Skip to content

Code for IJCAI24 paper "A Dual Memory System for Enhanced Replay in Continual Learning"

Notifications You must be signed in to change notification settings

siddharthamantrala/AER

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AER

aer_overall

We extended the Mammoth framework with our method AER.

Setup

Anaconda is recommended for virtual environment management.

After installation, do:

  • conda create -n AER python=3.10.0
  • conda activate AER
  • pip install -r requirements.txt

Run

Example:

python main.py --model 'er_bpcn' --buffer_size 200 --dataset 'seq-cifar100' --theta 0.1 --seed 0

About

Code for IJCAI24 paper "A Dual Memory System for Enhanced Replay in Continual Learning"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%