Skip to content
/ DMICC Public

The code for the paper "Dual Mutual Information Constraints for Discriminative Clustering"

Notifications You must be signed in to change notification settings

Li-Hyn/DMICC

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

How to train?

Setup environment

Install packages as: pip install DMICC.yaml

Training

To train DMICC, we take main.py as an example, run the following commands sequentially to perform our method on STL-10:

python main.py -g 0,1,2,3 -n 8 --batch_size 128 --epochs 5000 --pretrained checkpoint_dir/checkpoint.pth

About

The code for the paper "Dual Mutual Information Constraints for Discriminative Clustering"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages