<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[w1nd_的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/w1nd_</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; w1nd_]]></copyright><item><title><![CDATA[OpenCV基本操作]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/117447761</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/117447761</guid><author>w1nd_</author><pubDate>Wed, 02 Jun 2021 09:45:39 +0800</pubDate><description><![CDATA[Day46OpenCV基本操作图片读取视频读取截取部分图像颜色通道提取边界填充数值计算图像融合图像处理图像平滑加噪声均值滤波方框滤波1方框滤波2高斯滤波中值滤波展示所有形态学处理腐蚀操作膨胀操作开运算闭运算梯度运算礼帽黑帽边缘检测sobelscharr、laplaciancanny高斯金字塔拉普拉斯金字塔图像轮廓轮廓近似边界矩形外接圆模板匹配匹配多个对象直方图mask操作均衡化自适应直方图均衡化傅里叶变换
OpenCV基本操作
import cv2
from matplotlib import pyplot]]></description><category></category></item><item><title><![CDATA[CNN基础]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/117355750</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/117355750</guid><author>w1nd_</author><pubDate>Fri, 28 May 2021 11:02:22 +0800</pubDate><description><![CDATA[Day45CNN基础神经网络基础CNN基础
CNN基础
神经网络基础

























CNN基础




















]]></description><category></category></item><item><title><![CDATA[BP神经网络]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/117334158</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/117334158</guid><author>w1nd_</author><pubDate>Thu, 27 May 2021 17:52:03 +0800</pubDate><description><![CDATA[Day44BP神经网络基本介绍简单实例
BP神经网络
基本介绍












简单实例





]]></description><category></category></item><item><title><![CDATA[非深度学习的图像分割及人脸检测]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/117330751</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/117330751</guid><author>w1nd_</author><pubDate>Thu, 27 May 2021 16:01:02 +0800</pubDate><description><![CDATA[Day43非深度学习的图像分割及人脸检测图像分割基于阈值、边缘基于区域、图论分水岭算法Graph CutsGrabCut人脸检测Haar-like特征+级联分类器行人检测HOG+SVMDPM
非深度学习的图像分割及人脸检测
图像分割


基于阈值、边缘


基于区域、图论




分水岭算法

Graph Cuts





GrabCut







人脸检测

Haar-like特征+级联分类器







![在这里插入图片描述](https://img-blog.csdnimg.cn/20210]]></description><category></category></item><item><title><![CDATA[图像预处理介绍]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/117327727</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/117327727</guid><author>w1nd_</author><pubDate>Thu, 27 May 2021 14:30:00 +0800</pubDate><description><![CDATA[Day42图像预处理介绍图像显示与存储原理图像增强的目标图像处理方法点运算形态学处理域处理及变换空域分析及变换边界填充策略滤波频域分析及变换
图像预处理介绍
图像显示与存储原理





图像增强的目标

图像处理方法
点运算








形态学处理

域处理及变换
空域分析及变换



边界填充策略


滤波












频域分析及变换





















...]]></description><category></category></item><item><title><![CDATA[Auto-Encoder、Variational-Auto-Encoder]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/117020197</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/117020197</guid><author>w1nd_</author><pubDate>Wed, 19 May 2021 11:01:09 +0800</pubDate><description><![CDATA[Day41Auto-Encoder、Variational-Auto-EncoderAuto-EncoderVariational-Auto-Encoder
Auto-Encoder、Variational-Auto-Encoder
Auto-Encoder


import  os
import  tensorflow as tf
import  numpy as np
from PIL import  Image
from    tensorflow import keras
from tensorfl]]></description><category></category></item><item><title><![CDATA[RNN、LSTM、GRU实战——imdb情感分析]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/116938986</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/116938986</guid><author>w1nd_</author><pubDate>Mon, 17 May 2021 17:35:52 +0800</pubDate><description><![CDATA[Day40RNN、LSTM、GRU实战——imdb情感分析RNNCell模式Layer模式LSTMCell模式Layer模式GRUCell模式Layer模式
RNN、LSTM、GRU实战——imdb情感分析
RNN






Cell模式
import  os
import  tensorflow as tf
import  numpy as np
from    tensorflow import keras
from    tensorflow.keras import layers


tf.ran]]></description><category></category></item><item><title><![CDATA[CIFAR10简单实战——Resnet18]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/116301423</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/116301423</guid><author>w1nd_</author><pubDate>Fri, 30 Apr 2021 13:10:32 +0800</pubDate><description><![CDATA[Day39CIFAR10简单实战——Resnet18
CIFAR10简单实战——Resnet18
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics
import os
from resnet import resnet18

os.environ['TF_CPP_MIN_LOG_LEVEL'] =]]></description><category></category></item><item><title><![CDATA[CIFAR10简单实战——VGG13]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/116155147</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/116155147</guid><author>w1nd_</author><pubDate>Mon, 26 Apr 2021 14:34:45 +0800</pubDate><description><![CDATA[Day38CIFAR10简单实战
CIFAR10简单实战
import  tensorflow as tf
from    tensorflow.keras import datasets, layers, optimizers, Sequential, metrics
from 	tensorflow import keras
import  os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'


def preprocess(x, y):
    # [0~255]]]></description><category></category></item><item><title><![CDATA[Tf.keras的部分API]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/116133816</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/116133816</guid><author>w1nd_</author><pubDate>Mon, 26 Apr 2021 11:29:26 +0800</pubDate><description><![CDATA[Day37Tf.keras的部分APIMetricsCompilekeras快速自定义保存、加载模型save_weightssavesaved_model
Tf.keras的部分API
Metrics
import  tensorflow as tf
from    tensorflow.keras import datasets, layers, optimizers, Sequential, metrics


def preprocess(x, y):

    x = tf.cast(x, dtyp]]></description><category></category></item><item><title><![CDATA[Tensorboard可视化]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/116128719</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/116128719</guid><author>w1nd_</author><pubDate>Sun, 25 Apr 2021 15:01:30 +0800</pubDate><description><![CDATA[Day36Tensorboard可视化简介代码
Tensorboard可视化
简介
https://www.cnblogs.com/nxf-rabbit75/p/10635563.html.
代码


tensorboard --logdir logs（logs是自建的文件夹）




tensorflow没有这种仪表盘的显示很不方便



代码片


import  tensorflow as tf
from    tensorflow.keras import datasets, layers, opt]]></description><category></category></item><item><title><![CDATA[手写数字识别/fashion_mnist]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/116126420</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/116126420</guid><author>w1nd_</author><pubDate>Sun, 25 Apr 2021 13:57:00 +0800</pubDate><description><![CDATA[Day35手写数字识别/fashion_mnist
手写数字识别/fashion_mnist
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics

def preprocess(x, y):
    x = tf.cast(x, dtype=tf.float32) / 255.
    y = tf]]></description><category></category></item><item><title><![CDATA[tensorflow入门测试代码]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/115666649</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/115666649</guid><author>w1nd_</author><pubDate>Sun, 25 Apr 2021 13:54:13 +0800</pubDate><description><![CDATA[Day34tensorflow入门初识张量前向传播合并与分割数据统计张量排序张量填充与复制张量限幅进阶数据集加载全连接层MSE、EntropyGradient
tensorflow入门
初识
import tensorflow as tf
from tensorflow.keras import datasets, layers, optimizers
import numpy as np
from tensorflow import keras
from keras.layers.embeddings i]]></description><category></category></item><item><title><![CDATA[Recursive]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/115527633</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/115527633</guid><author>w1nd_</author><pubDate>Thu, 08 Apr 2021 18:07:04 +0800</pubDate><description><![CDATA[Day33Recursive
Recursive










]]></description><category></category></item><item><title><![CDATA[Generation]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/115523650</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/115523650</guid><author>w1nd_</author><pubDate>Thu, 08 Apr 2021 17:28:20 +0800</pubDate><description><![CDATA[Day32GenerationDynamic Conditional GenerationMemory NetworkNeural Turing MachineScheduled SamplingBeam Search
Generation





Dynamic Conditional Generation






Memory Network
方式一

方式二


Neural Turing Machine
k对应产生attention







下图中，上是根据实际情况纠正，下是根据模型情况]]></description><category></category></item><item><title><![CDATA[Unsupervised Learning]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/115232941</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/115232941</guid><author>w1nd_</author><pubDate>Mon, 29 Mar 2021 16:10:24 +0800</pubDate><description><![CDATA[Day31Unsupervised LearningLinear MethodPCAReferenceNeighbor EmbeddingAuto-encoderDeep GenerationPixelRNNAuto-encoderVAEGAN
Unsupervised Learning
Linear Method
PCA















Reference


Neighbor Embedding



Auto-encoder









经历encode和decode时(尽可能前后]]></description><category></category></item><item><title><![CDATA[Deep Reinforcement Learning]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/115087985</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/115087985</guid><author>w1nd_</author><pubDate>Mon, 22 Mar 2021 17:55:57 +0800</pubDate><description><![CDATA[Day30Deep Reinforcement Learning
Deep Reinforcement Learning

























]]></description><category></category></item><item><title><![CDATA[Word Embedding]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/114927149</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/114927149</guid><author>w1nd_</author><pubDate>Wed, 17 Mar 2021 13:47:29 +0800</pubDate><description><![CDATA[Day29Word Embedding例子
Word Embedding










例子








]]></description><category></category></item><item><title><![CDATA[半监督学习]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/114916174</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/114916174</guid><author>w1nd_</author><pubDate>Wed, 17 Mar 2021 09:36:03 +0800</pubDate><description><![CDATA[Day28Semi-supervisedGraph-based Approach
Semi-supervised








Graph-based Approach







]]></description><category></category></item><item><title><![CDATA[神经网络超简短介绍]]></title><link>https://blog.youkuaiyun.com/w1nd_/article/details/114680143</link><guid>https://blog.youkuaiyun.com/w1nd_/article/details/114680143</guid><author>w1nd_</author><pubDate>Thu, 11 Mar 2021 22:01:49 +0800</pubDate><description><![CDATA[Day27CNN基本介绍RNNLSTM
CNN



基本介绍
循环神经网络模型（RNN）是一种节点定向连接成环的人工神经网络，是一种反馈神经网络，RNN利用内部的记忆来处理任意时序的输入序列，并且在其处理单元之间既有内部的反馈连接又有前馈连接，这使得RNN可以更加容易处理不分段的文本等。但是由于RNN只能对部分序列进行记忆，所以在长序列上表现远不如短序列，造成了一旦序列过长便使得准确率下降的结果。
长短期记忆模型（LSTM）是RNN模型的一种特殊结构类型，其增加了输入门、输出门、忘记门三个控制单元（“ce]]></description><category></category></item></channel></rss>