Overview

This chapter will introduce you to the overall framework of MMPose and provide links to detailed tutorials.

What is MMPose

MMPose is a Pytorch-based pose estimation open-source toolkit, a member of the OpenMMLab Project. It contains a rich set of algorithms for 2d multi-person human pose estimation, 2d hand pose estimation, 2d face landmark detection, 133 keypoint whole-body human pose estimation, fashion landmark detection and animal pose estimation as well as related components and modules, below is its overall framework.

MMPose consists of 8 main components:

• apis provides high-level APIs for model inference

• structures provides data structures like bbox, keypoint and PoseDataSample

• datasets supports various datasets for pose estimation

  • transforms contains a lot of useful data augmentation transforms

• codecs provides pose encoders and decoders: an encoder encodes poses (mostly keypoints) into learning targets (e.g. heatmaps), and a decoder decodes model outputs into pose predictions

• models provides all components of pose estimation models in a modular structure

  • pose_estimators defines all pose estimation model classes

  • data_preprocessors is for preprocessing the input data of the model

  • backbones provides a collection of backbone networks

  • necks contains various neck modules

  • heads contains various prediction heads that perform pose estimation

  • losses contains various loss functions

• engine provides runtime components related to pose estimation

  • hooks provides various hooks of the runner

• evaluation provides metrics for evaluating model performance

• visualization is for visualizing skeletons, heatmaps and other information

How to Use this Guide

We have prepared detailed guidelines for all types of users:

1. For installation instrunctions:

   • Installation

2. For the basic usage of MMPose:

   • A 20-minute Tour to MMPose

   • Demos

   • Inference

   • Configs

   • Prepare Datasets

   • Train and Test

   • Deployment

   • Model Analysis

   • Dataset Annotation and Preprocessing

3. For developers who wish to develop based on MMPose:

   • Learn about Codecs

   • Dataflow in MMPose

   • Implement New Models

   • Customize Datasets

   • Customize Data Transforms

   • Customize Optimizer

   • Customize Logging

   • Migration Guide

4. For researchers and developers who are willing to contribute to MMPose:

   • Contribution Guide

5. For some common issues, we provide a FAQ list:

   • FAQ