Welcome to MyOCR Documentation

MyOCR is a highly extensible and customizable framework for streamline development and deployment of production-ready OCR systems.

MyOCR makes it easy to train your custom models and seamlessly integrate them into your own OCR pipeline.

Key Features

⚡️ End-to-End OCR Development Framework – Designed for developers to build and integrate detection, recognition and custom OCR models in a unified and flexible pipeline.

🛠️ Modular & Extensible – Mix and match components - swap models, predictors, or input output processors with minimal changes.

🔌 Developer-Friendly by Design - Clean Python APIs, prebuilt pipelines and processors, and straightforward customization for training and inference.

🚀 Production-Ready Performance – ONNX runtime support for fast CPU/GPU inference, support various ways of deployment.

Getting Started

1. Installation: Set up MyOCR and download necessary models.
2. Overview: Understand the core concepts (Models, Predictors, Pipelines) for building your OCR capabilities.
3. Inference Guide: Learn how to run OCR tasks using MyOCR.

Core Concepts

• Models: Learn about the supported model types (ONNX, PyTorch, Custom) and architectures.
• Predictors: Understand how models are wrapped with input/output processors to Predictor.
• Pipelines: Explore the high-level pipelines that orchestrate predictors for end-to-end OCR.

Additional Resources

• FAQ: Find answers to common questions.
• Changelog: See recent updates and changes.
• Contributing Guidelines: Learn how to contribute to the project.
• GitHub Repository: Source code, issues, and discussions.

License

MyOCR is open-sourced under the Apache 2.0 License.

Comments