Incognition logo
Home
Learn
Practice
Leaderboard
0
VisualizationsGenerative & Applied Deep Learning

VAE Sampling

Switch from rebuilding to generating. Drop the encoder, feed the decoder a random code, and a VAE becomes a model that makes new outputs.

encoder
input → code
→
code
from the input
→
decoder
output

To generate, you drop the encoder entirely. The decoder alone, fed a random code, is the generative model.

Customize