Comments (1)
Hi! It depends on the setting. For the normal linear eval experiments we used the same data used for the continual pre-training (all tasks), for or the semi-supervised experiments we used 1% or 10% of such data, and for the transfer experiments we used the domainnet real dataset.
from cassle.
Related Issues (17)
- How did you train the classifier? HOT 3
- problem with reproducibility HOT 3
- About the Forward Transfer HOT 2
- Difficulty In Reproducing The Paper Results (e.g., Table 4., BYOL reported 66%, measured <<60%) HOT 13
- Forward Transfer Issue HOT 10
- Some questions about training and evaluation process HOT 5
- Some question about lower and upper bounds HOT 2
- train data on DomainNet HOT 1
- Question about contrastive distillation loss
- Why did you load the checkpoint of task 0 before training cassle? HOT 5
- DomainNet dataset version HOT 1
- ¿Bug in online KNN eval? HOT 3
- Need of checkpoints : BT and VicReg HOT 4
- KNN Classifier Issue HOT 8
- Task_id set to zero as first task SSL HOT 2
- The classifier for Linear Evaluation Accuracy 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 cassle.