# mmdetection

**Repository Path**: openvinotoolkit-prc/mmdetection

## Basic Information

- **Project Name**: mmdetection
- **Description**: This is an Object Detection and Instance Segmentation toolbox, that is a part of OpenVINO Training Extensions.
- **Primary Language**: Python
- **License**: Apache-2.0
- **Default Branch**: ote
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 4
- **Forks**: 1
- **Created**: 2020-09-25
- **Last Updated**: 2025-08-10

## Categories & Tags

**Categories**: cv

**Tags**: None

## README

# MMDetection

![](https://img.shields.io/badge/python-3.6%2B-green)
![](https://img.shields.io/badge/pytorch-1.7.1%2B-orange)
![](https://img.shields.io/badge/openvino-2021.4-blue)
![](https://img.shields.io/badge/onnxruntime-1.1.2%2B-yellow)


This is an Object Detection and Instance Segmentation toolbox, that is a part of [OpenVINO™ Training Extensions](https://github.com/opencv/openvino_training_extensions).

Project is based on open-mmlab's [MMDetection](https://github.com/open-mmlab/mmdetection).

## Installation

Please refer to [install.md](docs/install.md) for installation and dataset preparation.

## Get Started

Please see [getting_started.md](docs/getting_started.md) for the basic usage. There are also tutorials for [finetuning models](docs/tutorials/finetune.md), [adding new dataset](docs/tutorials/new_dataset.md), [designing data pipeline](docs/tutorials/data_pipeline.md), and [adding new modules](docs/tutorials/new_modules.md).

## Models compression

This project allows making compression of the models by [NNCF](https://github.com/openvinotoolkit/nncf_pytorch) framework.

See details in [nncf_compression.md](docs/nncf_compression.md).

## Model Zoo

Please see [model_zoo.md](docs/model_zoo.md) for the list of pre-trained models.

## Contributing

We appreciate all contributions to improve this project. Please refer to [CONTRIBUTING.md](.github/CONTRIBUTING.md) for the contributing guideline.

## Contact

This repo is currently maintained by Ilya Krylov ([@Ilya-Krylov](https://github.com/Ilya-Krylov)), Pavel Druzhkov ([@druzhkov-paul](https://github.com/druzhkov-paul)) and Dmitry Sidnev ([@DmitriySidnev](https://github.com/DmitriySidnev)).