自定义博客皮肤VIP专享

*博客头图:

格式为PNG、JPG,宽度*高度大于1920*100像素,不超过2MB,主视觉建议放在右侧,请参照线上博客头图

请上传大于1920*100像素的图片!

博客底图:

图片格式为PNG、JPG,不超过1MB,可上下左右平铺至整个背景

栏目图:

图片格式为PNG、JPG,图片宽度*高度为300*38像素,不超过0.5MB

主标题颜色:

RGB颜色,例如:#AFAFAF

Hover:

RGB颜色,例如:#AFAFAF

副标题颜色:

RGB颜色,例如:#AFAFAF

自定义博客皮肤

-+

用思想、知识和音乐去影响和改变

  • 博客(8)
  • 资源 (6)
  • 收藏
  • 关注

转载 vim临时解决乱码的方法 e ++enc=utf-8

在vim中输入:e ++enc=utf8可以快速解决vim乱码问题,即使语言配置不正确,也可以快速解决乱码问题。这种方式的原理是: 当vim无法识别文档的编码的时候,会使用latin-1去读取,导致文档显示上出现乱码,上述命令,就会让vim用utf-8编码的方式重新加载一遍,当然如果你的文档是用gbk编码的,可以使用: e ++=enc=gbk的方式来转换。————————————————...

2020-01-09 14:26:21 3218

转载 NLP之BERT分类模型部署提供服务

1. labek2id.pkl2. graph.pb3. 模型参数需要一致在我们使用bert预分类模型微调之后(可以参考我前面写的文章),需要对项目进行支持,那就需要分类模型落地提供服务,这篇文章介绍python调用bert模型,提供服务。参考:https://github.com/xmxoxo/BERT-train2deploy在后期部署的时候,需要一个label2id的字典,所...

2020-01-08 17:50:10 1058

转载 搜索-Query Understanding (QU)

往简单来讲,用户输入了搜索词,系统通过搜索词找到与搜索词相关的商品集合,系统通过用户及商品的情况进行排序,最终展现给用户。0.找不到但是在构建搜索系统的初期总是无法精准地帮助用户找到想要的商品主要原因有以下几点:不同的用户对同一种诉求的表达往往是有差别的,往往会存在一种比较常见的现象,用户输入的query并不能清晰准确的表达需求。这一块是可以通过较好的产品设计及实时反馈来做精确需求...

2020-01-08 10:26:49 1733

转载 因果卷积(causal)与扩展卷积(dilated)之An Empirical Evaluation of Generic Convolutional and Recurrent Networks f

最近在看关于NLP(自然语言处理)方面的文章,(其实不是自己要看),anyway,看了一个“An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling“,讲到了:虽然人们现在都在用RNN和LSTm去处理序列问题(sequencemodeling),但是明显最近几年这些模...

2020-01-08 10:03:16 949

转载 Pig—MultiQuery Execution

A = LOAD'/user/input/t.txt' as (k:chararray,c:int);B = group A BY k;C = foreach Bgenerate group,SUM(A.c);store C into'/user/output/test1.out';DUMP C;store C into'/user/output/test2.out...

2020-01-07 23:47:40 180

转载 搜索-Query Rewrite (QR)

1. 为什么需要QR查询改写,即 Query Rewrite,主要解决的问题是用户的搜索 Query 和 被搜索的文档 不显式匹配。Query和Doc/Item有Semantic Gap,Query是用户端语言,Doc/Item是商户/平台端语言,风格和词汇都不一样。e.g. Query端是“通马桶”、“剪头”,Doc端是“管道疏通”、“理发”。Semantic Match是一种解决方...

2020-01-07 23:43:03 659

转载 C语言extern作用(全局变量)

用C语言编写程序的时候,我们经常会遇到这样一种情况:希望在头文件中定义一个全局变量,然后包含到两个不同的c文件中,希望这个全局变量能在两个文件中共用。  举例说明:项目文件夹project下有main.c、common.c和common.h三个文件,其中common.h文件分别#include在main.c和common.c文件中。现在希望声明一个字符型变量key,在main.c和com...

2020-01-07 23:15:02 3306 2

转载 搜索-Query理解(全)

Query 模块:纠错 分词 紧密度 同义词 词权重 实体词识别 意图识别长尾 query 的多样性对于搜索系统来说是一个很大的挑战,原因有:❶存在输入错误。例如上图中的错误 query "塞尔维雅" ( 塞尔维亚 ),对于这种错误我们希望系统能够自动的纠错;❷存在表达冗余。例如输入 "孙子兵法智慧的现代意义",在这个语境下,"智慧" 是一个无关紧要的词。如果强制去匹...

2020-01-06 17:39:08 6995 3

httpclient tutorial httpclient 指南

httpclient 指南 包括了详细的调用和常用代码 The Hyper-Text Transfer Protocol (HTTP) is perhaps the most significant protocol used on the Internet today. Web services, network-enabled appliances and the growth of network computing continue to expand the role of the HTTP protocol beyond user-driven web browsers, while increasing the number of applications that require HTTP support. Although the java.net package provides basic functionality for accessing resources via HTTP, it doesn't provide the full flexibility or functionality needed by many applications. HttpClient seeks to fill this void by providing an efficient, up-to-date, and feature-rich package implementing the client side of the most recent HTTP standards and recommendations. Designed for extension while providing robust support for the base HTTP protocol, HttpClient may be of interest to anyone building HTTP-aware client applications such as web browsers, web service clients, or systems that leverage or extend the HTTP protocol for distributed communication.

2018-03-08

mask rcnn paper

We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. Mask R-CNN is simple to train and adds only a small overhead to Faster R-CNN, running at 5 fps. Moreover, Mask R-CNN is easy to generalize to other tasks, e.g., allowing us to estimate human poses in the same framework. We show top results in all three tracks of the COCO suite of challenges, including instance segmentation, bounding-box object detection, and person keypoint detection. Without tricks, Mask R-CNN outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. We hope our simple and effective approach will serve as a solid baseline and help ease future research in instance-level recognition. Code will be made available.

2018-03-07

Applying Deep Learning To Answer Selection

Applying Deep Learning To Answer Selection- A Study And An Open Task

2018-03-07

Learning Phrase Representations using RNN Encoder–Decoder

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

2018-03-07

BPTT BackPropagation Through Time.pdf

BPTT paper This report provides detailed description and necessary derivations for the BackPropagation Through Time (BPTT) algorithm. BPTT is often used to learn recurrent neural networks (RNN). Contrary to feed-forward neural networks, the RNN is characterized by the ability of encoding longer past information, thus very suitable for sequential models. The BPTT extends the ordinary BP algorithm to suit the recurrent neural architecture.

2018-03-07

空空如也

TA创建的收藏夹 TA关注的收藏夹

TA关注的人

提示
确定要删除当前文章?
取消 删除