2019年04月_xiewenbo

12月 11月 07月 06月 05月 04月 03月 02月 01月

转载词向量与Embedding究竟是怎么回事？

词向量，英文名叫Word Embedding，按照字面意思，应该是词嵌入。说到词向量，不少读者应该会立马想到Google出品的Word2Vec，大牌效应就是不一样。另外，用Keras之类的框架还有一个Embedding层，也说是将词ID映射为向量。由于先入为主的意识，大家可能就会将词向量跟Word2Vec等同起来，而反过来问“Embedding是哪种词向量？”这类问题，尤其是对于初学者来说，应该是...

2019-04-12 10:47:09 873

转载 tensorflow read from HDFS

1.https://github.com/tensorflow/examples/blob/master/community/en/docs/deploy/hadoop.md2.https://www.jianshu.com/p/438febcc6674TensorFlow on HadoopThis document describes how to run TensorFlow...

2019-04-29 20:07:11 2759

转载 Tensorflow multi-models and multi-version

1. Multi-models预备备：docker使用的是17.05.0-ce及以上的版本，之前用的13.XX的版本没有--mount这样的命令0）下载安装tensorflow#官网上抄的，啊哈哈docker pull tensorflow/servinggit clonehttps://github.com/tensorflow/serving1）创建一个多模型配置文件...

2019-04-29 20:01:24 166

转载 tensorflow数据读取机制-Queue

转处：https://zhuanlan.zhihu.com/p/27238630在学习tensorflow的过程中，有很多小伙伴反映读取数据这一块很难理解。确实这一块官方的教程比较简略，网上也找不到什么合适的学习材料。今天这篇文章就以图片的形式，用最简单的语言，为大家详细解释一下tensorflow的数据读取机制，文章的最后还会给出实战代码以供参考。一、tensorflow读取机制图解...

2019-04-29 11:38:10 154

原创 what's the difference among bootstrap-server , zookeeper and broker-list ?

1. bootstrap-server vs zookeeper paramsIn the previous Kafka version (before 0.9.0), the consumer needed the connection to Zookeeper for committing the offset and for getting topics metadata as well...

2019-04-29 10:44:15 727

转载 tf.where()函数

tf.where()定义如下：where(condition, x=None, y=None,name=None)condition:一个Tensor,数据类型为tf.bool类型如果x、y均为空，那么返回condition中值为True的位置的Tensor：例如：x就是condition，y是返回值x中值为True的位置有[0,0,0],[0,1,1],[0,2,0],[0,...

2019-04-26 13:52:17 383

转载直观的理解tensorflow中的tf.tile()函数

tensorflow中的tile()函数是用来对张量(Tensor)进行扩展的，其特点是对当前张量内的数据进行一定规则的复制。最终的输出张量维度不变。函数定义：tf.tile( input, multiples, name=None)input是待扩展的张量，multiples是扩展方法。假如input是一个3维的张量。那么mutiples就必须是一个1x3...

2019-04-26 11:36:19 402

转载 tf.sequence_mask

用法：sequence_mask( lengths, maxlen=None, dtype=tf.bool, name=None)函数参数lengths：整数张量，其所有值小于等于maxlen。maxlen：标量整数张量，返回张量的最后维度的大小；默认值是lengths中的最大值。dtype：结果张量的输出类型。name：操作的名字。用例子说明用法：...

2019-04-26 11:35:16 435

转载 TensorFlow Text Classification using Attention Mechanism

http://androidkt.com/tensorflow-text-classification-attention-mechanism/In this tutorial, we’re gonna to build a recurrent neural network that’s able to classify reviews. This can be used to improve...

2019-04-18 21:02:14 448

转载 Text Classification using Attention Mechanism in Keras

http://androidkt.com/text-classification-using-attention-mechanism-in-keras/In this tutorial, We build text classification models in Keras that use attention mechanism to provide insight into how cl...

2019-04-18 20:56:56 492

转载深度学习干货学习（1）——center loss

在构建loss时pytorch常用的包中有最常见的MSE、cross entropy（logsoftmax+NLLLoss）、KL散度Loss、BCE、HingeLoss等等，详见：https://pytorch-cn.readthedocs.io/zh/latest/package_references/torch-nn/#loss-functions这里主要讲解一种考虑类间距离的Cente...

2019-04-13 18:14:01 891

转载对于矩阵操作中axis的理解，以及axis=-1的解释

1. axis的基本使用axis常常用在numpy和tensorflow中用到，作为对矩阵（张量）进行操作时需要指定的重要参数之一。设定axis=-1,0,1...，用来指定执行操作的数据如何划分。一句话解释：设axis=i，则沿着第i个下标变化的方向进行操作！[1]简单例子就不举了，其他博客有很多，这里举一个稍微复杂一点的三维矩阵的例子：设embeddings是一个shape=[3...

2019-04-13 13:29:28 8600

转载 How to define a keras custom loss function in simple mathematical operation

https://blog.csdn.net/xiewenbo/article/details/89255424I define a custom functionmy_sigmoidas following:import mathdef my_sigmoid(x): a = 1/ ( 1+math.exp( -(x-300)/30 ) ) return aA...

2019-04-12 19:55:44 447

转载 keras 自定义Layer

编写你自己的 Keras 层对于简单、无状态的自定义操作，你也许可以通过 layers.core.Lambda 层来实现。但是对于那些包含了可训练权重的自定义层，你应该自己实现这种层。这是一个 Keras2.0 中，Keras 层的骨架（如果你用的是旧的版本，请更新到新版）。你只需要实现三个方法即可:build(input_shape): 这是你定义权重的地方。这个方法必须设 self....

2019-04-12 15:27:09 4723

转载 Keras中自定义复杂的loss函数

https://kexue.fm/archives/4493

2019-04-12 14:21:53 1083

转载 softmax

2019-04-04 20:04:26 90

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