pytorch-generative-model-collections

https://github.com/znxlwm/pytorch-generative-model-collections

2017-10-29 22:06:25

阅读数:291

评论数:0

ICCV 2017:训练GAN的16个技巧,2400+星(PPT)

作者:Soumith Chintala等 编译:马文 【新智元导读】本文来自ICCV 2017的Talk:如何训练GAN,FAIR的研究员Soumith Chintala总结了训练GAN的16个技巧,例如输入的规范化,修改损失函数,生成器用Adam优化,使用Sofy和Noisy标签,等...

2017-10-29 21:35:06

阅读数:3357

评论数:1

GENERATIVE ADVERSARIAL NETWORKS FOR IMAGE STEGANOGRAPHY

Steganography is collection of methods to hide secret information (“payload”) within non-secret information (“container”). Its counterpart, Steganaly...

2017-10-27 22:15:45

阅读数:407

评论数:0

PyTorch参数初始化方法

torch.nn.init torch.nn.init.calculate_gain(nonlinearity, param=None)[source] Return the recommended gain value for the given nonlinearity funct...

2017-10-26 20:32:53

阅读数:1092

评论数:0

cs231n - assignment1 - softmax 梯度推导

Softmax exercise Complete and hand in this completed worksheet (including its outputs and any supporting code outside of the worksheet) with your ...

2017-10-26 15:41:15

阅读数:252

评论数:0

pooling mean max 前向和反向传播

对于mean pooling,真的是好简单:假设pooling的窗大小是2x2, 在forward的时候啊,就是在前面卷积完的输出上依次不重合的取2x2的窗平均,得到一个值就是当前mean pooling之后的值。backward的时候,把一个值分成四等分放到前面2x2的格子里面就好了。如下 ...

2017-10-26 15:38:30

阅读数:220

评论数:0

基于深度学习的Person Re-ID(综述)

一. 问题的提出        Person Re-ID 全称是 Person Re-Identification,又称为 行人重检测 or 行人再识别,直观上可以通过两种思路进行比对,一种是 通过 静态图像(still-image)进行特征比对,另一种是通过视频的时序特征(temporal...

2017-10-22 21:20:40

阅读数:1130

评论数:0

论文笔记-Person Re-identification Past, Present and Future

2016_Person Re-identification Past, Present and Future Liang Zheng, Yi Yang, and Alexander G. Hauptmann 这是一篇有关于Person re-ID 综述性文章。 转载请附原文地址:...

2017-10-22 20:56:00

阅读数:779

评论数:0

使用frp实现内网穿透

群晖NAS+frp发挥更大作用 Posted by SunnyRx on October 21, 2016 原文地址:http://www.sunnyrx.com/2016/10/21/simple-to-use-frp/ 该文章于2017年9月2日将frp版本从0.8.1更新到0.13.0...

2017-10-19 15:54:13

阅读数:1195

评论数:1

Captioning Images with Diverse Objects

Captioning Images with Diverse Objects Subhashini Venugopalan, Lisa Anne Hendricks, Marcus Rohrbach, Raymond Mooney, Trevor Darrell, Kate Sa...

2017-10-09 11:58:38

阅读数:401

评论数:0

Deep Reinforcement Learning-based Image Captioning with Embedding Reward

Deep Reinforcement Learning-based Image Captioning with Embedding Reward Zhou Ren, Xiaoyu Wang, Ning Zhang, Xutao Lv, Li-Jia Li (Submitted on...

2017-10-09 11:58:16

阅读数:446

评论数:0

Semantic Compositional Networks for Visual Captioning

Semantic Compositional Networks for Visual Captioning Zhe Gan, Chuang Gan, Xiaodong He, Yunchen Pu, Kenneth Tran, Jianfeng Gao, Lawrence Carin...

2017-10-09 11:55:33

阅读数:535

评论数:0

提示
确定要删除当前文章?
取消 删除
关闭
关闭