Coder Social home page Coder Social logo

keras-acgan-cifar10's Introduction

Keras-ACGAN-CIFAR10

Code Modified from https://github.com/lukedeo/keras-acgan,
This is CIFAR10 version. Some interesting tricks refers to Soumith Chintala ganhacks(https://github.com/soumith/ganhacks).
I directly use the Minibatch Layer Code from:
https://github.com/forcecore/Keras-GAN-Animeface-Character
Thanks for the great work!
Any suggestion is welcomed!
This is one of generated images after 50 epochs:  

This is one of generated images after 200 epochs:  
This is Discriminator Classification Result for Cifar-10 test dataset after 200 epochs(Confusion Matrix, Accurancy: 71.89%)  

keras-acgan-cifar10's People

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

Watchers

 avatar  avatar

keras-acgan-cifar10's Issues

生成图片全灰色

您好,我生成的图片全部是灰色的,并且我打印了代码中的generated_images参数,发现全都是e-3次方量级,请问这是什么原因呢?我对代码的改动只限于一些版本问题导致import的替换,尝试改小学习率也没有效果。如果您能抽空回复我,我将十分感激

mini batch discrimination hyperparameters

as i see, you call MinibatchDiscrimination(50, 30) in order to implement discrimination. Are these parameters 50 and 30 related with image size, etc. or completely arbitrary? thanks...

你好

你好,看到你目前研究的项目,想跟你交流一下

image extraction

thank for your awesome work, after whole training complete how can i generate examples and save them one by one. thanks...

Reproducing the results in this repository

Hello.

I've been trying to reproduce the results shown in the README file.
I have used your code, as is, and ran it multiple times but the images generated where never close to the ones in the README.

Here's an example of my results by epoch 20:
results

Do you have any idea why I'm failing to achieve the same results you did, or is there any tip you could give to help me?

Thank you in advance!

A problem about your code

y_real = np.random.uniform(0.0, 0.3, size=(batch_size,))

Hello sir.

I have a problem with these part of your code. Based on you previous codes, you set Real data has label in the range of 0.7-1.2 and Fake data is 0.0-0.3. But why in this place you reverse them and let Real data is 0.0-1.3?

The quality of the generator

Hi, from the picture you have shown in the Readme, I find the quality of the genreated images are not quit well .What dou you think about it.

License code

Hello, could you please provide a license for your code?

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.