Skip to content

yyotta/GAN-CBAM-SENet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Introduction

It is a GAN embedded with CBAM and SENet. We trained it on mnist, fashion-mnist and a dataset of anime faces.

Performance

On mnist dataset:

mnist

On fashion-mnist dataset:

fashion-mnist

On anime faces dataset:

anime-faces

Architecture

arch discriminator generator

Requirement

  • Linux
  • Python 3.x
  • Pytorch 1.11.0

Download dataset

Download anime faces dataset

Unzip and move it into : ./data/dataset_anime/data/faces

Quick Start

Train the model:

nohup bash train.sh > ./logs/res.txt 2> ./logs/err.txt &

or:

python train.py --dataset mnist --gan_type gan --epoch 50 --batch_size 64 --use_cuda True

The result will be saved in ./results/

About

GAN embedded with CBAM and SENet.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published