iandrover / maml_noisy_contrasive_learner Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License
License: MIT License
With zero trick, we set the head to zero after each outer loop. It seems we don't need the outer update for the head. However, I can not reproduce the result of "exact loss implementation" with zero initialization, zero trick and EFIL assumption. It only get about 30% acc for miniimagenet 5-way 1-shot setting.
We only update the head in the inner loop for meta training. But we set it to zero for next outer loop. It seems we don't need update the head in inner loop for meta training.
A clear code! I have two questions...
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.