laurent-dinh / nice Goto Github PK
View Code? Open in Web Editor NEWLicense: BSD 3-Clause "New" or "Revised" License
License: BSD 3-Clause "New" or "Revised" License
I have a decent understanding of Normalizing Flows and now have read both of your paper - NICE & Real NVP.
I understand the notion of Affine transform etc and believe have understood the mechanics of splitting the input into 2 parts etc as your papers describe.
The part that I am having little trouble with is the usage of the word "Coupling"? What does it mean in this context? I have a reason to believe that the usage has its roots in some mathematical concept that I am not aware of.
Would appreciate it if you could educate me.
Regards & thanks
Kapil
Hi,
I checked repo, seems some important modules like pylearn2.utils.py, pylearn2.config.py has been removed from repo or not included in repo.
Also, in some modules codes are wrong, for instance in the following module at line 21, packages has been imported from itself:
Will be great if anyone can help me to fix this issues, because I want use this codes for learning MNIST.
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.