Skip to content

Latest commit

 

History

History
2 lines (2 loc) · 302 Bytes

README.md

File metadata and controls

2 lines (2 loc) · 302 Bytes

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.