漫画上色, 构建神经网络CGAN

CGAN之deepcolor实践 http://blog.csdn.net/kwame211/article/details/78203862?locationNum=4&fps=1

神经网络2. epoch, iteration, batchsize相关理解和说明

http://blog.csdn.net/qq_20259459/article/details/53943413

百行代码构建神经网络黑白图片自动上色系统


http://blog.csdn.net/uwr44uouqcnsuqb60zk2/article/details/78409868
github代码deepcolor
https://github.com/kvfrans/deepcolor

阅读文章:http://kvfrans.com/coloring-and-shading-line-art-automatically-through-conditional-gans/

尝试演示:http://color.kvfrans.com

安装程序

前提

Python 2.7,NumPy

- Tensorflow 0.12

OpenCV

运行它

1、make a folder called "results"    制作一个名为“results”的文件夹

2、make a folder called "imgs‘’    做一个文件夹名为“imgs

3、Fill the "imgs" folder with your own .jpg images, or run "download_images.py" to download from Safebooru.
     填补“imgs”文件夹你自己的JPG图像,或者运行“download_images .py”下载来自Safebooru。

4、Run "python main.py train". I trained for ~20 epochs, taking about 16 hours on one GPU.

         运行“ python main.py train”.           我训练了20个纪元,花了大约16个小时在一个GPU上。

5、To sample, run "python main.py sample"
     样本,运行“python main.py样本 

6、To start the server, run "python server.py". It will host on port 8000.
       要启动服务器,请运行“python server.py”。它将在8000端口上主机。

Pre-trained

前期的培训

得到的pretrained模型:

 https://drive.google.com/file/d/0BydPPLNieijIdDlUYWxhelEwRnM/view?usp=sharing

文件夹结构应该走

main.py
server.py
checkpoint/
    tr/
        checkpoint
        model-1101500.index
        model-1101500.data-00000-of-00001
        model-1101500.meta


你可能感兴趣的:(python3)