Skip to content

elkhomar/Domain-adaptation-research-project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

86 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Domain-adaptation-research-project

Implementation of several domain adaptation methods with a pipeline that allows to run complex experiments with a CLI using yaml config files (hydra library)

How It Works :

The base configuration is found in config/e_ada.yaml and can be overridden by passing arguments in the command line :

  • For regular training : python src/train.py experiment=e_ada model.lambd=1.0 model.loss.target=src.losses.SlicedWassersteinLoss
  • For grid search : python src/train.py -m experiment=e_ada model.lambd=0.5,1.0,1.5,2.0 data.batch_size=16,32,64
  • For profiling: python src/train.py experiment=e_ada model.lambd=1.0 model.loss.target=src.losses.SlicedWassersteinLoss debug=profiler

The pipeline is based on https://github.com/ashleve/lightning-hydra-template

Overleaf :

https://www.overleaf.com/project/65bbbd12e2b5ee9e67df749c

Wandb runs :

Methods :

Invariant :

Data :

Useful resources

https://remi.flamary.com/cours/tuto_da/DA_shallow_to_deep.pdf

About

Implementation of several domain adaptations methods

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •  

Languages