bkmi / cnre Goto Github PK
View Code? Open in Web Editor NEWExtending amortized approximate likelihood-ratio estimation / neural ratio estimation to the contrastive case, while staying consistent with the original work.
Extending amortized approximate likelihood-ratio estimation / neural ratio estimation to the contrastive case, while staying consistent with the original work.
Dear authors,
Firstly, I want to thank you for providing the code! They are very helpful for enhancing our understanding our your method.
Second, through reading your Readme file and your provided folders, it seems that I cannot find a complete script to reproduce the training of your method. Especially, I have checked you 'basic algorithm.ipynb'.
At the block of loading the loss function, l2 = cnre.loss(classifier, theta[:256], x[:256], 2, gamma=1.0, reuse=True)
, the error message on my end is: NotImplementedError: there is a bug in this computation. refer to https://github.com/mackelab/sbi/blob/main/sbi/inference/snre/snre_c.py
.
And moreover, when running your function `doit(num_atoms=2)', I encountered the error 'module 'cnre.algorithms' has no attribute 'cnre''. And there seems to be no difference between the configuration of your method and the one under the title of 'gillies'.
Given all the issues, could I kindly ask your help?
Thanks!
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.