Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/nashory/gans-collection.torch
Torch implementation of various types of GAN (e.g. DCGAN, ALI, Context-encoder, DiscoGAN, CycleGAN, EBGAN, LSGAN)
https://github.com/nashory/gans-collection.torch
adversarial ali context-encoder dcgan deep-learning gans generative-adversarial-network torch
Last synced: 4 months ago
JSON representation
Torch implementation of various types of GAN (e.g. DCGAN, ALI, Context-encoder, DiscoGAN, CycleGAN, EBGAN, LSGAN)
- Host: GitHub
- URL: https://github.com/nashory/gans-collection.torch
- Owner: nashory
- License: mit
- Created: 2017-09-13T01:38:07.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2017-10-14T14:42:00.000Z (over 6 years ago)
- Last Synced: 2024-01-08T00:13:57.031Z (6 months ago)
- Topics: adversarial, ali, context-encoder, dcgan, deep-learning, gans, generative-adversarial-network, torch
- Language: Lua
- Homepage:
- Size: 260 KB
- Stars: 55
- Watchers: 4
- Forks: 15
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Lists
- gans-awesome-applications - nashory/gans-collections.torch
- gans-awesome-applications - nashory/gans-collections.torch
- awesome-GAN-papers - 18
- gans-awesome-applications - nashory/gans-collections.torch
- gans-awesome-applications - nashory/gans-collections.torch
README
# gans-collection.torch
Torch implementation of various types of GANs (e.g. DCGAN, ALI, Context-encoder, DiscoGAN, CycleGAN, EBGAN).
__Note that EBGAN and BEGAN implementation is still not stable yet. I am working on this.__
## Contents
+ [DCGAN](https://arxiv.org/abs/1511.06434)
+ [Context-encoder](http://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Pathak_Context_Encoders_Feature_CVPR_2016_paper.html)
+ [ALI](https://arxiv.org/abs/1606.00704)
+ [DiscoGAN](https://arxiv.org/pdf/1703.05192.pdf)
+ [CycleGAN](https://arxiv.org/abs/1703.10593)
+ [Energy-Based GAN (EBGAN)](https://arxiv.org/pdf/1609.03126.pdf)
+ [LSGAN](https://arxiv.org/pdf/1611.04076.pdf)
## Prerequisites
+ Torch7
+ python2.7
+ cuda
+ other torch packages (display, hdf5, image ...)
## Usage
1. download training data:
~~~
python download.py --datasets
(e.g) python run.py --datasets celebA
---------------------------------------
The training data folder should look like :
|--classA
|--image1A
|--image2B ...
|--classB
|--image1B
|--image2B ...
---------------------------------------
~~~
2. run GANs training:
__Note that you need to change parameter options in "script/opts.lua" for each GANs.__
~~~
python run.py --type
(e.g) python run.py --type dcgan
~~~
## Display GUI : How to see generated images in real-time?
step by step instruction:
~~~
1. set server-related options(ip, port, etc.) in "script.opts.lua"
2. run server (python server.py --type )
3. open web browser, and connect. (https://:)
~~~
you will see like this:
## Results
|training|Final|
|---|---|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## Acknowledgement
+ brought dataloader code from ([DCGAN](https://github.com/soumith/dcgan.torch))
+ referenced the code from ([Context-encoder](https://github.com/pathak22/context-encoder))
## Author
MinchulShin, [@nashory](https://github.com/nashory)
__Will keep updating other types of GANs.__
__Any insane bug reports or questions are welcome. (min.stellastra[at]gmail.com) :-)__