Skip to content

Integrated Google ViT-Base with OpenAI GPT2 to create a Sequence-2-Sequence model that generates a text caption given an input image.

Notifications You must be signed in to change notification settings

llLucidll/Captionr

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 

Repository files navigation

Uses a pretrained Google ViT vision encoder connected to GPT 2 to generate captions for images. Obtained a BLEU score of 8+ on the flickr8k Database.

About

Integrated Google ViT-Base with OpenAI GPT2 to create a Sequence-2-Sequence model that generates a text caption given an input image.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages