Skip to content

Classification of Tiny-Imagenet-200 dataset without any pretrained weights

Notifications You must be signed in to change notification settings

Ayush-Rai/Tiny-imagenet-200

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

Tiny-imagenet-200

Classification of Tiny-Imagenet-200 dataset without any pretrained weights

Architecture Used

Densenet-201 with a shallow network with following layers:

  • GlobalAveragePooling2D()
  • Dropout(0.4)
  • Softmax layer of 200 units.

Accuracy

  • Top-1 : 31.69%
  • Top-5 : 57.58%

Error

  • Top-1 :2.99
  • Top-5 :2.99

About

Classification of Tiny-Imagenet-200 dataset without any pretrained weights

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published