# sirius-ai/LPRNet_Pytorch

Pytorch Implementation For LPRNet, A High Performance And Lightweight License Plate Recognition Framework.

Repository: https://github.com/sirius-ai/LPRNet_Pytorch
Canonical: https://ross.abutalabs.com/products/lprnet_pytorch
Language: Python
License: Apache-2.0
License Family: permissive
Topics: license-plate-recognition, plate-recognition, plate-detection, lprnet, pytorch, ctc-loss
Last push: 2023-06-21T13:37:25+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": 2678, "days_push": 1169, "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 1156, forks 280 (observed 2026-08-28T04:03:48.178416+00:00)

## What it is
A PyTorch implementation of LPRNet, a lightweight deep neural network for license plate recognition. It ships with pretrained weights focused on Chinese blue and green (new energy) plates and supports training on custom datasets.

## Use cases
- recognize license plates from images
- train a license plate recognition model on my own dataset
- run lightweight ALPR inference on a GPU
- fine-tune plate recognition for other countries' plates
- test LPRNet accuracy on a custom plate dataset

## When to choose
- you need fast, lightweight license plate character recognition (1.7MB model, sub-millisecond GPU inference)
- you work primarily with Chinese blue/green plates or can fine-tune for others
- you want a PyTorch codebase with pretrained weights to build on

## When to avoid
- you need full ALPR pipelines including plate detection and localization out of the box
- you need production support, frequent updates, or a maintained release cycle
- you need recognition of many international plate formats without training data

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, deep-learning, computer-vision, ocr, image-processing
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python, cross-platform
- tags: license-plate-recognition, lprnet, pytorch, ctc-loss, alpr, pretrained-model

## Member repositories
- sirius-ai/LPRNet_Pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:48.178416+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 2026-08-30T06:32:09.356460+00:00, confidence not recorded.
  - readme: https://github.com/sirius-ai/LPRNet_Pytorch (fetched 2026-08-28T04:03:48.178416+00:00, sha ec6de3b366d4)
- Data as of 2026-08-30T08:39:29.467469+00:00.