netneurolab / conn2res Goto Github PK
View Code? Open in Web Editor NEWA reservoir computing toolbox for neuroscientists
Home Page: https://github.com/netneurolab/conn2res
License: BSD 3-Clause "New" or "Revised" License
A reservoir computing toolbox for neuroscientists
Home Page: https://github.com/netneurolab/conn2res
License: BSD 3-Clause "New" or "Revised" License
.
from bct import get_components, distance_bin, reference
Hi everyone, thankyou so much for this available tool, I have a problem with the bct library to import get_components, distance_bin, reference, how can I fix it, because apparently bct is not found as a file in the repository, so I looked for it in pypi and I understand that it is the brain connectivity toolboox for python and it appears as bctpy because bct is a version for matlab, then I want to know if the errors to import everything are because they are called disitnto in this case and then get_components, distance_bin, reference would change. I hope you can help me and thank you in advance.
Hello!
I have started exploring this package and ran into a few installation requirement errors. I ended up resolving them, but thought it might be useful to share some of the things.
In your requirements.txt file, it notes that gym==0.21.0 is required. However, there is currently a known bug in installing that version (Gym Issue 3176). I ran into this same issue when trying to install conn2res using a new virtual environment (using venv and python 3.10.9).
This was resolved by ensuring setuptools==66 (pip install --upgrade setuptools==66
) (Gym Issue 3200) and wheel==0.38.4 (pip install wheel==0.38.4
)(Gym Issue 3202 and Gym Issue 3221) before installing the required packages as noted in the conn2res installation instructions (pip install . -r requirements.txt
).
Hi, where can we find image file and its index file of the Desikan Killiany atlas which was used to parcellated human connectome and included 1015 brain regions according the statement in the tutorial.py?
Hello,
I am currently working with the conn2res tool and I have some questions regarding its usage.
Firstly, I noticed that the tasks used in the dataset are cognitive tasks extracted from another tool called NeuroGym. I am interested in using my own dataset instead. Could you provide some guidance on the nature of the dataset that conn2res expects? Specifically, what format should my dataset be in, and what changes would I need to make in the code to ensure it works with my custom dataset?
Secondly, I understand that conn2res uses a connectivity matrix from an existing database. However, I would like to use my own connectivity matrix. Could you provide some instructions or guidelines on how to incorporate my own connectivity matrix into the conn2res workflow?
Lastly, I am having some difficulty understanding the structure of the codebase. Could you clarify which is the main code file? Is it the one labeled as 'tutorial' or is it one of the files in the 'examples' directory?
Any help or guidance would be greatly appreciated. Thank you in advance for your time and assistance.
Hi,
When I ran the tutorial.py with 'PerceptualDecisionMaking', the output reservoir state is quite starnge that it seems the value of each node doesn't change.
Meanwhile, the performance of 'balanced_accuracy_score' also had a difference with paper, which had a drop of nearly more than 10%.
I just changed the 'adjusted' in 'balanced_accuracy_score' to 'True' and changed the file path of 'connectivity.npy', 'cortical.npy' and 'rsn_mapping.npy' to 'examples\data\human', which were downloaded with the guidance of closed issues 'Where can I get the three files connectivity.npy, cortical.npy, rsn_mapping.npy?'
Hi @estefanysuarez,
Thank you for the codes in this repository.
Can I know where can I get the .npy files used in the examples, i.e: connectivity.npy, cortical.npy, rsn_mapping.npy?
Where can I get the three files connectivity.npy, cortical.npy, rsn_mapping.npy?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.