search

wujian16 / Cornell-MOE

A Python library for the state-of-the-art Bayesian optimization algorithms, with the core implemented in C++.
Other
261 stars 64 forks source link

errors encountered when running the examples #90

Closed zullu14 closed 3 years ago

zullu14 commented 4 years ago

I have followed the installation instructions strictly, tried both with python 2 and python 3, but when it completes, I get the following error message when running the example (main.py) from the 'examples' folder:

Traceback (most recent call last): File "main.py", line 113, in cpp_gp_loglikelihood.train() File "/home/USER/ENV_NAME/lib/python2.7/site-packages/moe/optimal_learning/python/cpp_wrappers/log_likelihood_mcmc.py", line 207, in train rstate0=self.rng) File "/home/USER/ENV_NAME/lib/python2.7/site-packages/emcee/ensemble.py", line 384, in run_mcmc for results in self.sample(initial_state, iterations=nsteps, **kwargs): File "/home/USER/ENV_NAME/lib/python2.7/site-packages/emcee/ensemble.py", line 254, in sample "Initial state has a large condition number. " ValueError: Initial state has a large condition number. Make sure that your walkers are linearly independent for the best performance

I have tried several inputs with different objective functions, like: python main.py Branin KG 4 1 python main.py Hartmann6 KG 4 1 HeSBO 3 etc.

Has anybody encountered a similar problem?

git163 commented 4 years ago

I have a similar problem too , any ideas on how to solve it?

hermitdemschoenenleben commented 4 years ago

I have the same problem and didn't find a way to solve it

zullu14 commented 3 years ago

Apparently I have found a solution - one needs to install the older version of emcee package (https://emcee.readthedocs.io/en/stable/). I installed ver. 2.2.0 and now it is working (at least the examples are - now I will try to dig into this package).