# ruotianluo/ImageCaptioning.pytorch

I decide to sync up this repo and self-critical.pytorch. (The old master is in old master branch for archive)

Repository: https://github.com/ruotianluo/ImageCaptioning.pytorch
Canonical: https://ross.abutalabs.com/products/imagecaptioningpytorch
Language: Python
License: MIT
License Family: permissive
Last push: 2023-10-05T03:59:08+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3491, "days_push": 1063, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1476, forks 420 (observed 2026-08-28T04:04:50.239862+00:00)

## What it is
A PyTorch research codebase for image captioning, supporting self-critical sequence training, bottom-up features, transformer captioning models, multi-GPU training, and test-time ensembling. It includes pretrained models, training/evaluation tools for COCO and Flickr30k, and a demo Colab notebook.

## Use cases
- train an image captioning model on COCO
- generate captions for images with pretrained models
- apply self-critical sequence training to captioning
- evaluate captioning models with BLEU/METEOR/CIDEr
- train captioning models on Flickr30k
- run multi-GPU distributed training for captioning

## When to choose
- you need a proven research codebase for image captioning with self-critical training
- you want pretrained captioning models for COCO or Flickr30k
- you need bottom-up attention features or transformer captioning models in PyTorch

## When to avoid
- you need production-ready image captioning as a service
- you want a general-purpose vision-language framework beyond captioning
- you need active development or frequent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, nlp, image-processing
- domain: machine-learning, deep-learning, computer-vision
- platform: python
- tags: image-captioning, pytorch, self-critical-training, coco, transformer, research-codebase, natural-language-processing, gpu

## Member repositories
- ruotianluo/ImageCaptioning.pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:50.239862+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:34:28.828511+00:00, confidence not recorded.
  - readme: https://github.com/ruotianluo/ImageCaptioning.pytorch (fetched 2026-08-28T04:04:50.239862+00:00, sha a84ce43df533)
- Data as of 2026-08-30T08:39:29.467469+00:00.