Git Product home page Git Product logo

dynaphos's Introduction

About the project

A fully differentiable and biologically plausible simulation of cortical prosthetic vision, which can be used for end-to-end optimization.

Installation

pip install dynaphos

Getting Started

  • Download the default configuration file (config/params.yaml) from our repository and adjust according to needs.
  • Run the test suite.
  • See the examples directory for simple use cases.

Citation

van der Grinten, M., van Steveninck, J. D. R., Lozano, A., Pijnacker, L., Rueckauer, B., Roelfsema, P., Marcel van Gerven, Richard van Wezel, Umut Güçlü & Güçlütürk, Y. (2024). Towards biologically plausible phosphene simulation for the differentiable optimization of visual cortical prostheses. eLife, 13, e85812. https://doi.org/10.7554/eLife.85812.

Experiments

For the end-to-end optimization experiments in our publication see this repository. The code for the experiments described in our publication (using this simulator) can be found in this repository. All other code that was used in our publication can be made available on request.

Contact

Feel free to submit an issue, we're happy to help.

dynaphos's People

Contributors

deruyter92 avatar pcklink avatar mvdgrinten avatar

Stargazers

avatar Yasuo Kabe avatar avatar Bodo Rueckauer avatar Zuowen Wang avatar avatar Jason avatar Aton Kamanda avatar

Watchers

Umut Güçlü avatar Peter Meijer avatar Bodo Rueckauer avatar avatar

Forkers

pcklink gbouwman escialom tanyapak antonio-lozano

dynaphos's Issues

tests do not pass

Hi,

A number of tests fail out of the box. I am testing the master branch on git. Is this a known issue or am I doing something wrong?

joeyo:~/src/dynaphos/test> pytest
===================================================== test session starts ======================================================
platform darwin -- Python 3.10.13, pytest-7.4.3, pluggy-1.3.0
rootdir: /Users/joeyo/src/dynaphos
plugins: typeguard-3.0.2, nengo-3.2.0, anyio-3.7.1
collected 18 items

test_all.py ..F........FEEEFF.                                                                                           [100%]       
[... snip ...]                                                                             
=================================================== short test summary info ====================================================
FAILED test_all.py::TestCorticalModels::test_get_phosphene_map_from_electrodes - assert False
FAILED test_all.py::TestSimulator::test_generate_phosphene_maps - assert False
FAILED test_all.py::TestFunctional::test_image - AttributeError: 'GaussianSimulator' object has no attribute 'stimulus_scale'
FAILED test_all.py::TestFunctional::test_brightness - TypeError: only integer tensors of a single element can be converted to an index
ERROR test_all.py::TestSimulator::test_update - AttributeError: 'GaussianSimulator' object has no attribute 'stimulus_scale'
ERROR test_all.py::TestSimulator::test_gaussian_activation - AttributeError: 'GaussianSimulator' object has no attribute 'stimulus_scale'
ERROR test_all.py::TestSimulator::test_call - AttributeError: 'GaussianSimulator' object has no attribute 'stimulus_scale'
====================================== 4 failed, 11 passed, 7 warnings, 3 errors in 5.47s ======================================

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.