brain-research / l2hmc Goto Github PK

Hi,

Im trying to replicate the Mixture of Gaussians results from your paper but cant seem to get it to mix between the two modes. I've tried with two gaussians at (-10, 0) and (10, 0) each of which have diagonal covariances with ones down the diagonal. I've also tried the same two gaussians from the paper.

I'm currently using the same network structure as is in your IPython notebook and am training for 5000 iterations with 200 samples per iteration.

I've tried adding a temperature and annealing that as well but that hasn't seemed to help.

It also seems to be running extremely slowly, taking 30 minutes to train on cpu. Is this normal or am I doing something wrong?

I've attached my code and images of the samples drawn after training. As you can see the samples only explore one of the two modes.

many thanks!

mogexperiments.py.zip

Hi,

Really interesting research! Unfortunately, when I try to run the notebook, I run into a few issues:

• Unexpected indent in the ESS function in func_utils.py (easily fixed)
• No module named config when it tries to import config in sampler.py (also easily fixed)
• Finally: ImportError: No module named notebook_utils (did you forget to include the file?)

Just thought I'd make you aware -- or did I miss some steps?

All the best,
Martin

I can't run mnist_vae.py somehow. I am using Tensorflow 1.1.0. Which version are you using ?