xchoo / spaun2.0 Goto Github PK
View Code? Open in Web Editor NEWSpaun (nengo 2.0 version)
Spaun (nengo 2.0 version)
Spaun2.0 ======== Running the Spaun [1]_ model in Nengo 2.0. .. [1] Chris Eliasmith, Terrence C. Stewart, Xuan Choo, Trevor Bekolay, Travis DeWolf, Yichuan Tang, and Daniel Rasmussen. A large-scale model of the functioning brain. Science, 338:1202-1205, 2012. URL: http://nengo.ca/publications/spaunsciencepaper doi:10.1126/science.1225266. Running with Nengo OCL ---------------------- If you want to run with ``nengo_ocl``: python run_spaun.py -d 512 --ocl --ocl_platform=1 --ocl_device=3 where: - the -d flag sets the dimensionality of spaun, - the --ocl flag tells the run script to use ocl - the --ocl_platform flag tells it what OCL platform to use - the --ocl_device flag tells it what ocl device to use on said platform (this flag is optional, it's used in the context creation for pyopencl) To determine the ``ocl_platform`` and ``ocl_device`` of the device you want to use, see ``pyopencl.create_some_context()``. To enable OCL profiling, find where the ``nengo_ocl.Simulator`` is created in ``run_spaun.py``, and uncomment the version that has provifiling enabled. Also uncomment the line to print profiling.
Hi,
I'm successfully run this code and get the result with string.
I've read the code and found the input is the def_str and the out_put will display on my console.
Could I implement the result that the input is provided by 'eye' and the output can be written by 'arm' like the video on Youtube? If so, how can I configure it and what hardware device should I use?
Thank you!
nengo/nengo@e6a8304 added an n_neurons
property to Networks, which conflicts with some places in Spaun where data was being stored in a self.n_neurons
attribute (e.g.,
spaun2.0/_spaun/_networks/workingmemory.py
Line 167 in 9bb87ad
I don't mean to complain, but having all the data files in the repository means that it's huge. Partly because they're just large, and partly because when they're changed, git stores the old version too. These files should really be on figshare (I've got code for downloading the MNIST data and the augmented Spaun symbols, see here).
Hello, how much video memory is needed to run the full model using GPU?
Hello,
I have just installed Nengo (https://www.nengo.ai/) on a Windows 10 system that I have to experiment with and try some things, but would like to see if it is possible to load up Spaun 2.0 in Nengo so that I can look at the neural design and layout of the whole system.
Of course, I do not really expect to be able to run the full simulation from Nengo since I would imagine that it would take a considerable amount of computing resources and time to make it work, but to be able to explore the topology would be interesting.
Any help would be greatly appreciated.
Thanks in advance.
Excellent work! Thank you for sharing!
Could this model recognize hand-written characters like task2 which recognize hand-written number?
Hello,
I cloned the repository on Linux and tried to run it both from the terminal and from the Spyder IDE. The execution failed with the following exception:
Traceback (most recent call last):
File "<ipython-input-1-db715ac42e9c>", line 1, in <module>
runfile('/home/nest/Desktop/nengo/spaun2.0/run_spaun.py', wdir='/home/nest/Desktop/nengo/spaun2.0')
File "/home/nest/anaconda3/envs/nengo/lib/python3.7/site-packages/spyder_kernels/customize/spydercustomize.py", line 827, in runfile
execfile(filename, namespace)
File "/home/nest/anaconda3/envs/nengo/lib/python3.7/site-packages/spyder_kernels/customize/spydercustomize.py", line 110, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)
File "/home/nest/Desktop/nengo/spaun2.0/run_spaun.py", line 10, in <module>
from _spaun.configurator import cfg
File "/home/nest/Desktop/nengo/spaun2.0/_spaun/configurator.py", line 10, in <module>
from ._spa import MemoryBlock as MB
File "/home/nest/Desktop/nengo/spaun2.0/_spaun/_spa/__init__.py", line 2, in <module>
from .mem_block import MemoryBlock
File "/home/nest/Desktop/nengo/spaun2.0/_spaun/_spa/mem_block.py", line 8, in <module>
from .._networks import InputGatedMemory as WM
File "/home/nest/Desktop/nengo/spaun2.0/_spaun/_networks/__init__.py", line 1, in <module>
from .workingmemory import InputGatedMemory
File "/home/nest/Desktop/nengo/spaun2.0/_spaun/_networks/workingmemory.py", line 8, in <module>
from .assoc_mem import AssociativeMemory
File "/home/nest/Desktop/nengo/spaun2.0/_spaun/_networks/assoc_mem.py", line 9, in <module>
from nengo.utils.compat import is_iterable, range
ModuleNotFoundError: No module named 'nengo.utils.compat'
I looked through the Nengo source code and it seems that the module was deprecated and removed. Can you suggest some workaround to resolve the issue?
I use MAC(OSX El Captian) to run the code but it fails and says
ImportError: dlopen(/Users/liudong/Downloads/spaun2.0-master/_spaun/arms/three_link/py3LinkArm.so, 2): no suitable image found. Did find:
/Users/liudong/Downloads/spaun2.0-master/_spaun/arms/three_link/py3LinkArm.so: unknown file type, first eight bytes: 0x7F 0x45 0x4C 0x46 0x02 0x01 0x01 0x00
when the code run at 'import py3LinkArm' in '_spaun/arms/three_link/arm.py'.
Could you please tell me is this a environment problem or if i miss something or tell me some things I need to do before I run this code.
Thanks!
Hello all,
I'm trying to modify some of the model's components with a bit more subcortical detail, but it looks like when I run nengo-gui I'm unable to run the model and cannot drag across the screen. I figure this may be because I'm running on a Macbook pro 2014. These are my specs:
Processor: 2.6 GHz Dual-Core Intel Core i5
RAM: 8 GB 1600 MHz DDR3
Integrated Graphics: Intel Iris 1536 MB
Should I instead be running Spaun on a VM on GCP or AWS or something?
Thank you so much!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.