Poor performance because of bad initialization

RuiShu / vae-clustering

Unsupervised clustering with (Gaussian mixture) VAEs

MIT License

294 stars 57 forks source link

Poor performance because of bad initialization #10

Open JerryPeng21cuhk opened 5 years ago

JerryPeng21cuhk commented 5 years ago

This is for those are trying this vae-clustering repo which depends the tensorbayes library. I got very poor performance because of the bad initialization scheme in file: tensorbayes/layers/simple.py line 31.

Pls replace variance_scaling_initializer with xavier_initializier. Also, don't forget to import it: from tensorflow.contrib.layers import xavier_initializer

After this, the performance is boosted. Hope this help later followers~

JerryPeng21cuhk commented 5 years ago

I implemented a pytorch version and found the clustering accuracy(Or purity ?) can be boosted to 95% after 738 epoches...