Commit b2e2a664 authored by lucas_miranda's avatar lucas_miranda
Browse files

Implemented VAEP hypermodel in hypermodels.py

parent dcd20ea4
......@@ -530,9 +530,8 @@ class SEQ_2_SEQ_VAEP:
class SEQ_2_SEQ_MMVAE:
pass
# TODO:
# - cleaner implementation of reparameterization trick (sampling on input, outside the main graph)
# - Add learning rate scheduler callback
# - KL / MMD warmup (Ladder Variational Autoencoders)
# - Gaussian Mixture + Categorical priors -> Deep Clustering
# - free bits paper
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment