conditional GAN:
text ---> image
such as supervised approach ,lots of samples can not do average operation.
the works D does are evaluate the c and x
x is realistic or not , c and x are matched or not
matched are high scores
not matched low images that is not real are low
two case gave the low scores
in each iteration :
sample m positive example from database(word and image pair) high
sample m noise sample vecter from D obtain a condition
Discriminator
object--->NN condition--->NN then into NN --->output a scores
object x--->NN----->score
NN + condition ---> NN ---->match scores
one is to see object is real or not
one is to see both are matched or not
two task are divided into seperation
stack GAN(thought that is divided into more)
divide into two
text---->G--->image(low Dimention)--->D----->match scores
|
that image--->G----->image(high Dimention)---->G---->reality score
image ---->image
#supervised approach vagurous(average)
GAN: noise + image --> G(image)---->pair---->D
two goals: reality and match
patch GAN:
adjust patch size
speech enhancement
typical deep learning approach
use CNN
evaluation: real and match
vedio generator
D 's input is G's input and output match or not
thoughts:
conditional GAN
引入了条件控制的观念 给与人类能理解的输入的到人们想得到的输出。这是非常奇妙的。
引入条件匹配的概念
学习级联的思想 产出大规模的输出 那么先从小规模输出开始 级联分配任务 前级查匹配 后级查清晰度
级联评估的思想:评估清晰度与条件匹配时,分开两个D,一个D一个分数,用两个分数进行调整G,调整更加有针对性,调整第一项或者第二项就更有目标。
可以利用GAN 技术自动生成后续电影。
生成歌曲。
作诗。
生成音频动画。
GAN生成电影还是蛮有挑战性的。