haozhiqi / isonet Goto Github PK
View Code? Open in Web Editor NEWDeep Isometric Learning for Visual Recognition (ICML 2020)
License: MIT License
Deep Isometric Learning for Visual Recognition (ICML 2020)
License: MIT License
very interesting work. In the paper, there are no discusssions about the differences on the training and inference speed compared to standard resnet. Are there any differences? Thanks
Hi there. Thank you for the interesting paper.
I noticed that the implementation of the ISONet architecture includes the possibility of instantiating based on CIFAR's images' dimensions (as noted here). However, I notice that the Model Zoo does not provide official weights for CIFAR. Are you planning on making these weights available?
Thank you
I want to train a custom networks, in your experience, how to decide the coefficient of ortho loss, Thks
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.