A minimalist implementation of score-based diffusion model

Overview

sdeflow-light

This is a minimalist codebase for training score-based diffusion models (supporting MNIST and CIFAR-10) used in the following paper

"A Variational Perspective on Diffusion-Based Generative Models and Score Matching" by Chin-Wei Huang, Jae Hyun Lim and Aaron Courville [arXiv]

Also see the concurrent work by Yang Song & Conor Durkan where they used the same idea to obtain state-of-the-art likelihood estimates.

Experiments on Swissroll

Here's a Colab notebook which contains an example for training a model on the Swissroll dataset.

Open In Colab

In this notebook, you'll see how to train the model using score matching loss, how to evaluate the ELBO of the plug-in reverse SDE, and how to sample from it. It also includes a snippet to sample from a family of plug-in reverse SDEs (parameterized by λ) mentioned in Appendix C of the paper.

Below are the trajectories of λ=0 (the reverse SDE used in Song et al.) and λ=1 (equivalent ODE) when we plug in the learned score / drift function. This corresponds to Figure 5 of the paper. drawing drawing

Experiments on MNIST and CIFAR-10

This repository contains one main training loop (train_img.py). The model is trained to minimize the denoising score matching loss by calling the .dsm(x) loss function, and evaluated using the following ELBO, by calling .elbo_random_t_slice(x)

score-elbo

where the divergence (sum of the diagonal entries of the Jacobian) is estimated using the Hutchinson trace estimator.

It's a minimalist codebase in the sense that we do not use fancy optimizer (we only use Adam with the default setup) or learning rate scheduling. We use the modified U-net architecture from Denoising Diffusion Probabilistic Models by Jonathan Ho.

A key difference from Song et al. is that instead of parameterizing the score function s, here we parameterize the drift term a (where they are related by a=gs and g is the diffusion coefficient). That is, a is the U-net.

Parameterization: Our original generative & inference SDEs are

  • dX = mu dt + sigma dBt
  • dY = (-mu + sigma*a) ds + sigma dBs

We reparameterize it as

  • dX = (ga - f) dt + g dBt
  • dY = f ds + g dBs

by letting mu = ga - f, and sigma = g. (since f and g are fixed, we only have one degree of freedom, which is a). Alternatively, one can parameterize s (e.g. using the U-net), and just let a=gs.

How it works

Here's an example command line for running an experiment

python train_img.py --dataroot=[DATAROOT] --saveroot=[SAVEROOT] --expname=[EXPNAME] \
    --dataset=cifar --print_every=2000 --sample_every=2000 --checkpoint_every=2000 --num_steps=1000 \
    --batch_size=128 --lr=0.0001 --num_iterations=100000 --real=True --debias=False

Setting --debias to be False uses uniform sampling for the time variable, whereas setting it to be True uses a non-uniform sampling strategy to debias the gradient estimate described in the paper. Below are the bits-per-dim and the corresponding standard error of the test set recorded during training (orange for --debias=True and blue for --debias=False).

drawing drawing

Here are some samples (debiased on the right)

drawing drawing

It takes about 14 hrs to finish 100k iterations on a V100 GPU.

Owner
Chin-Wei Huang
Chin-Wei Huang
This project provides a stock market environment using OpenGym with Deep Q-learning and Policy Gradient.

Stock Trading Market OpenAI Gym Environment with Deep Reinforcement Learning using Keras Overview This project provides a general environment for stoc

Kim, Ki Hyun 769 Dec 25, 2022
ScaleNet: A Shallow Architecture for Scale Estimation

ScaleNet: A Shallow Architecture for Scale Estimation Repository for the code of ScaleNet paper: "ScaleNet: A Shallow Architecture for Scale Estimatio

Axel Barroso 34 Nov 09, 2022
Apply AnimeGAN-v2 across frames of a video clip

title emoji colorFrom colorTo sdk app_file pinned AnimeGAN-v2 For Videos 🔥 blue red gradio app.py false AnimeGAN-v2 For Videos Apply AnimeGAN-v2 acro

Nathan Raw 36 Oct 18, 2022
Our implementation used for the MICCAI 2021 FLARE Challenge titled 'Efficient Multi-Organ Segmentation Using SpatialConfiguartion-Net with Low GPU Memory Requirements'.

Efficient Multi-Organ Segmentation Using SpatialConfiguartion-Net with Low GPU Memory Requirements Our implementation used for the MICCAI 2021 FLARE C

Franz Thaler 3 Sep 27, 2022
Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learning

MSVCL_MICCAI2021 Installation Please follow the instruction in pytorch-CycleGAN-and-pix2pix to install. Example Usage An example of vendor-styles tran

Jaron Lee 11 Oct 19, 2022
[ACMMM 2021 Oral] Enhanced Invertible Encoding for Learned Image Compression

InvCompress Official Pytorch Implementation for "Enhanced Invertible Encoding for Learned Image Compression", ACMMM 2021 (Oral) Figure: Our framework

96 Nov 30, 2022
An Ensemble of CNN (Python 3.5.1 Tensorflow 1.3 numpy 1.13)

An Ensemble of CNN (Python 3.5.1 Tensorflow 1.3 numpy 1.13)

0 May 06, 2022
A simple implementation of Kalman filter in single object tracking

kalman-filter-in-single-object-tracking A simple implementation of Kalman filter in single object tracking https://www.bilibili.com/video/BV1Qf4y1J7D4

130 Dec 26, 2022
Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

News! Aug 2020: v0.4.0 version of AlphaPose is released! Stronger tracking! Include whole body(face,hand,foot) keypoints! Colab now available. Dec 201

Machine Vision and Intelligence Group @ SJTU 6.7k Dec 28, 2022
User-friendly bulk RNAseq deconvolution using simulated annealing

Welcome to cellanneal - The user-friendly application for deconvolving omics data sets. cellanneal is an application for deconvolving biological mixtu

11 Dec 16, 2022
AlphaBot2 Pi Core software for interfacing with the various components.

AlphaBot2-Pi-Core AlphaBot2 Pi Core software for interfacing with the various components. This project is currently a W.I.P. I will update this readme

KyleDev 1 Feb 13, 2022
The original weights of some Caffe models, ported to PyTorch.

pytorch-caffe-models This repo contains the original weights of some Caffe models, ported to PyTorch. Currently there are: GoogLeNet (Going Deeper wit

Katherine Crowson 9 Nov 04, 2022
Keras Image Embeddings using Contrastive Loss

Keras-Image-Embeddings-using-Contrastive-Loss Image to Embedding projection in vector space. Implementation in keras and tensorflow for custom data. B

Shravan Anand K 5 Mar 21, 2022
Code for Fully Context-Aware Image Inpainting with a Learned Semantic Pyramid

SPN: Fully Context-Aware Image Inpainting with a Learned Semantic Pyramid Code for Fully Context-Aware Image Inpainting with a Learned Semantic Pyrami

12 Jun 27, 2022
Predict Breast Cancer Wisconsin (Diagnostic) using Naive Bayes

Naive-Bayes Predict Breast Cancer Wisconsin (Diagnostic) using Naive Bayes Downloading Data Set Use our Breast Cancer Wisconsin Data Set Also you can

Faeze Habibi 0 Apr 06, 2022
Hl classification bc - A Network-Based High-Level Data Classification Algorithm Using Betweenness Centrality

A Network-Based High-Level Data Classification Algorithm Using Betweenness Centr

Esteban Vilca 3 Dec 01, 2022
4D Human Body Capture from Egocentric Video via 3D Scene Grounding

4D Human Body Capture from Egocentric Video via 3D Scene Grounding [Project] [Paper] Installation: Our method requires the same dependencies as SMPLif

Miao Liu 37 Nov 08, 2022
Source code for our Paper "Learning in High-Dimensional Feature Spaces Using ANOVA-Based Matrix-Vector Multiplication"

NFFT4ANOVA Source code for our Paper "Learning in High-Dimensional Feature Spaces Using ANOVA-Based Matrix-Vector Multiplication" This package uses th

Theresa Wagner 1 Aug 10, 2022
We envision models that are pre-trained on a vast range of domain-relevant tasks to become key for molecule property prediction

We envision models that are pre-trained on a vast range of domain-relevant tasks to become key for molecule property prediction. This repository aims to give easy access to state-of-the-art pre-train

GMUM 90 Jan 08, 2023
Local Attention - Flax module for Jax

Local Attention - Flax Autoregressive Local Attention - Flax module for Jax Install $ pip install local-attention-flax Usage from jax import random fr

Phil Wang 16 Jun 16, 2022