DoWG optimizer and 8bit variant
License: MIT License
This is an implementation of the DoWG optimization algorithm as laid out by Khaled et al.. I am unsure if the implementation is correct, and I took the liberty of creating a quantized implementation under DoWG8bit as the ordinary version absolutely gobbles up Vram.
Pull requests are welcome.
Line 41 in 1c72e4c
Division by zero can still happen with near zero values, you can either explicitly check if sqrt(v_t) is zero or add a small constant to divisor.
eta_t = r_t.pow(2) / (torch.sqrt(v_t) + 3e-8)
exact constant up to you, I picked 3e-8 because numpy.sqrt(numpy.float16(2e-8)) == 0
May not fix your problem, but couldn't hurt.
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
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.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.