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+.
- High-quality Training Performance: We currently support training on Unconditional GANs, Internal GANs, and Image Translation Models. Support for conditional models will come soon.
- Powerful Application Toolkit: A plentiful toolkit containing multiple applications in GANs is provided to users. GAN interpolation, GAN projection, and GAN manipulations are integrated into our framework. It's time to play with your GANs! (Tutorial for applications)
- Efficient Distributed Training for Generative Models: For the highly dynamic training in generative models, we adopt a new way to train dynamic models with
MMDDP. (Tutorial for DDP)
- 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 new modular design)
- 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.
v0.3.0 was released on 02/08/2021. Please refer to changelog.md for details and release history.
These methods have been carefully studied and supported in our frameworks:
Unconditional GANs (click to collapse)
Conditional GANs (click to collapse)
Internal Learning (click to collapse)
- ✅ SinGAN (ICCV'2019)