Welcome to MMOCR’s documentation!

You can switch between English and Chinese in the lower-left corner of the layout.

Get Started

• Overview
• Installation
  • Prerequisites
  • Environment Setup
  • Installation Steps
  • Customize Installation
  • Dependency on MMEngine, MMCV & MMDetection
• Quick Run
  • Inference
  • Prepare a Dataset
  • Modify the Config
  • Browse the Dataset
  • Training
  • Testing
  • Visualize the Outputs
• FAQ
  • General
  • Text Recognition

User Guides

• Inference
  • Basic Usage
  • Initialization
  • Inference
  • API
  • Command Line Interface
• Config
  • Common Usage
  • Configuration Content
  • Directory Structure
  • Naming Conventions
• Dataset Preparation
  • Introduction
  • Downloading Datasets and Converting Format
  • Dataset Configuration
• Training and Testing
  • Single GPU Training and Testing
  • Training and Testing with Multiple GPUs
  • Training and Testing with Slurm Cluster
  • Advanced Tips
• Visualization
  • Configuration
  • Storage
  • Plot
• Useful Tools
  • Analysis Tools

Basic Concepts

• Data Structures and Elements
  • Data Elements - xxxData
  • DataSample xxxDataSample
• Data Transforms and Pipeline
  • Data Loading
  • Data Augmentation
  • Data Formatting
  • Cross Project Data Adapters
  • Wrappers
• Evaluation
  • Metrics
• Dataset
  • Overview
  • Common Interfaces
  • Dataset Classes and Annotation Formats
• Overview & Features[coming soon]
• Data Flow[coming soon]
• Models[coming soon]
• Visualizers[coming soon]
• Convention[coming soon]
• Engine[coming soon]

Dataset Zoo

• Overview
  • Supported Datasets
  • Dataset Details
• Dataset Preparer (Beta)
  • One-click data preparation script
  • Advanced Usage
• Text Detection
  • Overview
  • Important Note
  • ICDAR 2011 (Born-Digital Images)
  • ICDAR 2017
  • CurvedSynText150k
  • DeText
  • Lecture Video DB
  • LSVT
  • IMGUR
  • KAIST
  • MTWI
  • ReCTS
  • ILST
  • VinText
  • BID
  • RCTW
  • HierText
  • ArT
• Text Recognition
  • Overview
  • ICDAR 2011 (Born-Digital Images)
  • coco_text
  • SynthAdd
  • OpenVINO
  • DeText
  • NAF
  • Lecture Video DB
  • LSVT
  • IMGUR
  • KAIST
  • MTWI
  • ReCTS
  • ILST
  • VinText
  • BID
  • RCTW
  • HierText
  • ArT
• Key Information Extraction
  • Overview
  • Preparation Steps

Model Zoo

• Overview
  • Weights
  • Statistics
• SOTA Models
  • ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
  • ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
  • SPTS: Single-Point Text Spotting
• BackBones
  • oCLIP
• Text Detection Models
  • DBNet
  • DBNetpp
  • DRRG
  • FCENet
  • Mask R-CNN
  • PANet
  • PSENet
  • Textsnake
• Text Recognition Models
  • ABINet
  • ASTER
  • CRNN
  • MASTER
  • NRTR
  • RobustScanner
  • SAR
  • SATRN
  • SVTR
• Key Information Extraction Models
  • SDMGR

Notes

• Branches
  • Branch Overview
• Contribution Guide
  • What is PR
  • Basic Workflow
  • Procedures in detail
  • PR Specs
• Changelog of v1.x
  • v1.0.0 (04/06/2023)
  • v1.0.0rc6 (03/07/2023)
  • v1.0.0rc5 (01/06/2023)
  • v1.0.0rc4 (12/06/2022)
  • v1.0.0rc3 (11/03/2022)
  • v1.0.0rc2 (10/14/2022)
  • v1.0.0rc1 (10/09/2022)
  • v1.0.0rc0 (09/01/2022)

Migrating from MMOCR 0.x

• Overview
• What’s New in MMOCR 1.x
• Branch Migration
  • Resolving Conflicts When Upgrading the main branch
• Code Migration
  • Fundamental Changes
  • Text Detection Models
  • Text Recognition
  • Key Information Extraction
  • Utils Migration
• Dataset Migration
  • Review of Old Dataset Formats
  • New Dataset Format
  • Compatibility
• Pretrained Model Migration
• Data Transform Migration
  • Introduction
  • Configuration Migration Guide

API Reference

• mmocr.apis
• mmocr.structures
• mmocr.datasets
• mmocr.transforms
• mmocr.models
• mmocr.evaluation
• mmocr.visualization
• mmocr.engine
• mmocr.utils

Contact US

• Welcome to the OpenMMLab community

Switch Language

• English
• 简体中文

Indices and tables

• Index

• Search Page