Skip to content

Meme Classifier over 780 categories (uses VGGNet's last layer features)

License

Notifications You must be signed in to change notification settings

mayanks43/Meme-Classifier

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Meme-Classifier

This is a demonstration of how to build a visual classifier for meme images. The classifier can identify categories (such as "bad luck brian") of meme images by scanning their pixels. As demonstrated in the two itorch notebooks, it can identify 780 meme categories with a confidence greater than 98% (usually). It uses the all-powerful VGGNet to generate features from pixels and then uses a simple logisitic regression to classify these features. Scroll to the end of the "Train_and_Test" ipython notebook to see an example of the classifier in action.

Requirements

  • torch
  • itorch
  • CUDA (Optional)
  • cunn (Optional)

About

Meme Classifier over 780 categories (uses VGGNet's last layer features)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published