Pytorch-diffusion - A basic PyTorch implementation of 'Denoising Diffusion Probabilistic Models'

Arthur Juliani

Last update: Jan 7, 2023

Related tags

Deep Learning pytorch-diffusion

Overview

PyTorch implementation of 'Denoising Diffusion Probabilistic Models'

This repository contains my attempt at reimplementing the main algorithm and model presenting in Denoising Diffusion Probabilistic Models, the recent paper by Ho et al., 2020. A nice summary of the paper by the authors is available here.

This implementation uses pytorch lightning to limit the boilerplate as much as possible. Due to time and computational constraints, I only experimented with 32x32 image datasets, but it should scale up to larger datasets like LSUN and CelebA as demonstrated in the original paper. This implementation was done for my own self-education, and hopefully it can help others learn as well.

Use the provided entry.ipynb notebook to train model and sample generated images.

Supports MNIST, Fashion-MNIST and CIFAR datasets.

Requirements

PyTorch
PyTorch-Lightning
Torchvision
imageio (for gif generation)

Generated Images

MNIST

Fashion-MNIST

CIFAR

a basic code repository for basic task in CV(classification,detection,segmentation)

basic_cv a basic code repository for basic task in CV(classification,detection,segmentation,tracking) classification generate dataset train predict de

1 Oct 15, 2021

Adversarial Attacks on Probabilistic Autoregressive Forecasting Models.

Attack-Probabilistic-Models This is the source code for Adversarial Attacks on Probabilistic Autoregressive Forecasting Models. This repository contai

25 Sep 14, 2022

Official implementation of Deep Convolutional Dictionary Learning for Image Denoising.

DCDicL for Image Denoising Hongyi Zheng*, Hongwei Yong*, Lei Zhang, "Deep Convolutional Dictionary Learning for Image Denoising," in CVPR 2021. (* Equ

91 Dec 21, 2022

Implementation of Common Image Evaluation Metrics by Sayed Nadim (sayednadim.github.io). The repo is built based on full reference image quality metrics such as L1, L2, PSNR, SSIM, LPIPS. and feature-level quality metrics such as FID, IS. It can be used for evaluating image denoising, colorization, inpainting, deraining, dehazing etc. where we have access to ground truth.

Image Quality Evaluation Metrics Implementation of some common full reference image quality metrics. The repo is built based on full reference image q

10 Jan 1, 2023

This is an official implementation of the CVPR2022 paper "Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots".

Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots Blind2Unblind Citing Blind2Unblind @inproceedings{wang2022blind2unblind, tit

58 Dec 6, 2022

Implementation based on Paper - Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

3 Jul 8, 2022

Implementation of the final project of the course DDA6309 Probabilistic Graphical Model

Task-aware Joint CWS and POS (TCwsPos) This is the implementation of the final project of the course DDA6309 Probabilistic Graphical Models, The Chine

1 Dec 26, 2021

Pseudo-Visual Speech Denoising

Pseudo-Visual Speech Denoising This code is for our paper titled: Visual Speech Enhancement Without A Real Visual Stream published at WACV 2021. Autho

94 Oct 22, 2022

EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising

EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising By Tengfei Liang, Yi Jin, Yidong Li, Tao Wang. Th

115 Jan 5, 2023

Comments

Wondering about attention

First of all - Thanks for the great implementation, which is very readable and simple to use and reach quick results with.

I noticed you're using the self attention in a different manner than the one written by Ho et al - they used the self attention in the 16x16 resolution layers in the network (both for 32x32 and 256x256 inputs) while you used it in the 8x8 resolution layers in the U-Net. Did you just happen to use it there / was there some guiding logic behind it?

opened by yanivnik 1

Owner

Arthur Juliani

GitHub

Pytorch-diffusion - A basic PyTorch implementation of 'Denoising Diffusion Probabilistic Models'

Related tags

Overview

PyTorch implementation of 'Denoising Diffusion Probabilistic Models'

Requirements

Generated Images

MNIST

Fashion-MNIST

CIFAR

You might also like...

a basic code repository for basic task in CV(classification,detection,segmentation)

Adversarial Attacks on Probabilistic Autoregressive Forecasting Models.

Official implementation of Deep Convolutional Dictionary Learning for Image Denoising.

This is an official implementation of the CVPR2022 paper "Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots".

Implementation based on Paper - Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

Implementation of the final project of the course DDA6309 Probabilistic Graphical Model

Pseudo-Visual Speech Denoising

EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising

Comments

Wondering about attention

Owner

Arthur Juliani

Implementation of Retrieval-Augmented Denoising Diffusion Probabilistic Models in Pytorch

Denoising Diffusion Probabilistic Models

ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models (ICCV 2021 Oral)

A denoising diffusion probabilistic model (DDPM) tailored for conditional generation of protein distograms

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

BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis

PyTorch Implementation of DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs

Pytorch implementation of "Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech"

NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling

NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling @ INTERSPEECH 2021 Accepted