An Image Caption Generator using CNN and LSTM with the Flickr8k dataset generates text descriptions for images. CNN extracts image features, which are passed to LSTM to produce captions word by word. Trained on 8000 images, each with 5 captions, the model learns to map visual content to meaningful text.
VC6378/Image-to-Caption-Generator
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|