3.1 KiB
Overview
This chapter introduces you to the overall framework of MMYOLO and provides links to detailed tutorials.
What is MMYOLO
MMYOLO is a YOLO series algorithm toolbox, which currently implements only the object detection task and will subsequently support various tasks such as instance segmentation, panoramic segmentation, and key point detection. It includes a rich set of object detection algorithms and related components and modules, and the following is its overall framework.
MMYOLO file structure is identical to the MMDetection. To fully reuse the MMDetection code, MMYOLO includes only custom content, consisting of 3 main parts: datasets, models, engine.
- datasets support a variety of data sets for object detection.
- transforms include various data enhancement transforms.
- models are the most important part of the detector, which includes different components of it.
- detectors define all detection model classes.
- data_preprocessors is used to preprocess the dataset of the model.
- backbones include various backbone networks.
- necks include various neck components.
- dense_heads include various dense heads of different tasks.
- losses include various loss functions.
- task_modules provide components for testing tasks, such as assigners, samplers, box coders, and prior generators.
- layers provide some basic network layers.
- engine is a component of running.
- optimizers provide optimizers and packages for optimizers.
- hooks provide hooks for runner.
How to use this tutorial
The detailed instruction of MMYOLO is as follows.
-
Look up install instructions to get_started.md.
-
The basic method of how to use MMYOLO can be found here:
-
YOLO series of tutorials on algorithm implementation and full analysis:
-
YOLO series of Deploy tutorials
-
Refer to the following tutorials for an in-depth look: