<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[大叔叔]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/chaochaopang0</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; chaochaopang0]]></copyright><item><title><![CDATA[Faster-Rcnn记录]]></title><link>https://blog.youkuaiyun.com/chaochaopang0/article/details/90443205</link><guid>https://blog.youkuaiyun.com/chaochaopang0/article/details/90443205</guid><author>chaochaopang0</author><pubDate>Wed, 22 May 2019 20:19:03 +0800</pubDate><description><![CDATA[Faster-Rcnn记录

上述图理解如下：
（1）Ncls=256

]]></description><category></category></item><item><title><![CDATA[深度学习开源项目整理]]></title><link>https://blog.youkuaiyun.com/chaochaopang0/article/details/82777267</link><guid>https://blog.youkuaiyun.com/chaochaopang0/article/details/82777267</guid><author>chaochaopang0</author><pubDate>Wed, 19 Sep 2018 19:50:24 +0800</pubDate><description><![CDATA[基于TensorFlow的框架
https://github.com/fchollet/keras
https://github.com/tflearn/tflearn
https://github.com/beniz/deepdetect
https://github.com/tensorflow/fold
https://github.com/leriomaggio/deep-learning...]]></description><category></category></item><item><title><![CDATA[java web 零基础]]></title><link>https://blog.youkuaiyun.com/chaochaopang0/article/details/82699697</link><guid>https://blog.youkuaiyun.com/chaochaopang0/article/details/82699697</guid><author>chaochaopang0</author><pubDate>Fri, 14 Sep 2018 11:10:00 +0800</pubDate><description><![CDATA[jdk配置：https://jingyan.baidu.com/article/6dad5075d1dc40a123e36ea3.html 
maven配置：https://www.cnblogs.com/eagle6688/p/7838224.html 
MyEclipse+Tomcat配置：https://blog.youkuaiyun.com/qq_25827845/article/details/53...]]></description><category></category></item><item><title><![CDATA[基于随机森林挖掘趵突泉景区气象对客流量影响]]></title><link>https://blog.youkuaiyun.com/chaochaopang0/article/details/81327036</link><guid>https://blog.youkuaiyun.com/chaochaopang0/article/details/81327036</guid><author>chaochaopang0</author><pubDate>Wed, 01 Aug 2018 11:03:28 +0800</pubDate><description><![CDATA[
# coding: utf-8

# # 趵突泉景区客流量预测
# 影响景区客流量的因素有很多，本例主要研究天气及节假日对景区客流量的影响


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
#get_ipython().magic('matplotlib inline')

### 导入数据集

df...]]></description><category></category></item><item><title><![CDATA[几个经典卷积神经网络]]></title><link>https://blog.youkuaiyun.com/chaochaopang0/article/details/80501967</link><guid>https://blog.youkuaiyun.com/chaochaopang0/article/details/80501967</guid><author>chaochaopang0</author><pubDate>Tue, 29 May 2018 20:53:16 +0800</pubDate><description><![CDATA[从AlexNet论文说起，ImageNet Classification with Deep Convolutional Neural Networks。

在ImageNet LSVRC-2010 2012表现突出

top-1误差率37.5%，以及top-5误差率17.0%

网络有6000万个参数和650,000个神经元

网络结构五个卷积层，以及某些卷积层后的池化层，以及最后的三个全连接层...]]></description><category></category></item><item><title><![CDATA[基于spark mllib 随机森林分类 代码记录后续完善]]></title><link>https://blog.youkuaiyun.com/chaochaopang0/article/details/80266362</link><guid>https://blog.youkuaiyun.com/chaochaopang0/article/details/80266362</guid><author>chaochaopang0</author><pubDate>Thu, 10 May 2018 13:34:04 +0800</pubDate><description><![CDATA[scala+spark+randomForests

代码实现分为读取hive数据、随机森林建模训练、数据预测


随机森林建模训练的代码主类（实现流程）


package com.inspur.mr.InspurMr.Classification
import java.io.File
import java.io.PrintWriter
import java.util.ArrayList
...]]></description><category></category></item><item><title><![CDATA[基于keras多层LSTM实现]]></title><link>https://blog.youkuaiyun.com/chaochaopang0/article/details/80266155</link><guid>https://blog.youkuaiyun.com/chaochaopang0/article/details/80266155</guid><author>chaochaopang0</author><pubDate>Thu, 10 May 2018 13:13:04 +0800</pubDate><description><![CDATA[代码分为数据读取、预处理、建模、训练、预测（测试集预测，未来连续预测）、结果展示（此代码是以单属性数据集为例）

# -*- coding: utf-8 -*-
&amp;quot;&amp;quot;&amp;quot;
Created on Tue May  8 14:28:43 2018

@author: lichao_lc
&amp;quot;&amp;quot;&amp;quot;
import numpy as np
import matplotlib.pyplot as plt
impo..]]></description><category></category></item><item><title><![CDATA[hadoop 、spark 、hive环境搭建]]></title><link>https://blog.youkuaiyun.com/chaochaopang0/article/details/79581359</link><guid>https://blog.youkuaiyun.com/chaochaopang0/article/details/79581359</guid><author>chaochaopang0</author><pubDate>Fri, 16 Mar 2018 14:30:42 +0800</pubDate><description><![CDATA[搭建spark、hive，应先搭建hadoop 
hadoop搭建教程：http://blog.youkuaiyun.com/xiaoxiangzi222/article/details/52757168

spark搭建教程：http://blog.youkuaiyun.com/bitcarmanlee/article/details/51967323

hive搭建教程：http://www.cnblogs.com/...]]></description><category></category></item><item><title><![CDATA[分类之性能评估指标]]></title><link>https://blog.youkuaiyun.com/chaochaopang0/article/details/78730639</link><guid>https://blog.youkuaiyun.com/chaochaopang0/article/details/78730639</guid><author>chaochaopang0</author><pubDate>Wed, 06 Dec 2017 14:49:54 +0800</pubDate><description><![CDATA[本文主要介绍几种常用的分类评估指标，同时介绍如何绘制ROC曲线以及AUC值的便捷的计算方法。最后再附上一个绘制ROC曲线和计算AUC的源码实现。
Precision和Recall
首先我们来看看下面这个混淆矩阵：



pred_label/true_label
Positive
Negative




Positive
TP
FP


Negtive
FN]]></description><category></category></item><item><title><![CDATA[scikit-learn K近邻法类库使用小结]]></title><link>https://blog.youkuaiyun.com/chaochaopang0/article/details/78678528</link><guid>https://blog.youkuaiyun.com/chaochaopang0/article/details/78678528</guid><author>chaochaopang0</author><pubDate>Thu, 30 Nov 2017 17:19:35 +0800</pubDate><description><![CDATA[在K近邻法(KNN)原理小结这篇文章，我们讨论了KNN的原理和优缺点，这里我们就从实践出发，对scikit-learn 中KNN相关的类库使用做一个小结。主要关注于类库调参时的一个经验总结。
1. scikit-learn 中KNN相关的类库概述
　　　　在scikit-learn 中，与近邻法这一大类相关的类库都在sklearn.neighbors包之中。KNN分类树的类是KNeighbor]]></description><category></category></item><item><title><![CDATA[Sklearn-RandomForest随机森林参数及实例]]></title><link>https://blog.youkuaiyun.com/chaochaopang0/article/details/78604014</link><guid>https://blog.youkuaiyun.com/chaochaopang0/article/details/78604014</guid><author>chaochaopang0</author><pubDate>Wed, 22 Nov 2017 15:16:01 +0800</pubDate><description><![CDATA[在scikit-learn中，RandomForest的分类类是RandomForestClassifier，回归类是RandomForestRegressor，需要调参的参数包括两部分，第一部分是Bagging框架的参数，第二部分是CART决策树的参数。

sklearn官网地址（RandomForestClassifier）：http://scikit-learn.org/stable/mod...]]></description><category></category></item><item><title><![CDATA[TensorFlow之损失函数、学习率、正则]]></title><link>https://blog.youkuaiyun.com/chaochaopang0/article/details/78489373</link><guid>https://blog.youkuaiyun.com/chaochaopang0/article/details/78489373</guid><author>chaochaopang0</author><pubDate>Thu, 09 Nov 2017 14:30:02 +0800</pubDate><description><![CDATA[#损失函数记录
import tensorflow as tf
#交叉熵的两种表示
cross_entropy=-tf.reduce_mean(y_*tf.log(tf.clip_by_value(y,1e-10,1.0)))
cross_entropy=tf.nn.softmax_cross_entropy_with_logits(y,y_)
#均方误差的表示
mse=tf.reduce_mea]]></description><category></category></item><item><title><![CDATA[TensorFlow之神经网络练习]]></title><link>https://blog.youkuaiyun.com/chaochaopang0/article/details/78488063</link><guid>https://blog.youkuaiyun.com/chaochaopang0/article/details/78488063</guid><author>chaochaopang0</author><pubDate>Thu, 09 Nov 2017 11:59:23 +0800</pubDate><description><![CDATA[TensorFlow实现神经网络：import tensorflow as tf
from numpy.random import RandomState

batch_size=8
#定义权值、x、y
w1=tf.Variable(tf.random_normal([2,3],stddev=1,seed=1))
w2=tf.Variable(tf.random_normal([3,1],stdd]]></description><category></category></item><item><title><![CDATA[Deep Spatio-Temporal Residual Networks（深度时空残差神经网络）]]></title><link>https://blog.youkuaiyun.com/chaochaopang0/article/details/78459460</link><guid>https://blog.youkuaiyun.com/chaochaopang0/article/details/78459460</guid><author>chaochaopang0</author><pubDate>Mon, 06 Nov 2017 17:03:16 +0800</pubDate><description><![CDATA[残差神经网络在时空数据的简单应用与学习，适合快速动手搭建，成功运行、分析代码，并学习怎样用keras实现模型的同学。]]></description><category></category></item></channel></rss>