search

slim1017 / VaDE

Python code for paper - Variational Deep Embedding : A Generative Approach to Clustering
284 stars 95 forks source link

same class probablities #8

Closed michelleowen closed 6 years ago

michelleowen commented 6 years ago

Hi, I translated your code to keras with tensorflow backend and run VaDE model on a simulated GMM data set. However, I always get same probabilities for all classes. For example, assuming I have four classes, then I always get [0.25, 0.25, 0.25, 0.25] from gamma_output. Is it a bug in your code?

michelleowen commented 6 years ago

I solved the problem with pre-training.