Fast-plate-ocr adds lightweight license plate recognition with Keras 3 and ONNX
tom_doerr · x · 2026-07-28
A GitHub project called fast-plate-ocr offers lightweight OCR models for license plate text recognition.
- Designed to run after a plate detector on cropped plate images
- Supports Keras 3 backends, including TensorFlow, JAX, and PyTorch
- Provides ONNX Runtime inference for fast, cheap deployment
- The project page shows a working demo that extracts both the plate text and region
More from Infra
- Frozen 12B system reuses verified memory at zero tokens and 6,000,000-token context — Corbenci · 2026-07-28
- OpenAI’s expected $750 billion compute spend puts Anthropic’s leasing strategy under pressure — remybigot · 2026-07-28
- AMD, SGLang and Moonshot ship together as the chip wars shift to infrastructure — AnushElangovan · 2026-07-28
- A user says GPT-5.4, Opus 4.6, and Kimi k3 already cover most needs — haider1 · 2026-07-28
- ai& and Rebellions set a webinar on sovereign AI and scalable inference — DavidBennett__ · 2026-07-28
- Inline prompt inspection adds about 525ms TTFB in an LLM proxy gateway — the_liberty · 2026-07-28