njchoma/transformer_image_caption

Image Captioning based on Bottom-Up and Top-Down Attention model

42
/ 100
Emerging

This project offers a baseline for developing image captioning models. It takes images as input and generates descriptive textual captions, providing a starting point for those building or experimenting with deep learning models for image understanding. It is primarily for deep learning researchers and engineers focusing on computer vision and natural language processing.

104 stars. No commits in the last 6 months.

Use this if you are a deep learning researcher or engineer who wants to train and evaluate image captioning models, or if you need a strong baseline for further experimentation in this field.

Not ideal if you are looking for a ready-to-use, off-the-shelf application to caption images without needing to delve into model training or development.

deep-learning computer-vision natural-language-processing image-captioning model-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

104

Forks

17

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 03, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/njchoma/transformer_image_caption"

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