uranusx86 / binarynet-on-tensorflow Goto Github PK
View Code? Open in Web Editor NEWbinary weight neural network implementation on tensorflow
binary weight neural network implementation on tensorflow
The test accuracy is too low, only 46.68%. I don't think this model works.
Hi!I am trying to replicate the accuracy of CIFAR-10, stated to be 88.60% in the paper (Theano Implementation). You managed to achieve 86.18% which is still low compared to that stated in the paper. Do you have any ideas as to why we get reduced accuracy? And why did you use layer learning rates as layer_lr/4 instead of the baseline Glorot?
Thanks
When I useBinaryNet, the weights saved reflect the actual weights, not the quantized one. What should I do if I want to save binary or quantized weights? Thanks a lot.
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.