Comments (3)
You are right, you should get the final clustering results via spherical kmeans on the target encoder's features.
from propos.
The features after projection head from the target encoder (ema-updated one).
from propos.
Thanks for answering, please excuse my interruption.
Should I get the final clustering results
via spherical kmeans on the target encoder's features, OR other ways instead?
P.S. The conclusion below is impressive:
directly using the representations learned by BYOL for k-means clustering outperforms previous work including the contrastive-based ones.
from propos.
Related Issues (16)
- About spherical k-means implementation HOT 2
- About Performance on Imagenetdogs HOT 4
- Could u please share the config file for STL? HOT 2
- Got 65% ACC for BYOL on ImageNetdogs HOT 2
- About cifar10 performance on SimSiam HOT 5
- How to change parameters when num_device =2 HOT 1
- How to train ProPos on the STL-10 dataset?
- what does the memory data loader do in the basic_template.py? HOT 1
- how to reproduce pcl HOT 2
- Can't Reproduce Result in CIFAR-20 HOT 14
- How to generate pseudo label for unlabeled data in STL-10 and use them in PSL term? HOT 1
- I can't get the results in the paper using the pretrained models you provided HOT 7
- How to train Propos on STL-10 dataset HOT 1
- Results on CIFAR10 with ResNet34 HOT 1
- Training speed of ImageNet-10 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 propos.