This repository contains a collection of PyTorch-Lightning implementations of Score-based Generative Model presented in research papers. Contributions and suggestions of SBMs to implement are very welcomed.
- Python >= 3.8
- PyTorch >= 1.9
- Pytorch Lightning >= 1.4.8
- CUDA enabled computing device
git clone https://github.com/vrvrv/PyTorch-SBM
cd PyTorch-SBM
pip install -r requirements.txt
python run.py experiment=ddpm_cifar10
Denoising Diffusion Probabilistic Model
Jonathan Ho, Ajay Jain, Pieter Abbeel
python run.py experiment=ddpm_cifar10
Generative Modeling by Estimating Gradients of the Data Distribution
Yang Song, Stefano Ermon
python run.py experiment=ncsn_cifar10
Improved Techniques for Training Score-Based Generative Models
Yang Song, Stefano Ermon
python run.py experiment=ncsnv2_cifar10
Denoising Diffusion Implicit Model
Jiaming Song, Chenlin Meng, Stefano Ermon
python run.py experiment=ddim_cifar10
Score-Based Generative Modeling through Stochastic Differential Equations
Yang Song, Jashcha Sohl-Dickstein, Diederik P.Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole
python run.py experiment=score_sde_cifar10
We can calculate FID and IS score on each models
python test.py expeirment=ddpm_cifar10 trainer.resume_from_checkpoint=ddpm/cifar10_epoch53.ckpt
Model | FID | IS |
---|---|---|
DDPM | 0 | 0 |
NCSN | 0 | 0 |
NCSNV2 | 0 | 0 |
Score SDE | 0 | 0 |