joelouismarino / amortized-variational-filtering Goto Github PK

Hey Joe,

I'm looking through your code trying to understand how to run the AVF algorithm with a convolutional model but am a bit confused about setting that up. It seems that by default you run a VRNN?

I notice that in train_config, inference_iterations=1, and step_samples=1. In practice, do you use 1? Reading your paper, I'm having a hard time figuring out if you run through all of your data until the current time-step for each inference step. My suspicion is that the answer is yes in the general variational filtering case but no in the "amortized variational filtering" case, where you only use the current time-step?

By the way, really neat paper.

Cheers

Hi there,

Thanks for the useful repo. I was trying to clone the repo and run by your experimental data. However, I am getting an error of Data path not found. I tried different dataset you have provided in the code such as, Nottingham but none of the dataset is downloaded to train. I am attaching the error I am getting as well. Could you please let me know how to fix it? Thanks in advance