资 源 简 介
# Generative Adversarial Nets for Matlab
only class 2 with GAN
![](https://github.com/layumi/2016_GAN_Matlab/blob/master/show.png)
class 0-9 with infoGAN
![](https://github.com/layumi/2016_GAN_Matlab/blob/master/show2.png)
I use feature matching to train Generative model. (I define this Loss in the `/matlab/+dagnn/Feature_Match_Loss.m`)
1.Compile matconvnet by run `gpu_compile.m` which you should remove comment in it.
2.You can test this code by run `test_gan_3.m` or `test_gan_info.m`
3.If you wanna train this code, you can run `train_gan_3.m` or `train_gan_info.m`
You can find the network structure in `GDnet_3.m` and `GDnet_info.m`
# Some Details
1.I may miss some thing or not select a good initial parameter. So any advice is welcome.
文 件 列 表
2016_GAN_Matlab-master
.gitattributes
.gitignore
.gitmodules
CONTRIBUTING.md
COPYING
GDnet.m
GDnet_2.m
GDnet_3.m
GDnet_info.m
Makefile
README.md
doc
draw
examples
gpu_compile.m
matconvnet.sln
matconvnet.vcxproj
matconvnet.vcxproj.filters
matconvnet.xcodeproj
matlab
minist_data.mat
minist_data
minist_data_only2.mat
prepare_minist_GAN.m
rand_same_class.m
rename_copy
scale_minist.m
show.png
show2.png
start-zzd.sh
test_gan.m
test_gan_2.m
test_gan_3.m
test_gan_info.m
train_gan.m
train_gan_2.m
train_gan_3.m
train_gan_info.m
utils
vlfeat