This repo contains sample files that implemented Conditiona GAN based on the machine-learining framework ‘jittor’, which is developed by Tsinghua University.(here is the github repo of jittor : https://github.com/Jittor/jittor) The provided file can produce hand-written number using the model.
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
A big thank to Tsinghua university and professor Hu, Shi-Min!
Conditional GAN
Description
This repo contains sample files that implemented Conditiona GAN based on the machine-learining framework ‘jittor’, which is developed by Tsinghua University.(here is the github repo of jittor : https://github.com/Jittor/jittor)
The provided file can produce hand-written number using the model.
Usage
安装jittor 参考：https://cg.cs.tsinghua.edu.cn/jittor/
在
CGAN.py中的number 改成（line:201）您想要的数字串。执行
即可生成想要的手写数字串。
默认epoch为100，batch size 为64。
*练数据集来自MNIST。
例子
输入 “13921891391015”，生成图像为如下
Contributing
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change. A big thank to Tsinghua university and professor Hu, Shi-Min!
License
This repo is covered under MIT.