MMGeneration
Project description
📘Documentation | 🛠️Installation | 👀Model Zoo | 🆕Update News | 🚀Ongoing Projects | 🤔Reporting Issues
English | 简体中文
Introduction
MMGeneration is a powerful toolkit for generative models, especially for GANs now. It is based on PyTorch and MMCV. The master branch works with PyTorch 1.5+.
Major Features
- High-quality Training Performance: MMGeneration currently support training on Unconditional GANs, Conditional GANs, Internal GANs, Image Translation Models, and Diffusion Models.
- Powerful Application Toolkit: A toolkit that provides plentiful applications to users. MMGeneration supports GAN interpolation, GAN projection, GAN manipulations and many other popular GAN's applications. It's time to play with your GANs! (Tutorial for applications)
- Efficient Distributed Training for Generative Models: With support of MMSeparateDistributedDataParallel, distributed training for dynamic architectures can be easily implemented.
- New Modular Design for Flexible Combination: A new design for complex loss modules is proposed for customizing the links between modules, which can achieve flexible combination among different modules.(Tutorial for losses)
Training Visualization
|
GAN Interpolation
|
GAN Projector
|
GAN Manipulation
|
Highlight
- Positional Encoding as Spatial Inductive Bias in GANs (CVPR2021) has been released in
MMGeneration
. [Config], [Project Page] - Conditional GANs have been supported in our toolkit. More methods and pre-trained weights will come soon.
- Mixed-precision training (FP16) for StyleGAN2 has been supported. Please check the comparison between different implementations.
What's new
v1.0.0rc0 was released in 31/8/2022.
This release introduced a brand new and flexible training & test engine, but it's still in progress. Welcome to try according to the documentation.
And there are some BC-breaking changes. Please check the migration tutorial.
The release candidate will last until the end of 2022, and during the release candidate, we will develop on the 1.x
branch. And we will still maintain 0.x version still at least the end of 2023.
Please refer to changelog.md for more details and other release history.
Installation
MMGeneration depends on PyTorch and MMCV. Below are quick steps for installation.
Step 1. Install PyTorch following official instructions, e.g.
pip3 install torch torchvision
Step 2. Install MMCV with MIM.
pip install -U openmim
# wait for more pre-compiled pkgs to release
mim install 'mmcv>=2.0.0rc1'
Step 3. Install MMGeneration from source.
git clone -b 1.x https://github.com/open-mmlab/mmgeneration.git
cd mmgeneration
pip3 install -e .[all]
Please refer to get_started.md for more detailed instruction.
Getting Started
Please see get_started.md for the basic usage of MMGeneration. For other details and tutorials, please go to our documentation.
ModelZoo
These methods have been carefully studied and supported in our frameworks:
Unconditional GANs (click to collapse)
- ✅ DCGAN (ICLR'2016)
- ✅ WGAN-GP (NIPS'2017)
- ✅ LSGAN (ICCV'2017)
- ✅ GGAN (arXiv'2017)
- ✅ PGGAN (ICLR'2018)
- ✅ StyleGANV1 (CVPR'2019)
- ✅ StyleGANV2 (CVPR'2020)
- ✅ StyleGANV3 (NeurIPS'2021)
- ✅ Positional Encoding in GANs (CVPR'2021)
Conditional GANs (click to collapse)
- ✅ SNGAN (ICLR'2018)
- ✅ Projection GAN (ICLR'2018)
- ✅ SAGAN (ICML'2019)
- ✅ BIGGAN/BIGGAN-DEEP (ICLR'2019)
Internal Learning (click to collapse)
- ✅ SinGAN (ICCV'2019)
Denoising Diffusion Probabilistic Models (click to collapse)
- ✅ Improved DDPM (arXiv'2021)
Related-Applications
Contributing
We appreciate all contributions to improve MMGeneration. Please refer to CONTRIBUTING.md in MMCV and [https://github.com/open-mmlab/mmengine/blob/main/CONTRIBUTING.md\] in MMEngine for more details about the contributing guideline.
Citation
If you find this project useful in your research, please consider cite:
@misc{2021mmgeneration,
title={{MMGeneration}: OpenMMLab Generative Model Toolbox and Benchmark},
author={MMGeneration Contributors},
howpublished = {\url{https://github.com/open-mmlab/mmgeneration}},
year={2021}
}
License
This project is released under the Apache 2.0 license. Some operations in MMGeneration
are with other licenses instead of Apache2.0. Please refer to LICENSES.md for the careful check, if you are using our code for commercial matters.
Projects in OpenMMLab 2.0
- MMEngine: OpenMMLab foundational library for training deep learning models.
- MMCV: OpenMMLab foundational library for computer vision.
- MIM: MIM installs OpenMMLab packages.
- MMClassification: OpenMMLab image classification toolbox and benchmark.
- MMDetection: OpenMMLab detection toolbox and benchmark.
- MMDetection3D: OpenMMLab's next-generation platform for general 3D object detection.
- MMRotate: OpenMMLab rotated object detection toolbox and benchmark.
- MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark.
- MMOCR: OpenMMLab text detection, recognition, and understanding toolbox.
- MMPose: OpenMMLab pose estimation toolbox and benchmark.
- MMHuman3D: OpenMMLab 3D human parametric model toolbox and benchmark.
- MMSelfSup: OpenMMLab self-supervised learning toolbox and benchmark.
- MMRazor: OpenMMLab model compression toolbox and benchmark.
- MMFewShot: OpenMMLab fewshot learning toolbox and benchmark.
- MMAction2: OpenMMLab's next-generation action understanding toolbox and benchmark.
- MMTracking: OpenMMLab video perception toolbox and benchmark.
- MMFlow: OpenMMLab optical flow toolbox and benchmark.
- MMEditing: OpenMMLab image and video editing toolbox.
- MMGeneration: OpenMMLab image and video generative models toolbox.
- MMDeploy: OpenMMLab model deployment framework.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for mmgen-1.0.0rc0-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6ddc7bb7b7970b863e699e3c43687af74cd86a5b1865d7a45d67ce3835f95b18 |
|
MD5 | 717fc56f3faff54357fcbda4aa8475fa |
|
BLAKE2b-256 | 05930e0c379b3e5d1ee769ed1992a9e242e5e32dbc56d4c307a7132e7d1df680 |