Attention: The EBRAINS drive will be unavailable for most of the weekend starting the 25th October. Although the Lab is availble while the Drive is down, files that are stored in the Drive will not be loaded and you will be unable to save documents directly on the Lab.


Wiki source code of AngoraPy

Last modified by weidler on 2023/05/12 13:23
Hide last authors
weidler 7.1 1 **AngoraPy** is an open source modeling library for [[goal-oriented research>>https://pubmed.ncbi.nlm.nih.gov/26906502/]] in **neuroscience**. It provides a simple interface to train deep neural network models of the human brain on various, customizable, sensorimotor tasks, using reinforcement learning. It thereby empowers goal-driven modeling to surpass the sensory domain and enter that of sensori//motor// control, closing the perception-action loop.
2
3 **AngoraPy** is designed to require no deeper understanding of reinforcement learning. It employs state-of-the-art machine learning techniques, optimized for distributed computation scaling from local workstations to high-performance computing clusters. We aim to hide as much of this under the hood of an intuitive, high-level API but preserve the option for customizing most aspects of the pipeline.
4
5 This library is developed as part of the [[Human Brain Project>>https://www.humanbrainproject.eu/]] at [[CCN Maastricht>>https://www.ccnmaastricht.com/]]. It is an effort to build software by neuroscientists, for neuroscientists. If you have suggestions, requests or questions, feel free to [[open an issue>>https://github.com/ccnmaastricht/angorapy/issues/new/choose]].
6
7 === Installation ===
8
9 AngoraPy is available on PyPI.
10
11 {{code language="bash"}}
12 pip install angorapy
13 {{/code}}
14
15 ==== From source ====
16
17 You can access the source code on [[Github>>https://github.com/ccnmaastricht/angorapy]]. After downloading, you may install it by pip.
18
19 {{code language="bash"}}
20 pip install -e .
21 {{/code}}
22
23 === Docker ===
24
25 Alternatively, you can install AngoraPy and all its dependencies in a docker container using the Dockerfile provided in this repository (/docker/Dockerfile). To this end, download the repository and build the docker image from the /docker directory:
26
27 {{code}}
28 sudo docker build -t angorapy:master https://github.com/ccnmaastricht/angorapy.git#master -f - < Dockerfile
29 {{/code}}
30
31 To install different versions, replace #master in the source by the tag/branch of the respective version you want to install.
32
33 === **More Information** ===
34
35 For more information consult our [[Github>>https://github.com/ccnmaastricht/angorapy]] page.
Public

AngoraPy