markusai / ra9 Goto Github PK
View Code? Open in Web Editor NEWJAX-based Spiking Neural Network framework
License: GNU General Public License v3.0
JAX-based Spiking Neural Network framework
License: GNU General Public License v3.0
Is your feature request related to a problem? Please describe.
TPU Cloud support
Describe the solution you'd like
Need to think
Describe alternatives you've considered
Nothing
Additional context
Nothing
when you see engine and function code,
output didn't work because of:
gamma is not the element of output function
so @jepetolee made not e/T but e @ e (absent means matrix multiplication)
This part should be resolved.
Describe the bug
img2col error when index add
To Reproduce
Steps to reproduce the behavior:
Expected behavior
work really well in test.py
Describe the bug
Dropout Error
To Reproduce
Steps to reproduce the behavior:
Expected behavior
Variable shape
When you see the paper(Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures), you can see the Convolution & pooling layers are based on LIF Neurons..
So we need to change the convolution and pooling layer into LIF Neurons...
It didn't work
Same as subject
Poisson Encoder is different when comparing the original paper
voltage rest value is undefined and i think this is the problem
최대한 논문 보고 backward를 따라 해 보았는데, 받아줘야하는 weight 형식이라던지 업데이트는 bintorch 기준으로만 하실 겁니까?
Same as above
Describe the bug
Loss function don't work when the batch size under the 10
To Reproduce
Steps to reproduce the behavior:
Expected behavior
Will raise TypeError
@junhoyeo Please check this issue
Is your feature request related to a problem? Please describe.
TPU_Colab_Version
Describe the solution you'd like
Using JAX example
Describe alternatives you've considered
No
Additional context
Nothing
Running with #4
in rA9/autograd/function.py, the Backward_function()doesn't get grads on output.py
Describe the bug
Output NaN problem
Is your feature request related to a problem? Please describe.
Not just a function to solve, but just use grad function
Describe the solution you'd like
Using jax grad
Describe alternatives you've considered
Nah
Additional context
Nah
Describe the bug
When it goes another data batch, then it fails to generate full spike
same as subject
The design of Poison encoder is wrecked i think.
memory leak problem occurred
in activation function
img2col.py in nn/_functions/
dataloader.py in utils/data/
Because some parts of img2col use numpy not jax.numpy, and dataloader is based on python so it is quite slow
Optimizer didn't work so I and my partner will fix it
AttributeError: module 'jax.numpy' has no attribute 'random'
We might don't think about the basic opponents, Function and Variable and Parameter.
Parameter did well on class but function didn't and actually loss is defined as the function.(or inherited)
Please Check this Issue for fixing it.
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.