AI
佐倉
皆さん、こんにちは。私は桜と申しますが、故郷は河南です。ソフトウェアが大好きだなあ。時間があれば一緒に勉強しましょう!よろしく、お願い致します!
展开
-
tensorflow2.0-维度变换
reshape(合并维度)a = tf.random.normal((4,28,28,3))a_1 = tf.reshape(a,[4,784,3]).shape #1a_1 = tf.reshape(a,[4,-1,3]).shape #和1等价a_2 = tf.reshape(a,[4,784*3]).shape #2a_2 = tf.reshape(a,[4,-1]).shape #和2等价aprint (a_1)print (a_2)"""28*28转为原创 2021-02-08 17:32:41 · 176 阅读 · 1 评论 -
词云应用
# -*- coding:utf-8 -*-from wordcloud import WordCloud,ImageColorGeneratorimport matplotlib.pyplot as pltimport jiebaimport numpy as npfrom PIL import Imageimport randomimport jieba.analysedef word_umaru1(path:"file"):#english text text = ope原创 2021-02-02 10:35:25 · 409 阅读 · 2 评论 -
日语语音合成系统
#! /usr/bin/python3import PySimpleGUI as sgimport glob, os, tempfile, subprocessimport winsoundimport datetime# -----------------------------------root=os.path.abspath(os.path.dirname(__file__))os.chdir(root)OJT_COMMAND = "open_jtalk.exe"VO原创 2021-02-01 21:46:51 · 500 阅读 · 0 评论 -
tensorflow2.0-Tensor创建
constantdata = tf.constant([2])data1 = tf.constant(1)data2 = tf.constant([1,2])data3 = tf.constant([True,False])data4 = tf.constant(["T","H","F"])print (data)print (data1)print (data2)print (data3)print (data4)"""result: tf.Tensor([2], shape=(原创 2021-02-01 19:05:34 · 123 阅读 · 0 评论 -
tensoflow2.0-数据类型
基本类型# -*- coding: utf-8 -*-import tensorflow as tfimport numpy as np"""constant(value, dtype=None, shape=None, name='Const')Creates a constant tensor from a tensor-like object."""#整型数据l11 = tf.constant(1,4)print (l11)l12 = tf.constant([1,2,..原创 2021-01-27 18:02:42 · 125 阅读 · 1 评论 -
open_jtalk实现日语语音系统
#coding: utf-8import subprocessfrom datetime import datetimeimport winsounddef jtalk(t): OPENJTALK_BINPATH = 'C://open_talk/open_jtalk-1.11/bin' OPENJTALK_DICPATH = 'C://open_talk/open_jtalk-1.11/dic' OPENJTALK_VOICEPATH = 'C://open_talk/原创 2021-01-29 17:55:09 · 655 阅读 · 0 评论 -
PCA手写数字降维
import numpy as npimport matplotlib.pyplot as pltfrom sklearn.datasets import load_digitsfrom sklearn.neural_network import MLPClassifierfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import classification_report,confusion_..原创 2021-01-17 16:44:27 · 391 阅读 · 0 评论 -
密度聚类_DBscan
import numpy as npimport matplotlib.pyplot as pltfrom sklearn import datasetsfrom sklearn.cluster import DBSCANfrom sklearn.cluster import KMeansdef draw_pic(data,result): plt.rcParams['font.sans-serif']=['SimHei'] plt.rcParams['axes.unicode_.原创 2021-01-15 17:11:14 · 120 阅读 · 2 评论 -
聚类_Kmeans优化
代价函数最小import numpy as npimport matplotlib.pyplot as pltfrom sklearn.datasets import load_irisdef distance(vex1,vex2): return np.sqrt(np.sum(np.power(vex1-vex2,2)))def kMeans_way(S,k,distMeas=distance): m=np.shape(S)[0] sampleTag = np.zero原创 2021-01-15 16:43:19 · 216 阅读 · 2 评论 -
聚类_Mini_Kmeans
import numpy as npimport matplotlib.pyplot as pltfrom sklearn.datasets import load_irisfrom sklearn.cluster import MiniBatchKMeansdef draw_pic(data,centers,result):plt.rcParams[‘font.sans-serif’]=[‘SimHei’]plt.rcParams[‘axes.unicode_minus’] = False.原创 2021-01-14 15:05:07 · 189 阅读 · 0 评论 -
贝叶斯模型(贝叶斯,高斯,伯努利)
import numpy as npimport matplotlib.pyplot as pltfrom sklearn.datasets import load_irisfrom sklearn import treefrom sklearn.model_selection import train_test_splitfrom sklearn import neighborsfrom sklearn.metrics import classification_report,confusio原创 2021-01-12 16:45:51 · 470 阅读 · 0 评论 -
集成学习_Stacking
import numpy as npimport matplotlib.pyplot as pltfrom sklearn.datasets import load_irisfrom sklearn import treefrom sklearn import model_selectionfrom sklearn.model_selection import train_test_splitfrom sklearn import neighborsfrom sklearn.ensemble.原创 2021-01-12 15:49:04 · 67 阅读 · 0 评论 -
集成学习_Adaboost分类
import numpy as npimport matplotlib.pyplot as pltfrom sklearn.datasets import load_irisfrom sklearn import treefrom sklearn.model_selection import train_test_splitfrom sklearn import neighborsfrom sklearn.ensemble import BaggingClassifierfrom sklea.原创 2021-01-11 17:34:19 · 86 阅读 · 0 评论 -
集成学习_随机森林分类
import numpy as npimport matplotlib.pyplot as pltfrom sklearn.datasets import load_irisfrom sklearn import treefrom sklearn.model_selection import train_test_splitfrom sklearn import neighborsfrom sklearn.ensemble import BaggingClassifierfrom sklea.原创 2021-01-11 16:28:44 · 122 阅读 · 0 评论 -
决策树_非线性分类
import numpy as npimport matplotlib.pyplot as pltfrom math import sqrtfrom sklearn.linear_model import *from sklearn.metrics import *from sklearn import preprocessingfrom numpy import genfromtxtimport randomfrom sklearn import *from sklearn.prepro原创 2021-01-10 16:20:39 · 117 阅读 · 0 评论 -
决策树_线性分类
import numpy as npimport matplotlib.pyplot as pltfrom sklearn.datasets import load_irisfrom sklearn import preprocessingfrom sklearn import treefrom sklearn.feature_extraction import DictVectorizerimport csvfrom sklearn import preprocessingfrom nu原创 2021-01-10 16:14:53 · 218 阅读 · 2 评论 -
决策树
判断一个人是否买电脑的例子,建立决策树。import numpy as npimport matplotlib.pyplot as pltfrom sklearn.datasets import load_irisfrom sklearn import preprocessingfrom sklearn import treefrom sklearn.feature_extraction import DictVectorizerimport csvdef read_data(fil..原创 2021-01-09 16:07:19 · 136 阅读 · 2 评论 -
鸢尾花_KNN分类
import numpy as npimport matplotlib.pyplot as pltfrom sklearn import datasetsfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import *import randomimport operatordef knn(x_test,x_data,y_data,k= 5): x_data_size = x_data.s原创 2021-01-06 17:01:04 · 252 阅读 · 0 评论 -
BP神经网络
import numpy as npimport matplotlib.pyplot as pltfrom math import sqrtfrom sklearn import linear_modelimport randomdef create_data(): X=np.array( [ [1,0,0], [1,0,1], [1,1,0], [1,1,1] ]) ...原创 2021-01-06 12:24:25 · 97 阅读 · 0 评论 -
Kmeans_鸢尾花聚类
import numpy as npimport matplotlib.pyplot as pltfrom sklearn.datasets import load_irisdef distance(vex1,vex2): return np.sqrt(np.sum(np.power(vex1-vex2,2)))def kMeans_way(S,k,distMeas=distance): m=np.shape(S)[0] sampleTag = np.zeros(m原创 2021-01-04 15:51:37 · 1243 阅读 · 0 评论 -
线性神经网络(异或)
import numpy as npimport matplotlib.pyplot as pltfrom math import sqrtfrom sklearn import linear_modelimport randomdef create_data(): X=np.array( [ [1,3,3], [1,4,3], [1,1,1], [1,0,2] ]) Y= n.原创 2021-01-02 12:31:03 · 112 阅读 · 2 评论 -
单层感知机
![在这里插入图片描述](https://img-blog.csdnimg.cn/20210101124538726.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzM4NjQxOTg1,size_16,color_FFFFFF,t_70)import numpy as npimport matplotlib.pyplot as pl原创 2021-01-01 12:51:41 · 200 阅读 · 0 评论 -
逻辑回归_非线性
手写import numpy as npimport matplotlib.pyplot as pltfrom math import sqrtfrom sklearn.linear_model import *from sklearn.metrics import *from sklearn import preprocessingfrom numpy import genfromtxtimport randomfrom sklearn import *from sklearn.pre原创 2020-12-31 15:09:29 · 94 阅读 · 0 评论 -
逻辑回归_线性
import numpy as npimport matplotlib.pyplot as pltfrom math import sqrtfrom sklearn.linear_model import *from sklearn.metrics import *from sklearn import preprocessingfrom numpy import genfromtxtimport randomdef get_vertix(x_data,y_data): pr...原创 2020-12-31 11:52:54 · 85 阅读 · 0 评论 -
Lasso 回归和弹性网
import numpy as npimport matplotlib.pyplot as pltfrom math import sqrtfrom sklearn import linear_modelimport randomfrom numpy import genfromtxtdef main(): data = genfromtxt("longley.csv",delimiter=",") print (data) x_ =data[1:,2:] y..原创 2020-12-30 11:19:03 · 151 阅读 · 0 评论 -
多元方程岭回归
调用sklearn岭回归import numpy as npimport matplotlib.pyplot as pltfrom math import sqrtfrom sklearn import linear_modelimport randomfrom numpy import genfromtxt def main(): data = genfromtxt("longley.csv",delimiter=",") #print (data) x原创 2020-12-29 17:49:32 · 320 阅读 · 2 评论 -
标准方程法(岭回归)
import numpy as npimport matplotlib.pyplot as pltfrom math import sqrtfrom sklearn.linear_model import *import randomfrom numpy import genfromtxtdef create_vertix(n):vertix_x = []vertix_y = []for i in range(n):x=i*4-2.5y = x/2+4 +random.rando..原创 2020-12-29 11:40:10 · 282 阅读 · 1 评论 -
多项式回归
多项式形式import numpy as npimport randomfrom sklearn.linear_model import LinearRegressionfrom sklearn.preprocessing import PolynomialFeaturesimport matplotlib.pyplot as pltdef create_vertix(n): vertix_x = [] vertix_y = [] for i in range(n)原创 2020-12-28 20:36:01 · 149 阅读 · 0 评论 -
线性回归
一元线性回归手工写法import numpy as npimport matplotlib.pyplot as pltfrom math import sqrtimport randomdef create_vertix(n): vertix_x = [] vertix_y = [] for i in range(n): x=i*4-2.5 y = x/2+4 +random.random() vertix_x .ap原创 2020-12-28 18:10:22 · 98 阅读 · 4 评论 -
【TensorFlow2.0】训练本地图片进行手写体数字识别
配置tensorflow-gpu环境首先,配置tensorflow-gpu环境。(不使用GPU环境运行出错)我的环境配置:python3.7.9cuda_10.0.130_411.31_win10cudnn-10.0-windows10-x64-v7.5.0.56配置步骤#coding=utf-8import tensorflow as tfimport numpy as npimport matplotlib.pyplot as pltfrom PIL import Imagei原创 2020-11-06 14:25:44 · 821 阅读 · 0 评论 -
tensorflow 2.0-根据图片制作数据集
#coding=utf-8 import tensorflow as tf import numpy as np import matplotlib.pyplot as plt from PIL import Image import datetime import os root=os.path.abspath(os.path.dirname(__file__)) os.chdir(root) image_train_path="train" #label_tra.原创 2020-10-30 22:01:54 · 1234 阅读 · 0 评论 -
tensorflow 2.0-基本操作
常数# -*- coding: utf-8 -*-import tensorflow as tfc1=tf.constant(2)print (c1)c2=tf.constant(2.5)print (c2)c3=tf.constant("a")print (c3)c4=tf.constant((1,-1),tf.complex64)print (c4) 常数运算c11=tf.constant(2)c12=tf.constant(4)print ((c11+c12).nump原创 2020-10-22 11:41:24 · 128 阅读 · 0 评论 -
【TensorFlow2.0】LeNet进行手写体数字识别
LeNet简介LeNet-5出自论文Gradient-Based Learning Applied to Document Recognition,是一种用于手写体字符识别的非常高效的卷积神经网络。卷积神经网络卷积神经网络能够很好的利用图像的结构信息。LeNet-5是一个较简单的卷积神经网络。下图显示了其结构:输入的二维图像,先经过两次卷积层到池化层,再经过全连接层,最后使用softmax分类作为输出层。下面我们主要介绍卷积层和池化层。LeNet1、INPUT层-输入层2、C1层-卷积层3、转载 2020-10-19 20:16:26 · 1042 阅读 · 1 评论 -
Python3.7 线性回归
# -*- coding: UTF-8 -*-import tensorflow as tfimport numpy as npimport osimport matplotlib.pyplot as pltimport timeos.environ['TF_CPP_MIN_LOG_LEVEL']='1'print ("GPU",tf.test.is_gpu_available())a=tf.constant(2.)b=tf.constant(4.)print (a*b)def原创 2020-06-30 12:34:03 · 151 阅读 · 0 评论