Code Monkey home page Code Monkey logo

gan-keras's Introduction

GAN生成对抗网络在Keras当中的实现


注意事项

该库上传时间较早,结构不明确且功能有限,本人进行了一定重置,重置后网络结构与功能会相对更好一些。

DCGAN:https://github.com/bubbliiiing/dcgan-keras
SRGAN:https://github.com/bubbliiiing/srgan-keras

目录

  1. 所需环境 Environment
  2. 仓库内容 WhatsIn
  3. 使用方法 Usage
  4. 参考资料 Reference

所需环境

tensorflow-gpu==1.13.1
keras==2.1.5

仓库内容

  • gan
  • dcgan
  • cgan
  • acgan
  • cogan
  • srgan
  • cyclegan-keras
  • cyclegan-pytorch

使用方法

acgan、cgan、gan、dcgan、cogan

这些gan直接运行其中的代码。

cycleGAN

1、下载数据集
这是斑马to黄种马的数据集下载:
https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/horse2zebra.zip
苹果to橘子数据集下载:
[https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/apple2orange.zip] (https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/apple2orange.zip)
画作to照片数据集下载:
https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/monet2photo.zip
2、将数据集解压后放入到dataset中
3、运行cyclegan.py进行训练

Reference

https://github.com/eriklindernoren/Keras-GAN
https://github.com/eriklindernoren/PyTorch-GAN

gan-keras's People

Contributors

bubbliiiing avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

gan-keras's Issues

ACGAN.save_model()

大哥,ACGAN里面那个模型该怎么才能保存下来?我是这样写的,
acgan = ACGAN(train_x, train_y) acgan.train(epochs=3, batch_size=64, sample_interval=200) acgan.save_model()
当程序运行到保存那一行程序直接崩溃了,不知道怎么才能把模型保存下来,并且能够加载出来。求指教

I got the following error when trying to use cyclegan. Could anyone help me? Thanks!

Traceback (most recent call last):
File "cyclegan.py", line 239, in
gan.train(init_epoch=0, epochs=200, batch_size=1, sample_interval=200)
File "cyclegan.py", line 160, in train
for batch_i, (imgs_A, imgs_B) in enumerate(self.data_loader.load_batch(batch_size)):
File "/data/home/TheBigDrive/Allergan/MYe/GAN/GAN-keras/cyclegan/data_loader.py", line 40, in load_batch
path_A = np.random.choice(path_A, total_samples, replace=False)
File "mtrand.pyx", line 1126, in mtrand.RandomState.choice
ValueError: a must be non-empty

SRGAN复原效果的问题

在CSDN看到您的博客,请问为什么您的SRGAN复原效果这么好(甚至好于后来ESRGAN),是因为对数据插值使用的是nearest吗?

SRGAN

SRGAN有两个问题想请教:1,想要训练灰度图像数据集应该怎么修改呢? 2,低分辨率的图像是怎么得来的呢? 感谢~

环境的版本问题

这个除了作者说的版本,其他俺的tf,keras的版本可以实现吗?

srgan-问题

博主,我想问下,如果我图片样本数量比较少才480张每张800x800大小的,测试的结果不太好,该往什么方向改进才能怎么提升呢?

srgan 如何生成高分辨率的图片

感谢你的源码,非常的棒,给了我很大的指导作用。我在学习srgan的时候,也找了很多的资源,我现在有一个图片,也有了现成的model,我发现通过srgan的模型直接进行运算,图片最后的结果并没有预想的效果那么好。这是为什么呢,是不是我需要对我的图片进行处理呢?多谢你的回答。。。
https://github.com/dongheehand/SRGAN-PyTorch
https://github.com/krasserm/super-resolution

预训练模型

作者大大,请问有cyclegan训练好的的预训练模型吗?

gan怎么实现水下图片的图像增强呢?

好多水下目标检测的项目一般都会对原始的图像做一些图像增强,目的是把图片质量提上去这样有助于后续的目标检测任务,那我想请问gan怎样实现水下图像增强呢?我的数据集除了要有水下图像,还要准备什么

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.