Closed RHammond2 closed 5 years ago
Hello @RHammond2 ,
I'm unable to replicate under CentOS7, Python 3.6.3 and joblib=0.11.
In [5]: from pyGPGO.GPGO import GPGO
...: gpgo = GPGO(gp, acq, evaluateModel, params, n_jobs=4)
...: gpgo.run(max_iter = 5)
...:
Evaluation Proposed point Current eval. Best eval.
init [ 1.39850819 -1.17881649]. 0.8493761140819965 0.8493761140819965
init [ 3.7303667 4.7255962]. 0.5148544266191325 0.8493761140819965
init [-2.35468526 2.4390623 ]. 0.6149732620320855 0.8493761140819965
1 [ 0.69315004 -0.49900347]. 0.849227569816 0.849376114082
2 [ 1.6262495 -0.23700775]. 0.884284016637 0.884284016637
3 [ 0.8895309 0.7722795]. 0.889483065954 0.889483065954
4 [-0.26714709 0.84576647]. 0.884432560903 0.889483065954
5 [ 0.01668053 1.81505441]. 0.834373143197 0.889483065954
Maybe this is related. Which joblib version are you using?
Hello again @RHammond2,
Was able to replicate and can confirm this is caused by the latest joblib
version. Use 0.11 in the meantime.
I will correct dependencies in the repo.
Hello @hawk31
I was able to run the example successfully when reverting to version 0.11.
Thanks so much! Rob
Hello,
I am testing a number of Bayesian Optimization packages out for setting up a hyperparameter search, and had quite liked the setup of pyGPGO, but am running into an issue with parallelizing the code. I was using the tutorial from https://github.com/hawk31/pyGPGO/blob/master/tutorials/mlopt.ipynb as a reference.
When modifying
gpgo = GPGO(gp, acq, evaluateModel, params)
to begpgo = GPGO(gp, acq, evaluateModel, params, n_jobs=4)
with the same example. I get a BrokenProcessPool error with both your sample code and my own similar example. The output for modifying the code as I described is as follows.I'm not really sure if the underlying issue is with joblib.Parallel or with pyGPGO, any help would be greatly appreciated!
For reference I am running on MacOS with an Anaconda distribution of Python 3.6.
Thank you, Rob