Skip to content

Trying out different image classification algorithms on Fashion MNIST dataset

License

Notifications You must be signed in to change notification settings

rupak-118/Fashion-MNIST-experiments

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 

Repository files navigation

Fashion-MNIST-experiments

Tried and tested :

  1. Stacked, deep CNN architectures (~90.5% test acc.)
  2. Stacked, deep CNN architectures with dropout, data augmentation or both (~92% test acc.)

To-Do :

  1. Usage of SVM loss instead of softmax loss
  2. Ensembles of deep CNN models with SVC/kNNs etc.
  3. Try application of pre-trained ImageNet models
  4. CapsNet implementation on Fashion MNIST

About

Trying out different image classification algorithms on Fashion MNIST dataset

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published