Light

khakhulin / compressed-transformer Goto Github PK

View Code? Open in Web Editor NEW

46.0 46.0 9.0 1.67 MB

Compression of NMT transformer model with tensor methods

License: MIT License

Python 22.24% Lua 7.31% Shell 1.23% Jupyter Notebook 67.55% Perl 1.67%

compression deep-learning mnist nlp nmt pytorch tensor-train transformer translation tucker

compressed-transformer's People

Contributors

Stargazers

Watchers

Forkers

sunyancn maxindian iamweiweishi graftedlife abhid1 zhaoyibo61 lovegood-1 tripleess ozturkosu

compressed-transformer's Issues

inference time

hi, I am in a puzzle about the inference time of the compressed model. Why is the compressed model more time consuming? Shouldn't it be faster with fewer parameters(about half of the orignal) ?

thx

High GPU memory consumption

Hi,
I tried to integrate the TTLinear layer into TransformerXL,
however I found that it consumes much more memory than usual.
Couldn't even train it.

Model before compression was 151M params, after compression was 124M params.
It even consumed much more memory in inference - 3021MB for the compressed model versus 2132MB for the normal model.

I also tried to write the "forward" method more efficiently (e.g with bmm) , it didn't help too.

Did you experience such problems? do you know anyway around this?
Thanks,

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 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.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

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.