and retrain the decoder using a vNN
We could also try this both ways. Train a basic non-convex VAE, remove the encoder, keep the decoder, and then retrain the encoder using a vNN
If this works, we could then generate FID and IS scores.
Train a basic non-convex variational autoencoder. Once it is trained, remove the basic decoder, keep the encoder, and retrain the decoder using a vNN