Comments (3)
For pretraining&fine-tuning, don't understand why ground truth labels are used as [CLS] token as well.
from saint.
Hi, you don't need to base the CLS token on the actual label. It's an artifact from another project, the static token is generated in the embed_data_mask function (L321).
from saint.
Ah I see. Thanks for the explaianation.
from saint.
Related Issues (20)
- Problem about dataset id of Openml HOT 1
- Implementation of Attention module in Transformer
- Errors about dividing by zero
- fillna continuous data HOT 1
- Question: only continuous variables (no category) HOT 1
- Plotting attention for explainability
- Environment: packages not found HOT 1
- Attention plotting code HOT 1
- Module is absent when importing HOT 1
- enumerate DataLoader is too slow. HOT 2
- How do I use data other than openml data? HOT 1
- Issues with datasets
- MLP is equivalent to a single linear layer
- Deprecated saint_environment.yml file
- Muilti output regression HOT 1
- Handling missing values HOT 2
- Including target data while pretraining HOT 1
- Code for interpretability HOT 4
- issue about data 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 saint.