Feras Saad
Feras Saad
Hi @bookRa. Thanks for your interest in Gen. Are you experiencing issues or errors with running the software? We are using Github tickets to track those issues.
Code referred to as "here": https://github.com/probcomp/crosscat/commit/950787f1a2e812763d7447469d3827e6ce1495f4#diff-1c75fbbdfb035344508f37d7dce685b5R74
Hi there, There are a few ways to access the posterior row and column partitions. The easiest way is to use the `X_L` and `X_D` dictionaries that summarize a particular...
> Length of the X_L and X_D equal the number of chains but the chains are not drawn from the same models because the hyper-parameters are different, correct? How do...
> Do you see s and r and nu are different for chain 0 and chain 1 ? Are those samples from distribution on the top of the `column_hypers`? Yes,...
> it takes about 10hr for 200 transitions My sense is that you might be using a dataset size which is larger than the target of this software --- how...
@kayhan-batmanghelich I'm not sure immediately why MultiprocessingEngine is not respecting `max_time`, please open a separate ticket so we can track the issue, and let me know if it is OK...
The same should be true for weighting the estimates of `logpdf` by probability of the `conditions` under each `State`. For reference, `gpmcc.Engine` implements the weighting as post-processing steps on the...
Sounds right, although with the `agg` backend `show()` has no blocking effect as far as I know.
Hi @lastrk, have you tried the workaround from https://github.com/probcomp/gen-quickstart/issues/77