Comments (4)
Wouldn't it be easier to just shuffle training data before training in fastText itself so that users do not get surprised?
from fasttext.
@riyadparvez No since fastText does not accept IDs separately it would be difficult to join data back if it was part of a larger data set. I dont want to append an ID to the text itself. So shuffle-> break text off -> fasttext -> join. I can count on order this way.
from fasttext.
Yes, this is an expected behavior. FastText uses stochastic gradient descent to learn the model, and the examples are processed "in order". Thus, it is important to shuffle the training data, so that not all the examples of a given class are seen first, then the examples of a second class, etc.
from fasttext.
Thanks for the clarification 👍
from fasttext.
Related Issues (20)
- Same
- What's the status of this project? HOT 1
- pip install imutils not working HOT 1
- how to compress fasttext unsupervised model ? HOT 1
- G
- Unable to build wasm HOT 6
- error during pip install HOT 5
- model can't be loaded by fasttext(python ) while the model trained by fasttext(cmake/make)
- Facing wrong prediction due to antonym vector closer than synonym vectors
- no data
- 🔥 Any plans to update the pre-trained model for Language Identification? HOT 1
- AWS - No module named 'fasttext_pybind' HOT 2
- @abdoulfatah Omar Abdillahi HOT 1
- So many wrong predictions in latest version?
- Replicating Results HOT 3
- if i want to load pretrained model and train, what should i do HOT 1
- How is the underlying embedding matrix updated?
- Cannot install FastText on Windows using pip HOT 6
- Fa
- Improved LangID model?
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 fasttext.