Skip to content
/ mini_edm Public

Minimum implementation of EDM (Elucidating the Design Space of Diffusion-Based Generative Models) on cifar10 and mnist

arxiv.org/abs/2206.00364
51 stars 5 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

yuanzhi-zhu/mini_edm

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
figs
figs
 
 
.gitignore
.gitignore
 
 
README.md
README.md
 
 
networks_edm.py
networks_edm.py
 
 
requirements.txt
requirements.txt
 
 
run.sh
run.sh
 
 
sample_edm.py
sample_edm.py
 
 
train_edm.py
train_edm.py
 
 

Repository files navigation

Mini-EDM -- A minimalistic EDM with all the essence

Introduction

To train or evaluate the EDM, please follow the command in run.sh.

Results

Results FID on CIFAIR-10:

FID of this implementation.

Reference FID (each snapshot=5000k images=5000k/128 steps) from the original EDM codebase using the same model architecture and the same batch size of 128 (nothing else changed):

FID of original EDM.

The difference may come from the learning rate and warmup strategy.

About

Minimum implementation of EDM (Elucidating the Design Space of Diffusion-Based Generative Models) on cifar10 and mnist

arxiv.org/abs/2206.00364

Resources

Readme
Activity

Stars

51 stars

Watchers

2 watching

Forks

5 forks
Report repository

Languages