Comments (1)
I haven't had any numerical issues when training with this loss function. It converges fine and the c implementation closely matches the reference python implementation which passes the numerical grad check to pretty high tolerance. Have you seen numerical issues or convergence problems when using the loss function in practice?
from transducer.
Related Issues (15)
- always get nothing trying to use viterbi decode interface HOT 4
- An error occurred while compiling HOT 5
- import error HOT 3
- Possible numerical error in log-norm computation HOT 2
- Cuda version HOT 1
- Just questions about the code.
- Questions about the reasoning in forward-backward algorithm HOT 2
- pytorch 1.1 support HOT 1
- Does not work for Pytorch 1.1 HOT 1
- Transducer update not backward compatible with speech repo running pytorch 0.4.1 HOT 1
- setup error: ‘isfinite’ was not declared in this scope HOT 3
- Question about the gradient computation HOT 2
- Support complex joiner networks HOT 2
- Import Error, _transducer can not be imported. HOT 1
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 transducer.