GAN学习笔记

1.原始的GAN

1.1原始的损失函数

1.1.1写法1参考1参考2

1.1.2 写法2

where,

  • G = Generator
  • D = Discriminator
  • Pdata(x) = distribution of real data
  • P(z) = distribution of generator
  • x = sample from Pdata(x)
  • z = sample from P(z)
  • D(x) = Discriminator network
  • G(z) = Generator network

1.1.3 写法3: 参考3

1.2Wasserstein损失 参考

2.**Conditional GAN (**CGAN)

2.1 写法1:

The Discriminator has two task

  • Discriminator has tocorrectly label real images which are coming from training data set as "real".
  • Discriminator has to correctly label generated images which are coming from Generator as "fake".

We need to calculate two losses for the Discriminator. The sum of the "fake" image and "real" image loss is the overall Discriminator loss.** So the loss function of the Discriminator is aiming at minimizing the error of predicting real images coming from the dataset and fake images coming from the Generator given their one-hot labels.

The Generator network has one task

  • To create an image that looks as "real" as possible to fool the Discriminator.

The loss function of the Generator minimizes the correct prediction of the Discriminator on fake images conditioned on the specified one-hot labels.

  • The conditioning is performed by feeding y into the both the discriminator and generator as additional input layer.
  • In the generator the prior input noise p_z (z ), and y are combined in joint hidden representation.
  • In the discriminator x and y are presented as inputs and to a discriminative function.
  • The objective function of a two-player minimax game become:

2.2 写法2:

where is a probability distribution over classes, is the probability distribution of real images of class C, and the probability distribution of images generated by the generator when given class label C.

2.3 写法3:参考

相关推荐
Caramel_biscuit21 分钟前
STM32 CAN学习
stm32·嵌入式硬件·学习
cwtlw1 小时前
JavaRedis和数据库相关面试题
java·数据库·笔记·面试
DayDayUp..1 小时前
[算法学习笔记] 《Hello算法》第10章 搜索
笔记·学习
大霸王龙1 小时前
LLM(语言学习模型)行为控制技术
python·深度学习·学习
Long_poem1 小时前
【自学笔记】ELK基础知识点总览-持续更新
笔记·elk·jenkins
cwtlw2 小时前
PhotoShop学习03
笔记·学习·photoshop
职业考试资料墙3 小时前
如何报名参加登高架设作业考试?
学习·考试·题库·考证
Peter11467178503 小时前
服务器入门操作1(深度学习)
服务器·人工智能·笔记·深度学习·学习
小王努力学编程3 小时前
动态规划学习——背包问题
开发语言·c++·学习·算法·动态规划
Qwertyuiop201611 小时前
搭建开源笔记平台:outline
笔记·开源