深度卷积生成式对抗网络,Deep Convolutional Generative Adversarial Nerworks
来源:互联网 发布:Linux安装sip 编辑:程序博客网 时间:2024/05/16 08:13
无监督学习的方法:聚类、自编码、深度置信网络
生成自然图像的各类方式:
1. 非参数~The non-parametric models often do matching from a database of existing images, often matching patches of images常用领域是纹理合成,超分辨率和图像修复。
2. 参数~A variational sampling approach to generating images (Kingma & Welling, 2013) has had some success, but the samples often suffer from being blurry变分采样,会出现模糊。
Another approach generates images using an iterative forward diffusion process (Sohl-Dickstein et al.,2015)
Generative Adversarial Networks(Goodfellow et al., 2014) generated images suffering from being noisy and incomprehensible GAN会出现噪声和不能理解的图像
A laplacian pyramid extension to this approach (Denton et al., 2015) showed higher quality images
A recurrent network approach (Gregor et al., 2015) and a deconvolution network approach (Dosovitskiy et al., 2014) have also recently had some success with generating natural images
DCGAN的架构技巧:
1. 不使用pooling层:the all convolutional net which replaces deterministic spatial pooling functions (such as maxpooling) with strided convolutions(strided convolutions——discriminator,fractional-strided
——generator)
2. 不使用全连接层:the trend towards eliminating fully connected layers on top of convolutional features 在100维z经矩阵乘法输出以后reshape得到了4×4×1024的卷积层
3. 使用BN层:Batch Normalization which stabilizes learning by normalizing the input to each unit to have zero mean and unit variance(both the generator and the discriminator )
4. 激活函数:generator除最后一层用ReLU,最后一层为Tanh;discriminator全部用LearkyReLU
对无监督表示学习的测评方法:evaluating the quality of unsupervised representation learning algorithms is to apply them as a feature extractor on supervised datasets and evaluate the performance of linear models fitted on top of these features
重用神经网络中的部分层作为特征提取器进行有监督学习。
【1】UNSUPERVISED REPRESENTATION LEARNING WITH DEEP CONVOLUTIONAL
GENERATIVE ADVERSARIAL NETWORKS
- 深度卷积生成式对抗网络,Deep Convolutional Generative Adversarial Nerworks
- 【神经网络与深度学习】生成式对抗网络GAN研究进展(五)——Deep Convolutional Generative Adversarial Nerworks,DCGAN
- 生成式对抗网络GAN研究进展(五)——Deep Convolutional Generative Adversarial Nerworks,DCGAN
- 生成对抗网络学习笔记3----论文unsupervised representation learning with deep convolutional generative adversarial
- GANs学习系列(8):Deep Convolutional Generative Adversarial Nerworks,DCGAN
- GANs学习系列(8):Deep Convolutional Generative Adversarial Nerworks,DCGAN
- Generative Adversarial Nets 生成式对抗网络
- 生成式对抗网络generative adversarial nets
- 【深度学习】生成对抗网络Generative Adversarial Nets
- 生成式对抗网络(Generative Adversarial Nets)
- 生成式对抗网络Generative Adversarial Networks(GANs)
- 生成式对抗网络(Generative Adversarial Networks,GAN)
- 对抗生成网络(Generative Adversarial Net)
- 生成对抗网络Generative Adversarial Nets资料
- 对抗生成网络(Generative Adversarial Net)
- 对抗生成网络(Generative Adversarial Net)
- 对抗生成网络(Generative Adversarial Net)
- 对抗生成网络(Generative Adversarial Network)
- nio 使用的都是直接内存吗?
- Java多线程综述
- BZOJ3343[教主的魔法]
- "-"滚动条(CScoollar)综合文件
- Spring事务管理(详解+实例)
- 深度卷积生成式对抗网络,Deep Convolutional Generative Adversarial Nerworks
- Java GC专家系列2:Java 垃圾回收的监控
- "-"对话框(Dialog)汇总文件
- LeetCode.395
- Linux 链接命令
- 利用css3实现3d立体特效--正方体
- JSON转换成JSONArray数组
- MVC设计思想
- XMAN2017选拔赛Crypto-Caesar