Comments (1)
Yes, code Is already available, instructions for training are in the examples/parallel_multi-scale_attention/readme.md, see the combine_transformer.py and transformer_bm(means big matrix, code for acceleration) in the fairseq/models for the main code, the idea to combine convolution and self attention is in the fairseq/moudules/multihead_attention.py.
from prime.
Related Issues (9)
- Spelling in the paper appendix HOT 1
- TypeError: argument of type 'NoneType' is not iterable
- TypeError: argument of type 'NoneType' is not iterable
- TypeError: argument of type 'NoneType' is not iterable HOT 1
- anyone running into 'nan' HOT 4
- The multi-scale gate is modeled by parameterized weights instead of depending on the input data. So, why should term it 'dymanticlly' rather than 'adaptively'? HOT 1
- Reproducing IWSLT14-de-en results HOT 3
- IWSLT'14 DE-EN Numbers HOT 2
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.
from prime.