zarzouram/image_captioning_with_transformers
Pytorch implementation of image captioning using transformer-based model.
Implements an encoder-decoder transformer architecture with per-head attention visualization capabilities, modified from PyTorch's standard multi-head attention to enable detailed attention analysis. Trained on MS COCO 2017 with beam search inference and comprehensive NLG evaluation metrics (BLEU, METEOR, GLEU). Includes preprocessing pipeline for image-caption dataset creation with HDF5 storage and Tensorboard integration for training monitoring.
No commits in the last 6 months.
Stars
68
Forks
9
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Apr 13, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/zarzouram/image_captioning_with_transformers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
rese1f/aurora
[ICLR 2025] AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
senadkurtisi/pytorch-image-captioning
Transformer & CNN Image Captioning model in PyTorch.
tanishqgautam/Image-Captioning
Implemented 3 different architectures to tackle the Image Caption problem, i.e, Merged...
ilya16/deephumor
DeepHumor: Image-based Meme Generation using Deep Learning
Hamtech-ai/Persian-Image-Captioning
A Persian Image Captioning model based on Vision Encoder Decoder Models of the transformers🤗.