Top AI Repos — open-source AI, indexed and scored

Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.

open-mmlab/mmflow

OpenMMLab optical flow toolbox and benchmark

48Apache-2.0Python

View on GitHub Website

Stars: 1,060
Forks: 117
Watchers: 5
Open issues: 24
Contributors: 12

Star history, last 90 days— over 5 snapshots

2026-07-24 · 1,0602026-08-06 · 1,060

Star history, last 90 days
Date	Stars
2026-07-24	1060
2026-07-25	1060
2026-07-28	1060
2026-07-30	1060
2026-08-06	1060

Today

— stars today

This week

— stars this week

This month

— stars this month

Momentum

0.0

growth rate 0.00%/day

From the README

<div align="center">
  <img src="resources/mmflow-logo.png" width="600"/>
    <div>&nbsp;</div>
  <div align="center">
    <b><font size="5">OpenMMLab website</font></b>
    <sup>
      <a href="https://openmmlab.com">
        <i><font size="4">HOT</font></i>
      </a>
    </sup>
    &nbsp;&nbsp;&nbsp;&nbsp;
    <b><font size="5">OpenMMLab platform</font></b>
    <sup>
      <a href="https://platform.openmmlab.com">
        <i><font size="4">TRY IT OUT</font></i>
      </a>
    </sup>
  </div>
  <div>&nbsp;</div>

[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/mmflow)](https://pypi.org/project/mmflow/)
[![PyPI](https://img.shields.io/pypi/v/mmflow)](https://pypi.org/project/mmflow)
[![docs](https://img.shields.io/badge/docs-latest-blue)](https://mmflow.readthedocs.io/en/latest/)
[![badge](https://github.com/open-mmlab/mmflow/workflows/build/badge.svg)](https://github.com/open-mmlab/mmflow/actions)
[![codecov](https://codecov.io/gh/open-mmlab/mmflow/branch/master/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmflow)
[![license](https://img.shields.io/github/license/open-mmlab/mmflow.svg)](https://github.com/open-mmlab/mmflow/blob/master/LICENSE)
[![open issues](https://isitmaintained.com/badge/open/open-mmlab/mmflow.svg)](https://github.com/open-mmlab/mmflow/issues)

[📘Documentation](https://mmflow.readthedocs.io/en/latest/) |
[🛠️Installation](https://mmflow.readthedocs.io/en/latest/install.html) |
[👀Model Zoo](https://mmflow.readthedocs.io/en/latest/model_zoo.html) |
[🤔Reporting Issues](https://github.com/open-mmlab/mmflow/issues/new/choose)

</div>

<div align="center">

English | [简体中文](README_zh-CN.md)

</div>

## Introduction

MMFlow is an open source optical flow toolbox based on PyTorch. It is a part of the [OpenMMLab](https://openmmlab.com/) project.

The master branch works with **PyTorch 1.5+**.

<https://user-images.githubusercontent.com/76149310/141947796-af4f1e67-60c9-48ed-9dd6-fcd809a7d991.mp4>

### Major features

- **The First Unified Framework for Optical Flow**

  MMFlow is the first toolbox that provides a framework for unified implementation and evaluation of optical flow algorithms.

- **Flexible and Modular Design**

  We decompose the flow estimation framework into different components,
  which makes it much easy and flexible to build a new model by combining different modules.

- **Plenty of Algorithms and Datasets Out of the Box**

  The toolbox directly supports popular and contemporary optical flow models, *e.g.* FlowNet, PWC-Net, RAFT, etc,
  and representative datasets, FlyingChairs, FlyingThings3D, Sintel, KITTI, etc.

## What's New

**v0.5.2** was released in 01/10/2023:

- Add flow1d attention

Please refer to [changelog.md](docs/en/changelog.md) for details and release history.

## Installation

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

## Get Started

If you're new of optical flow, you can start with [learn the basics](docs/en/intro.md). If you’re familiar with it, check out [getting_started](docs/en/getting_started.md) to try out MMFlow.

Refer to the below tutorials to dive deeper:

- [config](docs/en/tutorials/0_config.md)

- [model inference](docs/en/tutorials/1_inference.md)

- [fine tuning](docs/en/tutorials/2_finetune.md)

- [data pipeline](docs/en/tutorials/3_data_pipeline.md)

- [add new modules](docs/en/tutorials/4_new_modules.md)

- [customized runtime](docs/en/tutorials/5_customize_runtime.md)

## Benchmark and model zoo

Results and models are available in the [model zoo](docs/en/model_zoo.md).

Supported methods:

- [x] [FlowNet (ICCV'2015)](configs/flownet/README.md)
- [x] [FlowNet2 (CVPR'2017)](configs/flownet2/README.md)
- [x] [PWC-Net (CVPR'2018)](configs/pwcnet/README.md)
- [x] [LiteFlowNet (CVPR'2018)](configs/liteflownet/README.md)
- [x] [LiteFlowNet2 (TPAMI'2020)](configs/liteflownet2/README.md)
- [x] [IRR (CVPR'2019)](configs/irr/README.m

Excerpt of 7,327 characters

Read on GitHub

Top contributors12 shown

MeowZheng
Miao Zheng · OpenMMLab · China
109
Zachary-66
9
zhouzaida
Zaida Zhou
5
lhao0301
2
Weepingchestnut
1
lyq10085
1
Salvatore-tech
1
HiiiXinyiii
1
Fc-idris
1
SheffieldCao
Xu CAO · Tongji Univ · China
1
gaotongxiao
Tong Gao · Moonshot AI
1
ucalyptus2
1

Quality score

Would you bet a product on this? Bounded 0–100 and slow moving.

48/10048

Maintenance: 5%; How recently the default branch was pushed to
Releases: 10%; Recency and cadence of tagged releases
Community: 39%; Contributor breadth and bus factor
Issue backlog: 85%; Open issues measured against the size of the audience
Documentation: 96%; README depth, plus a homepage and topics
Licensing: 100%; How freely the code can be adopted

What to know before adopting

No commits in over a year
No release in over a year
Usable in commercial products with attribution.

Details

Created: 5 years ago
Last push: 2 years ago
Last release: 4 years ago
Release tag: v0.5.2
Releases in the last year: 0
Default branch: master
Size: 23k KB
Owner type: Organization
Owner location: China
Discovered via: topic:pytorch
First indexed: 13 days ago
Last synced: 12 days ago

open-mmlab/mmflow

OpenMMLab optical flow toolbox and benchmark

48Apache-2.0Python

View on GitHub Website

Stars: 1,060
Forks: 117
Watchers: 5
Open issues: 24
Contributors: 12

Star history, last 90 days— over 5 snapshots

2026-07-24 · 1,0602026-08-06 · 1,060

Star history, last 90 days
Date	Stars
2026-07-24	1060
2026-07-25	1060
2026-07-28	1060
2026-07-30	1060
2026-08-06	1060

Today

— stars today

This week

— stars this week

This month

— stars this month

Momentum

0.0

growth rate 0.00%/day

From the README

<div align="center">
  <img src="resources/mmflow-logo.png" width="600"/>
    <div>&nbsp;</div>
  <div align="center">
    <b><font size="5">OpenMMLab website</font></b>
    <sup>
      <a href="https://openmmlab.com">
        <i><font size="4">HOT</font></i>
      </a>
    </sup>
    &nbsp;&nbsp;&nbsp;&nbsp;
    <b><font size="5">OpenMMLab platform</font></b>
    <sup>
      <a href="https://platform.openmmlab.com">
        <i><font size="4">TRY IT OUT</font></i>
      </a>
    </sup>
  </div>
  <div>&nbsp;</div>

[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/mmflow)](https://pypi.org/project/mmflow/)
[![PyPI](https://img.shields.io/pypi/v/mmflow)](https://pypi.org/project/mmflow)
[![docs](https://img.shields.io/badge/docs-latest-blue)](https://mmflow.readthedocs.io/en/latest/)
[![badge](https://github.com/open-mmlab/mmflow/workflows/build/badge.svg)](https://github.com/open-mmlab/mmflow/actions)
[![codecov](https://codecov.io/gh/open-mmlab/mmflow/branch/master/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmflow)
[![license](https://img.shields.io/github/license/open-mmlab/mmflow.svg)](https://github.com/open-mmlab/mmflow/blob/master/LICENSE)
[![open issues](https://isitmaintained.com/badge/open/open-mmlab/mmflow.svg)](https://github.com/open-mmlab/mmflow/issues)

[📘Documentation](https://mmflow.readthedocs.io/en/latest/) |
[🛠️Installation](https://mmflow.readthedocs.io/en/latest/install.html) |
[👀Model Zoo](https://mmflow.readthedocs.io/en/latest/model_zoo.html) |
[🤔Reporting Issues](https://github.com/open-mmlab/mmflow/issues/new/choose)

</div>

<div align="center">

English | [简体中文](README_zh-CN.md)

</div>

## Introduction

MMFlow is an open source optical flow toolbox based on PyTorch. It is a part of the [OpenMMLab](https://openmmlab.com/) project.

The master branch works with **PyTorch 1.5+**.

<https://user-images.githubusercontent.com/76149310/141947796-af4f1e67-60c9-48ed-9dd6-fcd809a7d991.mp4>

### Major features

- **The First Unified Framework for Optical Flow**

  MMFlow is the first toolbox that provides a framework for unified implementation and evaluation of optical flow algorithms.

- **Flexible and Modular Design**

  We decompose the flow estimation framework into different components,
  which makes it much easy and flexible to build a new model by combining different modules.

- **Plenty of Algorithms and Datasets Out of the Box**

  The toolbox directly supports popular and contemporary optical flow models, *e.g.* FlowNet, PWC-Net, RAFT, etc,
  and representative datasets, FlyingChairs, FlyingThings3D, Sintel, KITTI, etc.

## What's New

**v0.5.2** was released in 01/10/2023:

- Add flow1d attention

Please refer to [changelog.md](docs/en/changelog.md) for details and release history.

## Installation

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

## Get Started

If you're new of optical flow, you can start with [learn the basics](docs/en/intro.md). If you’re familiar with it, check out [getting_started](docs/en/getting_started.md) to try out MMFlow.

Refer to the below tutorials to dive deeper:

- [config](docs/en/tutorials/0_config.md)

- [model inference](docs/en/tutorials/1_inference.md)

- [fine tuning](docs/en/tutorials/2_finetune.md)

- [data pipeline](docs/en/tutorials/3_data_pipeline.md)

- [add new modules](docs/en/tutorials/4_new_modules.md)

- [customized runtime](docs/en/tutorials/5_customize_runtime.md)

## Benchmark and model zoo

Results and models are available in the [model zoo](docs/en/model_zoo.md).

Supported methods:

- [x] [FlowNet (ICCV'2015)](configs/flownet/README.md)
- [x] [FlowNet2 (CVPR'2017)](configs/flownet2/README.md)
- [x] [PWC-Net (CVPR'2018)](configs/pwcnet/README.md)
- [x] [LiteFlowNet (CVPR'2018)](configs/liteflownet/README.md)
- [x] [LiteFlowNet2 (TPAMI'2020)](configs/liteflownet2/README.md)
- [x] [IRR (CVPR'2019)](configs/irr/README.m

Excerpt of 7,327 characters

Read on GitHub

Top contributors12 shown

MeowZheng
Miao Zheng · OpenMMLab · China
109
Zachary-66
9
zhouzaida
Zaida Zhou
5
lhao0301
2
Weepingchestnut
1
lyq10085
1
Salvatore-tech
1
HiiiXinyiii
1
Fc-idris
1
SheffieldCao
Xu CAO · Tongji Univ · China
1
gaotongxiao
Tong Gao · Moonshot AI
1
ucalyptus2
1

Quality score

Would you bet a product on this? Bounded 0–100 and slow moving.

48/10048

Maintenance: 5%; How recently the default branch was pushed to
Releases: 10%; Recency and cadence of tagged releases
Community: 39%; Contributor breadth and bus factor
Issue backlog: 85%; Open issues measured against the size of the audience
Documentation: 96%; README depth, plus a homepage and topics
Licensing: 100%; How freely the code can be adopted

What to know before adopting

No commits in over a year
No release in over a year
Usable in commercial products with attribution.

Details

Created: 5 years ago
Last push: 2 years ago
Last release: 4 years ago
Release tag: v0.5.2
Releases in the last year: 0
Default branch: master
Size: 23k KB
Owner type: Organization
Owner location: China
Discovered via: topic:pytorch
First indexed: 13 days ago
Last synced: 12 days ago

Top AI Repos — open-source AI, indexed and scored

open-mmlab/mmflow

From the README

Top contributors12 shown

Quality score

What to know before adopting

Categories

Details

open-mmlab/mmflow

From the README

Top contributors12 shown

Quality score

What to know before adopting

Categories

Details

Top AI Repos — open-source AI, indexed and scored

Trend

From the README

Top contributors12 shown

Quality score

What to know before adopting

Categories

Details

Trend

From the README

Top contributors12 shown

Quality score

What to know before adopting

Categories

Details