Skip to content

A project showcasing image captioning using two approaches: a custom CNN-based model for feature extraction and BLIP for state-of-the-art multimodal caption generation. Includes model comparisons, results, and code for training, inference, and evaluation on custom datasets.

Notifications You must be signed in to change notification settings

pratikkmane/ImageCaptioning-CNN-BLIP

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 

Repository files navigation

ImageCaptioning-CNN-BLIP

A project showcasing image captioning using two approaches: a custom CNN-based model for feature extraction and BLIP for state-of-the-art multimodal caption generation. Includes model comparisons, results, and code for training, inference, and evaluation on custom datasets.

About

A project showcasing image captioning using two approaches: a custom CNN-based model for feature extraction and BLIP for state-of-the-art multimodal caption generation. Includes model comparisons, results, and code for training, inference, and evaluation on custom datasets.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published