# meijieru/crnn.pytorch

Convolutional recurrent network in pytorch

Repository: https://github.com/meijieru/crnn.pytorch
Canonical: https://ross.abutalabs.com/products/crnnpytorch
Language: Python
License: MIT
License Family: permissive
Topics: neural-network, scene-texts, recognition
Last push: 2024-09-19T06:50:05+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": 3474, "days_push": 713, "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 2492, forks 657 (observed 2026-08-28T04:06:56.496702+00:00)

## What it is
A PyTorch implementation of the Convolutional Recurrent Neural Network (CRNN) for scene text recognition, based on the 2016 paper by Shi et al. It includes a pretrained model for recognizing text in images and scripts for training new models on custom datasets.

## Use cases
- recognize text in scene images
- run OCR on images containing words
- train a CRNN text recognition model on my own dataset
- convert a pretrained CRNN model to PyTorch
- extract text from photos of signs

## When to choose
- you need a lightweight, well-known scene text recognition model in PyTorch
- you want to train CRNN from scratch on your own labeled text images
- you need CTC-based sequence recognition for variable-length text images

## When to avoid
- you need full OCR pipelines with detection plus recognition
- you want the latest state-of-the-art text recognition accuracy
- you need actively maintained code with recent PyTorch compatibility guarantees

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, ocr, image-processing
- domain: computer-vision, deep-learning
- platform: python, windows
- tags: crnn, scene-text-recognition, pytorch, ctc, text-recognition, pretrained-model, natural-language-processing, linux, macos

## Member repositories
- meijieru/crnn.pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:56.496702+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 2026-08-30T02:27:46.068589+00:00, confidence not recorded.
  - readme: https://github.com/meijieru/crnn.pytorch (fetched 2026-08-28T04:06:56.496702+00:00, sha 5fd464619b5f)
- Data as of 2026-08-30T08:39:29.467469+00:00.