Comments (3)
Can you try with larger signals? If this is still the case, then there is indeed something missing/a bug. I guess you're running into round-off errors, as I did not specifically intend to support very small signals (better to pad them), and there might be some dependancies in the length that lead to what you do observe.
from pyscatwave.
Round-off errors are violent!
You are right, I tried other power of two sizes (20 run, taking the max of standard deviation over coordinates), and 4 is the only one for which I get absurd results. From 8 onwards, I get standard deviation of the order of 10^{-7}.
(Of course, nothing for 2, since your code works only if the size can be divided by 4, but this sounds like a reasonable requirement).
A+ !
from pyscatwave.
Well, all of this is due to conditioning & mantissa: with single floats on GPUs, your precision is about 10^-6 (which is around the normalized std you reported), and I guess a very small number like that occurs, then inverting such numbers is pretty much ill-conditioned! Indeed, there are many improvements to do, feel free to push...
from pyscatwave.
Related Issues (20)
- Inverse of Scattering Transform HOT 3
- Speed and FLOPs Information HOT 9
- run pyscatwave without cuda HOT 6
- How to calculate K, the output dimension of the output of scattering? HOT 1
- Is it very slow for big images like 4000*2000?
- Is there an implementation of 1-D Scattering Transform? HOT 2
- Error on AWS pytorch2.7 AIM
- why do you want to avoid fft normalization? HOT 1
- New version with 1D scaterring HOT 1
- Reconstructing the input image HOT 4
- Fantastic work! HOT 1
- MNIST example is incorrect HOT 2
- I have a question about reconstruction_exp.py HOT 1
- Implementation of pyscatwave using DL library primitives HOT 4
- About the problems of scattering network
- cublasNotInitialized HOT 13
- Tensorflow re-implementation HOT 10
- which part is gaussian smoothing? HOT 3
- Is calculating a derivative possible? HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pyscatwave.