文档章节

人工智能资料库:第56辑(20170524)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:24
字数 437
阅读 3
收藏 0

1.【代码】paraphrase-id-tensorflow

简介:

Various models and code for paraphrase identification implemented in Tensorflow (1.1.0).

I took great care to document the code and explain what I'm doing at various steps throughout the models; hopefully it'll be didactic example code for those looking to get started with Tensorflow!

So far, this repo has implemented:

PR's to add more models / optimize or patch existing ones are more than welcome! The bulk of the model code resides in duplicate_questions/models

A lot of the data processing code is taken from / inspired by allenai/deep_qa, go check them out if you like how this project is structured!

原文链接:https://github.com/nelson-liu/paraphrase-id-tensorflow


2.【代码】Face classification and detection

简介:

Real-time face detection and emotion/gender classification using fer2013/IMDB datasets with a keras CNN model and openCV.
IMDB gender classification test accuracy: 96%.
fer2013 emotion classification test accuracy: 66%.

Emotion/gender classification of the B-IT-BOTS robotics team :)


原文链接:https://github.com/oarriaga/face_classification


3.【博客】TensorFlow Dev Summit 2017: Integrating Keras and TensorFlow

简介:

I am briefly sharing a video from the last TensorFlow Dev Summit in February 2017. My choice has fallen to a presentation by François Chollet of the deep learning library API Keras and its integration with TensorFlow. As Dr. Chollet explains, Keras integrated with TensorFlow promises to streamline deep learning frameworks in ways that will be increasingly user-friendly, rendering the mass adoption of these software developments a more feasible reality:

原文链接:https://theintelligenceofinformation.wordpress.com/2017/05/22/tensorflow-dev-summit-2017-integrating-keras-and-tensorflow/


4.【博客】Understanding and Implementing CycleGAN in TensorFlow

简介:

Transferring characteristics from one image to another is an exciting proposition. How cool would it be if you could take a photo and convert it into the style of Van Gogh or Picasso!


原文链接:https://hardikbansal.github.io/CycleGANBlog/?utm_campaign=Revue+newsletter&utm_medium=Newsletter&utm_source=revue


5.【资源】Deep Learning Resources

简介:

比较多样化的资源。

原文链接:http://www.jeremydjacksonphd.com/deep-learning-resources/


本文转载自:http://www.jianshu.com/p/b2da8d0fbc76

共有 人打赏支持
AllenOR灵感
粉丝 11
博文 2635
码字总数 83001
作品 0
程序员
私信 提问
预测流行偏好,时尚 AI 未来可望取代造型师

【Technews科技新报】预测时尚潮流是一项需要天分的工作,还得仰赖一个庞大的系统让少数人追捧的时尚进入大众流行市场,进而让业者赚取大笔钞票。现在预测工作也可以交给人工智能,让服饰业者...

黄 嬿
2017/12/26
0
0
人工智能资料库:第72辑(20171203)

1.【会议】Bayesian Deep Learning 简介: While deep learning has been revolutionary for machine learning, most modern deep learning models cannot represent their uncertainty nor......

chen_h
2017/12/03
0
0
国行版HomePod售价2799元,本周五发售

(图片源自苹果中国官网截图) 整理 | 一一 出品 | AI科技大本营 去年 12 月,苹果表示将于今年年初在中国销售其 HomePod 智能音箱。1 月 14 日,苹果公司正式宣布,HomePod 将于 1 月 18 日...

AI科技大本营
01/14
0
0
资源 | 剑桥大学:156页PPT全景展示AI过去的12个月(附下载)

  转载自专知   作者:Nathan Benaich、Ian Hogarth      剑桥大学 Nathan Benaich 与 Ian Hogarth 博士共同发布关于人工智能最近 12 个月进展的报告,其中包含对新技术,人才流动,...

机器之心
2018/07/03
0
0
人工智能知识整理-第1辑(20170603)-机器学习入门资源汇总

有一天我忽然忘记了一个函数的用法,于是就上谷歌搜,结果搜出来的竟然是自己写的一篇笔记,上面有很详细的回答。当时感觉是跟另外一个自己进行交流,那一个是刚学完知识,印象还非常深的自己...

人工智豪
2017/06/03
0
0

没有更多内容

加载失败,请刷新页面

加载更多

Java生成二维码图片

maven配置jar包 <dependency><groupId>com.google.zxing</groupId><artifactId>core</artifactId><version>3.3.3</version></dependency><dependency><groupId>com.google.z......

骑羊放狼灬
4分钟前
0
0
oracle 修改字段类型

1.varchar2 类型修改 例子:alter table T_Node modify (NODE_CONTEXT varchar2(4000)); 2.varchar2 修改为clob 例子: alter table T_Node add hehe clob; update T_Node set hehe=NODE_CO......

qimh
7分钟前
1
0
别再写 bug 了,避免空指针的 5 个案例!

空指针是我们 Java 开发人员经常遇到的一个基本异常,这是一个极其普遍但似乎又无法根治的问题。 本文,栈长将带你了解什么是空指针,还有如何有效的避免空指针。 什么是空指针? 当一个变量...

Java技术栈
11分钟前
1
0
FastJson对BigDecimal保留两位小数(valueFilter)

实现ValueFilter public class BigDecimalValueFilter implements ValueFilter { @Override public Object process(Object o, String name, Object value) {//o是待转换的对象,n......

石日天
13分钟前
1
0
android 颜色透明度参照比

##透明度参照表: 00%=FF(不透明) 5%=F2 10%=E5 15%=D8 20%=CC 25%=BF 30%=B2 35%=A5 40%=99 45%=8c 50%=7F 55%=72 60%=66 65%=59 70%=4c 75%=3F 80%=33 85%=21 90%=19 95%=0c 100%=00(全透......

东街小霸王
14分钟前
1
0

没有更多内容

加载失败,请刷新页面

加载更多

返回顶部
顶部