Reading CSV file...
Parsed 79171 sentences.
Found 65376 unique words tokens.
Using vocabulary size 8000.
The least frequent word in our vocabulary is 'documentary' and appeared 10 times.
Example sentence: 'SENTENCE_START i joined a new league this year and they have different scoring rules than i'm used to. SENTENCE_END'
Example sentence after Pre-processing: '['SENTENCE_START', 'i', 'joined', 'a', 'new', 'league', 'this', 'year', 'and', 'they', 'have', 'different', 'scoring', 'rules', 'than', 'i', "'m", 'used', 'to', '.', 'SENTENCE_END']'
X_train shape: (78483,)
y_train shape: (78483,)
x:
SENTENCE_START what are n't you understanding about this ? !
[0, 51, 27, 16, 10, 858, 54, 25, 34, 69]
y:
what are n't you understanding about this ? ! SENTENCE_END
[51, 27, 16, 10, 858, 54, 25, 34, 69, 1]
2020-02-17 21:40:17: Loss after num_examples_seen=0 epoch=0: 8.987458
2020-02-17 21:42:08: Loss after num_examples_seen=100 epoch=1: 8.973082
2020-02-17 21:44:01: Loss after num_examples_seen=200 epoch=2: 8.951076
2020-02-17 21:45:51: Loss after num_examples_seen=300 epoch=3: 8.907623
2020-02-17 21:47:41: Loss after num_examples_seen=400 epoch=4: 8.803412
2020-02-17 21:49:35: Loss after num_examples_seen=500 epoch=5: 6.866650
2020-02-17 21:51:26: Loss after num_examples_seen=600 epoch=6: 6.271906
2020-02-17 21:53:18: Loss after num_examples_seen=700 epoch=7: 5.981103
2020-02-17 21:55:09: Loss after num_examples_seen=800 epoch=8: 5.786999
2020-02-17 21:57:01: Loss after num_examples_seen=900 epoch=9: 5.654783

参考:

https://github.com/pangolulu/rnn-from-scratch

https://blog.csdn.net/xfwdxt/article/details/102823159

Implementing Recurrent Neural Network from Scratch的更多相关文章

  1. 从0开始用python实现神经网络 IMPLEMENTING A NEURAL NETWORK FROM SCRATCH IN PYTHON – AN INTRODUCTION

    code地址:https://github.com/dennybritz/nn-from-scratch 文章地址:http://www.wildml.com/2015/09/implementing ...

  2. 计算机视觉学习记录 - Implementing a Neural Network from Scratch - An Introduction

    0 - 学习目标 我们将实现一个简单的3层神经网络,我们不会仔细推到所需要的数学公式,但我们会给出我们这样做的直观解释.注意,此次代码并不能达到非常好的效果,可以自己进一步调整或者完成课后练习来进行改 ...

  3. Recurrent Neural Network系列1--RNN(循环神经网络)概述

    作者:zhbzz2007 出处:http://www.cnblogs.com/zhbzz2007 欢迎转载,也请保留这段声明.谢谢! 本文翻译自 RECURRENT NEURAL NETWORKS T ...

  4. 课程五(Sequence Models),第一 周(Recurrent Neural Networks) —— 1.Programming assignments:Building a recurrent neural network - step by step

    Building your Recurrent Neural Network - Step by Step Welcome to Course 5's first assignment! In thi ...

  5. Sequence Models Week 1 Building a recurrent neural network - step by step

    Building your Recurrent Neural Network - Step by Step Welcome to Course 5's first assignment! In thi ...

  6. Recurrent Neural Network系列2--利用Python,Theano实现RNN

    作者:zhbzz2007 出处:http://www.cnblogs.com/zhbzz2007 欢迎转载,也请保留这段声明.谢谢! 本文翻译自 RECURRENT NEURAL NETWORKS T ...

  7. Recurrent Neural Network系列4--利用Python,Theano实现GRU或LSTM

    yi作者:zhbzz2007 出处:http://www.cnblogs.com/zhbzz2007 欢迎转载,也请保留这段声明.谢谢! 本文翻译自 RECURRENT NEURAL NETWORK ...

  8. Recurrent Neural Network(循环神经网络)

    Reference:   Alex Graves的[Supervised Sequence Labelling with RecurrentNeural Networks] Alex是RNN最著名变种 ...

  9. Recurrent Neural Network系列3--理解RNN的BPTT算法和梯度消失

    作者:zhbzz2007 出处:http://www.cnblogs.com/zhbzz2007 欢迎转载,也请保留这段声明.谢谢! 这是RNN教程的第三部分. 在前面的教程中,我们从头实现了一个循环 ...

随机推荐

  1. WampServer 的安装\配置和使用

    WampServer下载地址:http://www.wampserver.com/ WampServer安装(请按序号点击) 双击WampServer安装程序 步骤①更改路径 直接点击安装 等待安装不 ...

  2. 执行yum命令报错"Unable to connect to Registration Management Service"

    问题描述 linux上执行yum相关命令时,报无法连接到注册管理服务的错误,具体报错信息如下 [root@aijihe-core-zy-2-3 ~]# yum install gcc Loaded p ...

  3. 三剑客-sed awk

     目录 1.sed 2.awk 1.sed //sed命令 #语法说明:命令 参数 条件+处理= (指令) 处理文件信息 字符流编辑工具(行编辑工具)==按照每行中的字符进行处理操作 ). 擅长对行进 ...

  4. CSS布局的四种定位方式

    1.static(静态定位): 默认值.没有定位,元素出现在正常的流中(忽略 top, bottom, left, right 或者 z-index 声明).参考上篇随笔. 2.relative(相对 ...

  5. C#中Dictionary的实现简述

    更详细的解析可以查看这篇文章:https://blog.csdn.net/zhaoguanghui2012/article/details/88105715 简要描述就是通过桶Buckets与Entr ...

  6. quartus在线调试的方法

    quartus在线调试的方法 在Quartus II Version 7.2 Handbook Volume 3: Verification中的Section V. In-System Design ...

  7. java_细节_windows7下记事本保存为utf-8格式的问题

    如果在win7下的记事本直接另存为utf-8格式,是带有dom的utf-8,所以处理的时候需要注意,因为第一个字符是"?",而且不可见

  8. 总结下抽象类Abstract和虚方法Virtual(易混点)

    1.普通类中可以有普通方法和虚方法,在被继承时,虚方法可以选择重写(override)或者不重写 2.抽象类中可以有普通方法和虚方法和抽象方法,当被继承时 如下 1.普通方法不能被子类重写 2.虚方法 ...

  9. 力扣MYSQL练习

    176编写一个 SQL 查询,获取 Employee 表中第二高的薪水(Salary) . select IFNULL((SELECT distinct salary from employee or ...

  10. 001.Django_Model.整理

    Django001_Model.整理 Model表设计 数据定义数据存储,输出 a.定义表(信息 =字段) + 定义表关系 + (定义/限制)数据 b.通过orm等方法来,定义method来编辑原始数 ...