Official PyTorch implementation for FastDPM, a fast sampling algorithm for diffusion probabilistic models

Related tags

Deep LearningFastDPM_pytorch
Overview

Official PyTorch implementation for "On Fast Sampling of Diffusion Probabilistic Models".

FastDPM generation on CIFAR-10, CelebA, and LSUN datasets. See paper via this link.

Pretrained models

Download checkpoints from this link and this link. Put them under checkpoints\ema_diffusion_${dataset_name}_model\model.ckpt, where ${dataset_name} is cifar10, celeba64, lsun_bedroom, lsun_church, or lsun_cat.

Usage

General command: python generate.py -ema -name ${dataset_name} -approxdiff ${approximate_diffusion_process} -kappa ${kappa} -S ${FastDPM_length} -schedule ${noise_level_schedule} -n ${number_to_generate} -bs ${batchsize} -gpu ${gpu_index}

  • ${dataset_name}: cifar10, celeba64, lsun_bedroom, lsun_church, or lsun_cat
  • ${approximate_diffusion_process}: VAR or STEP
  • ${kappa}: a real value between 0 and 1
  • ${FastDPM_length}: an integer between 1 and 1000; 10, 20, 50, 100 used in paper.
  • ${noise_level_schedule}: linear or quadratic

CIFAR-10

Below are commands to generate CIFAR-10 images.

  • Standard DDPM generation: python generate.py -ema -name cifar10 -approxdiff STD -n 16 -bs 16
  • FastDPM generation (STEP + DDPM-rev): python generate.py -ema -name cifar10 -approxdiff STEP -kappa 1.0 -S 50 -schedule quadratic -n 16 -bs 16
  • FastDPM generation (STEP + DDIM-rev): python generate.py -ema -name cifar10 -approxdiff STEP -kappa 0.0 -S 50 -schedule quadratic -n 16 -bs 16
  • FastDPM generation (VAR + DDPM-rev): python generate.py -ema -name cifar10 -approxdiff VAR -kappa 1.0 -S 50 -schedule quadratic -n 16 -bs 16
  • FastDPM generation (VAR + DDIM-rev): python generate.py -ema -name cifar10 -approxdiff VAR -kappa 0.0 -S 50 -schedule quadratic -n 16 -bs 16

CelebA

Below are commands to generate CelebA images.

  • Standard DDPM generation: python generate.py -ema -name celeba64 -approxdiff STD -n 16 -bs 16
  • FastDPM generation (STEP + DDPM-rev): python generate.py -ema -name celeba64 -approxdiff STEP -kappa 1.0 -S 50 -schedule linear -n 16 -bs 16
  • FastDPM generation (STEP + DDIM-rev): python generate.py -ema -name celeba64 -approxdiff STEP -kappa 0.0 -S 50 -schedule linear -n 16 -bs 16
  • FastDPM generation (VAR + DDPM-rev): python generate.py -ema -name celeba64 -approxdiff VAR -kappa 1.0 -S 50 -schedule linear -n 16 -bs 16
  • FastDPM generation (VAR + DDIM-rev): python generate.py -ema -name celeba64 -approxdiff VAR -kappa 0.0 -S 50 -schedule linear -n 16 -bs 16

LSUN_bedroom

Below are commands to generate LSUN bedroom images.

  • Standard DDPM generation: python generate.py -ema -name lsun_bedroom -approxdiff STD -n 8 -bs 8
  • FastDPM generation (STEP + DDPM-rev): python generate.py -ema -name lsun_bedroom -approxdiff STEP -kappa 1.0 -S 50 -schedule linear -n 8 -bs 8
  • FastDPM generation (STEP + DDIM-rev): python generate.py -ema -name lsun_bedroom -approxdiff STEP -kappa 0.0 -S 50 -schedule linear -n 8 -bs 8
  • FastDPM generation (VAR + DDPM-rev): python generate.py -ema -name lsun_bedroom -approxdiff VAR -kappa 1.0 -S 50 -schedule linear -n 8 -bs 8
  • FastDPM generation (VAR + DDIM-rev): python generate.py -ema -name lsun_bedroom -approxdiff VAR -kappa 0.0 -S 50 -schedule linear -n 8 -bs 8

Note

To generate 50K samples, set -n 50000 and batchsize (-bs) divisible by 50K.

Compute FID

To compute FID of generated samples, first make sure there are 50K images, and then run

  • python FID.py -ema -name cifar10 -approxdiff STEP -kappa 1.0 -S 50 -schedule quadratic

Code References

Owner
Zhifeng Kong
Ph.D. student, UCSD
Zhifeng Kong
GitHub Repository
Neural Style and MSG-Net

PyTorch-Style-Transfer This repo provides PyTorch Implementation of MSG-Net (ours) and Neural Style (Gatys et al. CVPR 2016), which has been included

Hang Zhang 904 Dec 21, 2022
Continual reinforcement learning baselines: experiment specifications, implementation of existing methods, and common metrics. Easily extensible to new methods.

Continual Reinforcement Learning This repository provides a simple way to run continual reinforcement learning experiments in PyTorch, including evalu

55 Dec 24, 2022
A modern pure-Python library for reading PDF files

pdf A modern pure-Python library for reading PDF files. The goal is to have a modern interface to handle PDF files which is consistent with itself and

6 Apr 06, 2022
PyTorch code of "SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks"

SLAPS-GNN This repo contains the implementation of the model proposed in SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks

60 Dec 22, 2022
Semantic Image Synthesis with SPADE

Semantic Image Synthesis with SPADE New implementation available at imaginaire repository We have a reimplementation of the SPADE method that is more

NVIDIA Research Projects 7.3k Jan 07, 2023
A dataset for online Arabic calligraphy

Calliar Calliar is a dataset for Arabic calligraphy. The dataset consists of 2500 json files that contain strokes manually annotated for Arabic callig

ARBML 114 Dec 28, 2022
functorch is a prototype of JAX-like composable function transforms for PyTorch.

functorch is a prototype of JAX-like composable function transforms for PyTorch.

Facebook Research 1.2k Jan 09, 2023
EfficientDet (Scalable and Efficient Object Detection) implementation in Keras and Tensorflow

EfficientDet This is an implementation of EfficientDet for object detection on Keras and Tensorflow. The project is based on the official implementati

1.3k Dec 19, 2022
Implementation of STAM (Space Time Attention Model), a pure and simple attention model that reaches SOTA for video classification

STAM - Pytorch Implementation of STAM (Space Time Attention Model), yet another pure and simple SOTA attention model that bests all previous models in

Phil Wang 109 Dec 28, 2022
Replication package for the manuscript "Using Personality Detection Tools for Software Engineering Research: How Far Can We Go?" submitted to TOSEM

tosem2021-personality-rep-package Replication package for the manuscript "Using Personality Detection Tools for Software Engineering Research: How Far

Collaborative Development Group 1 Dec 13, 2021
Implementation of Geometric Vector Perceptron, a simple circuit for 3d rotation equivariance for learning over large biomolecules, in Pytorch. Idea proposed and accepted at ICLR 2021

Geometric Vector Perceptron Implementation of Geometric Vector Perceptron, a simple circuit with 3d rotation equivariance for learning over large biom

Phil Wang 59 Nov 24, 2022
A tight inclusion function for continuous collision detection

Tight-Inclusion Continuous Collision Detection A conservative Continuous Collision Detection (CCD) method with support for minimum separation. You can

Continuous Collision Detection 89 Jan 01, 2023
Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

Official repository of OFA. Paper: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

OFA Sys 1.4k Jan 08, 2023
An implementation demo of the ICLR 2021 paper Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks in PyTorch.

Neural Attention Distillation This is an implementation demo of the ICLR 2021 paper Neural Attention Distillation: Erasing Backdoor Triggers from Deep

Yige-Li 84 Jan 04, 2023
DeepStruc is a Conditional Variational Autoencoder which can predict the mono-metallic nanoparticle from a Pair Distribution Function.

ChemRxiv | [Paper] XXX DeepStruc Welcome to DeepStruc, a Deep Generative Model (DGM) that learns the relation between PDF and atomic structure and the

Emil Thyge Skaaning Kjær 13 Aug 01, 2022
RoIAlign & crop_and_resize for PyTorch

RoIAlign for PyTorch This is a PyTorch version of RoIAlign. This implementation is based on crop_and_resize and supports both forward and backward on

Long Chen 530 Jan 07, 2023
Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features

MediumVC MediumVC is an utterance-level method towards any-to-any VC. Before that, we propose SingleVC to perform A2O tasks(Xi → Ŷi) , Xi means utter

谷下雨 47 Dec 25, 2022
Deep metric learning methods implemented in Chainer

Deep Metric Learning Implementation of several methods for deep metric learning in Chainer v4.2.0. Proxy-NCA: No Fuss Distance Metric Learning using P

ronekko 156 Nov 28, 2022
PyTorch Implementation of CvT: Introducing Convolutions to Vision Transformers

CvT: Introducing Convolutions to Vision Transformers Pytorch implementation of CvT: Introducing Convolutions to Vision Transformers Usage: img = torch

Rishikesh (ऋषिकेश) 193 Jan 03, 2023
Sinkformers: Transformers with Doubly Stochastic Attention

Code for the paper : "Sinkformers: Transformers with Doubly Stochastic Attention" Paper You will find our paper here. Compat This package has been dev

Michael E. Sander 31 Dec 29, 2022