I have an error when running gp_minimize

[kkt922]

Hi.
Thank you for making this very useful tutorial.
I have an error when running gp_minimize (19_Hyper-Parameters.ipynb).
When I run the fitness function (when I test it), the training works well.

That is,

fitness(x = default_parameters)

works well.

But
search_result = gp_minimize (func = fitness, dimensions = dimensions,  acq_func = 'EI', n_calls = 40, x0 = default_parameters)

When I put the fitness function in gp_minimize like above,

Process finished with exit code 139 (interrupted by signal 11: SIGSEGV)

This error occurs.
It seems to be a memory allocation problem, and I can not confirm the exact error.
All tutorials that use gp_minimize in the skopt documentation works well.
When using the fitness function with the gp_minimize function, is there a certain conflict that may occur?

The system of my machine is Linux Mint 18.1 Serena.
The version of python is 3.5.2.
The libraries installed are the following:

Thank you.!

[kkt922]

In stack overflow, Someone said this error equates to a read or write of a memory address that's not mapped in the process. This is either a bug in the interpreter or in an extension module being used (and the latter is the most common cause). The following is the stack overflow URL.

https://stackoverflow.com/questions/49414841/python-process-finished-with-exit-code-139-interrupted-by-signal-11-sigsegv

[kkt922]

I finally implemented! This error is due to tensorflow version.