Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Python module version? What are the versions of each module that you used? #38

Closed
Ibrainscn opened this issue Mar 7, 2019 · 6 comments

Comments

@Ibrainscn
Copy link

File "C:\Users\myUser\AppData\Local\Continuum\anaconda2\lib\site-packages\lasagne_init_.py", line 17, in
from . import nonlinearities

ImportError: cannot import name nonlinearities

I am wonder are there any other specific requirements to run your code(e.g. specific modules version, python environment)? Can you kindly write a demo to show how to run your code? I really want to try out your method on my EEG data. Really appreciate!

@pbashivan
Copy link
Owner

From the looks of it the error is caused by lasagne and probably due to differences in versions.

The code was tested with the following:

python 2.7 
theano 0.8 
lasagne 0.2.dev1 
CUDA 8.0

I updated the setup file to included these.

@Ibrainscn
Copy link
Author

Thanks a lot! I tried with exactly the above version.
It can run Loading data...
Generating images...
Interpolating 2594/2670Interpolating 2611/2670Interpolating 2630/2670Interpolating 2648/2670Interpolating 2665/2670

Training the CNN Model...
fold 1/13
Traceback (most recent call last):
And then give me the following error:

File "C:\Users\myUser\AppData\Local\Continuum\anaconda2\lib\site-packages\theano\tensor\type.py", line 47, in init
# broadcastable is immutable, and all elements are either

AttributeError: 'TheanoConfigParser' object has no attribute 'floatX'

@pbashivan
Copy link
Owner

I see. It's weird that having the same package versions you are still getting this error. Try setting this ENV variable when running the script.

THEANO_FLAGS='floatX=float32' python <script_name.py>

@Ibrainscn
Copy link
Author

Finally, it works now! Thanks so much!!

For the topology-preserving projections of electrode locations (3D-->2D), I am just wondering the input for the following function is in 3D Cartesian Coordinates (x, y, z), right? That means your sample data Neuroscan_locs_orig.mat is a Neuroscan 64 EEG channels system in Cartesian Coordinates (x, y, z), right?

def azim_proj(position):
"""
Computes the Azimuthal Equidistant Projection of input point in 3D Cartesian Coordinates.

If I change the input "position" by using let's say Biosemi (another EEG system) 128 channel location files in Cartesian Coordinates. It should also work, right?

Thanks for your help and clarification.

@pbashivan
Copy link
Owner

Yes, the inputs are in Cartesian coordinates. It should work if you replace the channel coordinates with another one of your choice (in Cartesian coordinates).

@Ibrainscn
Copy link
Author

I see. Thanks so much. Really appreciate your help.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants