AmirhosseinHonardoust/Image-Captioning-CNN-LSTM

An end-to-end image captioning project using a CNN encoder (ResNet-50) and LSTM decoder in PyTorch. Includes vocabulary building, preprocessing, training with BLEU evaluation, and inference. Generates natural language captions for images with saved metrics, model checkpoints, and visualization outputs.

25
/ 100
Experimental

This project helps you automatically generate descriptive sentences for images. You provide a set of images along with their human-written captions, and the system learns to produce new, human-like captions for any new image you show it. This is useful for anyone working with large collections of images who needs to quickly describe their content.

No commits in the last 6 months.

Use this if you need to automatically generate clear, concise text descriptions for a collection of images, perhaps for searchability or accessibility.

Not ideal if you need highly nuanced or subjective interpretations of images, as the captions are based on learned patterns from existing descriptions.

content-management digital-asset-management image-cataloging accessibility-enhancement
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

47

Forks

Language

Python

License

MIT

Last pushed

Sep 13, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AmirhosseinHonardoust/Image-Captioning-CNN-LSTM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.