ericjang / normalizing-flows-tutorial Goto Github PK
View Code? Open in Web Editor NEWTutorial on normalizing flows.
License: MIT License
Tutorial on normalizing flows.
License: MIT License
Thanks for your elegant tutorial code.
I ran the nf_part1_intro.ipynb, and the results are quite normal with Tensorflow r1.5, r1.6, r1.7. But does not look friendly with r1.8. It can't produce the same result.
Does anyone have a similar problem?
From the example I know how to generate samples mimicking the destinated distribution. How do I get the z0 from a given sample x?
what exactly is the 'event_ndims'? how to fix this?
I read the code and find that base_dist which I believe is p(z0|x) is just a predefined network but an encoding network which is used in VAE. is p(z0|x) always a predefined distribution in practical use?
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.