一个网站如何做cdn加速器,长沙公司有哪些,东阿做网站,网站问答平台推广方案一、实验目的
1. 了解SkLearn Tensorlow使用方法
2. 了解SkLearn keras使用方法
二、实验工具#xff1a;
1. SkLearn 三、实验内容 #xff08;贴上源码及结果#xff09; 使用Tensorflow对半环形数据集分
#encoding:utf-8import numpy as npfrom sklearn.datasets i…一、实验目的
1. 了解SkLearn Tensorlow使用方法
2. 了解SkLearn keras使用方法
二、实验工具
1. SkLearn 三、实验内容 贴上源码及结果 使用Tensorflow对半环形数据集分
#encoding:utf-8import numpy as npfrom sklearn.datasets import make_moonsimport tensorflow as tffrom sklearn.model_selection import train_test_splitfrom tensorflow.keras import layers,Sequential,optimizers,losses, metricsfrom tensorflow.keras.layers import Denseimport matplotlib.pyplot as plt#产生一个半环形数据集X,y make_moons(200,noise0.25,random_state100)#划分训练集和测试集X_train,X_test, y_train, y_test train_test_split(X, y, test_size0.25,random_state2)print(X.shape,y.shape)def make_plot(X,y,plot_name,XXNone, YYNone, predsNone):plt.figure()axes plt.gca()x_minX[:,0].min()-1x_maxX[:,0].max() 1y_minX[:,1].min()-1y_maxX[:,1].max() 1axes.set_xlim([x_min,x_max])axes.set_ylim([y_min,y_max])axes.set(xlabel$x 1$,ylabel$x 2$)if XX is None and YY is None and preds is None:yr y.ravel()for step in range(X[:,0].size):if yr[step] 1:plt.scatter(X[step,0],X[step,1],cb,s20,edgecolorsnone,markerx)else:plt.scatter(X[step,0],X[step,1],cr,s30,edgecolorsnone,markero)plt.show()else:plt.contour(XX,YY,preds,cmapplt.cm.spring,alpha0.8)plt.scatter(X[:, 0], X[:, 1], c y, s 20, cmapplt.cm.Greens, edgecolors k)plt.rcParams[font.sans-serif] [SimHei]plt.rcParams[axes.unicode_minus] Falseplt.title(plot_name)plt.show()make_plot(X, y, None)# 创建容器model Sequential()# 创建第一层model.add(Dense(8, input_dim 2, activation relu))for _ in range(3):model.add(Dense(32, activationrelu))# 创建最后一层,激活model.add(Dense(1, activationsigmoid))model.compile(lossbinary_crossentropy, optimizeradam, metrics[accuracy])history model.fit(X_train, y_train, epochs 30, verbose 1)# 绘制决策曲线x_min X[:,0].min() - 1x_max X[:, 0].max() 1y_min X[:1].min() - 1y_max X[:, 1].max() 1XX, YY np.meshgrid(np.arange(x_min, x_max, 0.01), np.arange(y_min, y_max, 0.01))Z np.argmax(model.predict(np.c_[XX.ravel(), YY.ravel()]), axis-1)preds Z.reshape(XX.shape)title 分类结果make_plot(X_train, y_train, title, XX, YY, preds) 使用VGGNet 识别猫狗
from tensorflow import keras from keras.applications.resnet import ResNet50 from keras.preprocessing import image# #手写文字识别 from keras.applications.resnet import preprocess_input,decodimport numpy as np# #载人 MNIST 数据集 from PIL import ImageFont,ImageDraw,Image# #拆分数据集 # (x_train,y_train),(x_test,y_test) mnist.load_data() # #将样本进行预处理,并从整数转换为浮点数 # x_train,x_testx_train/255.0,x_test /255.0 img1rC:\Users\PDHuang\Downloads\ch11\dog.jpg# #使用 tf.kerasimg2rC:\Users\PDHuang\Downloads\ch11\cat.jpg# model tf.keimg3rC:\Users\PDHuang\Downloads\ch11\deer.jpg# tf.keras.laweight_pathrC:\Users\PDHuang\Downloads\ch11\resnet50_weightimgimage.load_img(img1,target_size(224,224))# tf.keras.ximage.img_to_array(img)# tf.keras.layers.Dense(10,activxnp.expand_dims(x,axis0)# ]) xpreprocess_input(x)# #设置模型的优化器和损失函数 def get_model():# model.compile(optimizeradam,losssparsemodelResNet50(weightsweight_path)# #训练并验证模型 print(model.summary())# model.fit(x_train,y_train,epochsreturn model# model.evaluate(x_test,y_test,verbose2) modelget_model() #预测图片 predsmodel.predict(x) #打印出top-5的结果 print(predicted,decode_predictions(preds,top5)[0]) 使用深度学习进行手写数字识别
#手写文字识别 import tensorflow as tf #载人 MNIST 数据集 mnist tf.keras.datasets.mnist #拆分数据集 (x_train,y_train),(x_test,y_test) mnist.lo#将样本进行预处理,并从整数转换为浮点数 x_train,x_testx_train/255.0,x_test /255.0#使用 tf.keras.Sequential将模型的各层堆看,并设置参数 model tf.keras.models.Sequential([ tf.keras.layers.Flatten(input_shape(28tf.keras.layers.Dense(128,activationrtf.keras.layers.Dropout(0.2), tf.keras.layers.Dense(10,activationso]) #设置模型的优化器和损失函数 model.compile(optimizeradam,losssparse#训练并验证模型 model.fit(x_train,y_train,epochs5) model.evaluate(x_test,y_test,verbose2) 使用Tensorflow keras 实现人脸识别
from os import listdirimport numpy as npfrom PIL import Imageimport cv2from spyder.plugins.findinfiles.widgets.combobox import FILE_PATHfrom tensorflow.keras.models import Sequential, load_modelfrom tensorflow.keras.layers import Dense, Activation, Convolution2D,MaxPooling2D,Flattenfrom sklearn.model_selection import train_test_splitfrom tensorflow.python.keras.utils import np_utils#读取人脸图片数据def img2vector(fileNamestr):#创建向量returnVectnp.zeros((57,47))image Image.open(fileNamestr).convert(L)imgnp.asarray(image).reshape(57,47)return img#制作人脸数据集def GetDataset(imgDataDir):print(| Step1 |: Get dataset...)imgDataDirC:/Users/PDHuang/Downloads/ch11/faces_4/FileDirlistdir(imgDataDir)m len(FileDir)imgarray[]hwLabels[]hwdata[]#逐个读取文件for i in range(m):#提取子目录classNameisubdirNameC:/Users/PDHuang/Downloads/ch11/faces_4/str(FileDir[i])/fileNames listdir(subdirName)lenFileslen(fileNames)#提取文件名for j in range(lenFiles):fileNamestrsubdirNamefileNames[j]hwLabels.append(className)imgarrayimg2vector(fileNamestr)hwdata.append(imgarray)hwdata np.array(hwdata)return hwdata,hwLabels,6# CNN 模型类class MyCNN(object):FILE_PATH C:/Users/PDHuang/Downloads/ch11/face_recognition.h5picHeight57picwidth47#模型存储/读取目录#模型的人脸图片长47,宽57def __init__(self):self.model None#获取训练数据集def read_trainData(self,dataset):self.datasetdataset#建立 Sequential模型,并赋予参数def build_model(self):print(| step2 |:Init CNN model...)self.modelSequential()print(self.dataset.x train.shape[1:],self.dataset.X_train.shape[1:])self.model.add(Convolution2D(filters32,kernel_size(5,5),paddingsame,#dim orderingth,input_shapeself.dataset.X_train.shape[1:]))self.model.add(Activation(relu))self.model.add(MaxPooling2D(pool_size(2,2),strides(2,2),paddingsame))self.model.add(Convolution2D(filters64,kernel_size(5,5),paddingsame))self.model.add(Activation(relu))self.model.add(MaxPooling2D(pool_size(2,2),strides(2,2),paddingsame))self.model.add(Flatten())self.model.add(Dense(512))self.model.add(Activation(relu))self.model.add(Dense(self.dataset.num_classes))self.model.add(Activation(softmax))self.model.summary()# 模型训练def train_model(self):print(| Step3 l: Train CNN model...)self.model.compile(optimizeradam, losscategorical_crossentropy,metrics [accuracy])# epochs:训练代次;batch size:每次训练样本数self.model.fit(self.dataset.X_train, self.dataset.Y_train, epochs10,batch_size20)def evaluate_model(self):loss, accuracy self.model.evaluate(self.dataset.X_test, self.dataset.Y_test)print(|Step4|:Evaluate performance...)print(-------------------------------)print(Loss Value is:, loss)print(Accuracy Value is :, accuracy)def save(self, file_path FILE_PATH):print(| Step5 l: Save model...)self.model.save(file_path)print(Model,file_path, is successfully saved.)def predict(self, input_data):prediction self.model.predict(input_data)return prediction#建立一个用于存储和格式化读取训练数据的类class DataSet(object):def __init__(self, path):self.num_classes Noneself.X_train Noneself.X_test Noneself.Y_train Noneself.Y_test Noneself.picwidth47self.picHeight57self.makeDataSet(path)#在这个类初始化的过程中读取path下的训练数据def makeDataSet(self, path):#根据指定路径读取出图片、标签和类别数imgs,labels,classNum GetDataset(path)#将数据集打乱随机分组X_train,X_test,y_train,y_test train_test_split(imgs, labels, test_size0.2,random_state1)#重新格式化和标准化X_trainX_train.reshape(X_train.shape[0],1,self.picHeight, self.picwidth)/255.0X_testX_test.reshape(X_test.shape[0],1,self.picHeight, self.picwidth)/255.0X_trainX_train.astype(float32)X_testX_test.astype(float32)#将labels 转成 binary class matricesY_trainnp_utils.to_categorical(y_train, num_classesclassNum)Y_test np_utils.to_categorical(y_test,num_classesclassNum)#将格式化后的数据赋值给类的属性上self.X_trainX_trainself.X_testX_testself.Y_train Y_trainself.Y_test Y_testself.num_classesclassNum#人脸图片目录dataset DataSet(C:/Users/PDHuang/Downloads/ch11/faces_4/)model MyCNN()model.read_trainData(dataset)model.build_model()model.train_model()model.evaluate_model()model.save()import osimport cv2import numpy as npfrom tensorflow.keras.models import load_modelhwdata []hwLabels []classNum 0picHeight57picwidth47#人物标签(编号 0~5)#图像高度#图像宽度#根据指定路径读取出图片、标签和类别数hwdata,hwLabels,classNum GetDataset(C:/Users/PDHuang/Downloads/ch11/faces_4/)#加载模型if os.path.exists(face recognition.h5):model load_model(face recognition.h5)else:print(build model first)#加载待判断图片photo cv2.imread(C:/Users/PDHuang/Downloads/ch11/who.jpg)#待判断图片调整resized_photocv2.resize(photo,(picHeight, picwidth)) #调整图像大小recolord_photocv2.cvtColor(resized_photo, cv2.COLOR_BGR2GRAY)#将图像调整成灰度图recolord_photo recolord_photo.reshape((1,1,picHeight,picwidth))recolord_photo recolord_photo/255#人物预测print(| Step3 |:Predicting......)result model.predict(recolord_photo)max_indexnp.argmax(result)#显示结果print(The predict result is Person,max_index 1)cv2.namedWindow(testperson,0);cv2.resizeWindow(testperson,300,350);cv2.imshow(testperson,photo)cv2.namedWindow(PredictResult,0);cv2.resizeWindow(PredictResult,300,350);cv2.imshow(predictResult,hwdata[max_index * 10])#print(resultrile)k cv2.waitKey(0)#按Esc 键直接退出if k 27:cv2.destroyWindow() 使用Tensorflow keras 实现电影评论情感分类
# 导包import matplotlib as mplimport matplotlib.pyplot as pltimport numpy as npimport pandas as pdimport os# 导入tfimport tensorflow as tffrom tensorflow import kerasprint(tf.__version__)print(keras.__version__)# 加载数据集# num_words只取10000个词作为词表imdb keras.datasets.imdb(train_x_all, train_y_all),(test_x, test_y)imdb.load_data(num_words10000)# 查看数据样本数量print(Train entries: {}, labels: {}.format(len(train_x_all), len(train_y_all)))print(Train entries: {}, labels: {}.format(len(test_x), len(test_y)))print(train_x_all[0]) # 查看第一个样本数据的内容print(len(train_x_all[0])) # 查看第一个和第二个训练样本的长度不一致print(len(train_x_all[1]))# 构建字典 两个方法一个是id映射到字一个是字映射到idword_index imdb.get_word_index()word2id { k:(v3) for k, v in word_index.items()}word2id[PAD] 0word2id[START] 1word2id[UNK] 2word2id[UNUSED] 3id2word {v:k for k, v in word2id.items()}def get_words(sent_ids):return .join([id2word.get(i, ?) for i in sent_ids])sent get_words(train_x_all[0])print(sent)# 句子末尾进行填充train_x_all keras.preprocessing.sequence.pad_sequences(train_x_all,valueword2id[PAD],paddingpost, #pre表示在句子前面填充 post表示在句子末尾填充maxlen256)test_x keras.preprocessing.sequence.pad_sequences(test_x,valueword2id[PAD],paddingpost,maxlen256)print(train_x_all[0])print(len(train_x_all[0]))print(len(train_x_all[1]))#模型编写vocab_size 10000model keras.Sequential()model.add(keras.layers.Embedding(vocab_size, 16))model.add(keras.layers.GlobalAveragePooling1D())model.add(keras.layers.Dense(16, activationrelu))model.add(keras.layers.Dense(1, activationsigmoid))model.summary()model.compile(optimizeradam, losskeras.losses.binary_crossentropy, metrics[accuracy])train_x, valid_x train_x_all[10000:], train_x_all[:10000]train_y, valid_y train_y_all[10000:], train_y_all[:10000]# callbacks Tensorboard, earlystoping, ModelCheckpoint# 创建一个文件夹用于放置日志文件logdir os.path.join(callbacks)if not os.path.exists(logdir):os.mkdir(logdir)output_model_file os.path.join(logdir, imdb_model.keras)# 当训练模型到什么程度的时候就停止执行 也可以直接不用然后直接训练callbacks [# 保存的路径使用TensorBoard就可以用命令tensorboard --logdir callbacks 来分析结果keras.callbacks.TensorBoard(logdir),# 保存最好的模型keras.callbacks.ModelCheckpoint(filepathoutput_model_file, save_best_onlyTrue),# 当精度连续5次都在1乘以10的-1次方之后停止训练keras.callbacks.EarlyStopping(patience5, min_delta1e-3)]history model.fit(train_x, train_y,epochs40,batch_size512,validation_data(valid_x, valid_y),callbacks callbacks,verbose1 # 设置为1就会打印日志到控制台0就不打印)def plot_learing_show(history):pd.DataFrame(history.history).plot(figsize(8,5))plt.grid(True)plt.gca().set_ylim(0,1)plt.show()plot_learing_show(history)result model.evaluate(test_x, test_y)print(result)test_classes_list model.predict_classes(test_x)print(test_classes_list[1][0])print(test_y[1]) 使用Tensorflow keras 解决 回归问题预测汽车燃油效率
# 导包import matplotlib as mplimport matplotlib.pyplot as pltimport numpy as npimport pandas as pdimport osimport pathlibimport seaborn as sns# 导入tfimport tensorflow as tffrom tensorflow import kerasprint(tf.__version__)print(keras.__version__)# 加载数据集dataset_path keras.utils.get_file(auto-mpg.data,http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data)print(dataset_path)# 使用pandas导入数据集column_names [MPG, Cylinders, Displacement, Horsepower, Weight, Acceleration, Model Year, Origin]raw_dataset pd.read_csv(dataset_path, namescolumn_names, na_values?, comment\t,sep , skipinitialspaceTrue)dataset raw_dataset.copy()print(dataset.tail())# 数据清洗print(dataset.isna().sum())dataset dataset.dropna()print(dataset.isna().sum())# 将origin转换成one-hot编码origin dataset.pop(Origin)dataset[USA] (origin 1) * 1.0dataset[Europe] (origin 2) * 1.0dataset[Japan] (origin 3) * 1.0print(dataset.tail())# 拆分数据集 拆分成训练集和测试集train_dataset dataset.sample(frac0.8, random_state0)test_dataset dataset.drop(train_dataset.index)# 总体数据统计train_stats train_dataset.describe()train_stats.pop(MPG)train_stats train_stats.transpose()print(train_stats)# 从标签中分类特征train_labels train_dataset.pop(MPG)test_labels test_dataset.pop(MPG)print(train_labels[0])# 数据规范化def norm(x):return (x - train_stats[mean]) / train_stats[std]norm_train_data norm(train_dataset)norm_test_data norm(test_dataset)# 构建模型def build_model():model keras.Sequential([keras.layers.Dense(512, activationrelu, input_shape[len(train_dataset.keys())]),keras.layers.Dense(256, activationrelu),keras.layers.Dense(128, activationrelu),keras.layers.Dense(64, activationrelu),keras.layers.Dense(1)])optimizer keras.optimizers.RMSprop(0.001)model.compile(lossmse, optimizeroptimizer, metrics[mae, mse])return model# 构建防止过拟合的模型加入正则项L1和L2def build_model2():model keras.Sequential([keras.layers.Dense(512, activationrelu, kernel_regularizerkeras.regularizers.l1_l2(0.001),input_shape[len(train_dataset.keys())]),keras.layers.Dense(256, activationrelu, kernel_regularizerkeras.regularizers.l1_l2(0.001)),keras.layers.Dense(128, activationrelu, kernel_regularizerkeras.regularizers.l1_l2(0.001)),keras.layers.Dense(64, activationrelu, kernel_regularizerkeras.regularizers.l1_l2(0.001)),keras.layers.Dense(1)])optimizer keras.optimizers.RMSprop(0.001)model.compile(lossmse, optimizeroptimizer, metrics[mae, mse])return model# 构建防止过拟合的模型加入正则项L1def build_model3():model keras.Sequential([keras.layers.Dense(512, activationrelu, kernel_regularizerkeras.regularizers.l1(0.001),input_shape[len(train_dataset.keys())]),keras.layers.Dense(256, activationrelu, kernel_regularizerkeras.regularizers.l1(0.001)),keras.layers.Dense(128, activationrelu, kernel_regularizerkeras.regularizers.l1(0.001)),keras.layers.Dense(64, activationrelu, kernel_regularizerkeras.regularizers.l1(0.001)),keras.layers.Dense(1)])optimizer keras.optimizers.RMSprop(0.001)model.compile(lossmse, optimizeroptimizer, metrics[mae, mse])return model# 构建防止过拟合的模型加入正则项L2def build_model4():model keras.Sequential([keras.layers.Dense(512, activationrelu, kernel_regularizerkeras.regularizers.l2(0.001),input_shape[len(train_dataset.keys())]),keras.layers.Dense(256, activationrelu, kernel_regularizerkeras.regularizers.l2(0.001)),keras.layers.Dense(128, activationrelu, kernel_regularizerkeras.regularizers.l2(0.001)),keras.layers.Dense(64, activationrelu, kernel_regularizerkeras.regularizers.l2(0.001)),keras.layers.Dense(1)])optimizer keras.optimizers.RMSprop(0.001)model.compile(lossmse, optimizeroptimizer, metrics[mae, mse])return model# 构建模型 使用dropout来防止过拟合def build_model5():model keras.Sequential([keras.layers.Dense(512, activationrelu, input_shape[len(train_dataset.keys())]),keras.layers.Dropout(0.5),keras.layers.Dense(256, activationrelu),keras.layers.Dropout(0.5),keras.layers.Dense(128, activationrelu),keras.layers.Dropout(0.5),keras.layers.Dense(64, activationrelu),keras.layers.Dropout(0.5),keras.layers.Dense(1)])optimizer keras.optimizers.RMSprop(0.001)model.compile(lossmse, optimizeroptimizer, metrics[mae, mse])return model# 构建模型 使用正则化L1和L2以及dropout来预测def build_model6():model keras.Sequential([keras.layers.Dense(512, activationrelu, kernel_regularizerkeras.regularizers.l1_l2(0.001),input_shape[len(train_dataset.keys())]),keras.layers.Dropout(0.5),keras.layers.Dense(256, activationrelu, kernel_regularizerkeras.regularizers.l1_l2(0.001)),keras.layers.Dropout(0.5),keras.layers.Dense(128, activationrelu, kernel_regularizerkeras.regularizers.l1_l2(0.001)),keras.layers.Dropout(0.5),keras.layers.Dense(64, activationrelu, kernel_regularizerkeras.regularizers.l1_l2(0.001)),keras.layers.Dropout(0.5),keras.layers.Dense(1)])optimizer keras.optimizers.RMSprop(0.001)model.compile(lossmse, optimizeroptimizer, metrics[mae, mse])return modelmodel build_model()model.summary()early_stop keras.callbacks.EarlyStopping(monitorval_loss, patience200)# 模型训练history model.fit(norm_train_data, train_labels, epochs1000, validation_split0.2, verbose0, callbacks[early_stop])def plot_history(history):hist pd.DataFrame(history.history)hist[epoch] history.epochplt.figure()plt.xlabel(Epoch)plt.ylabel(Mean Abs ERROR [PMG])plt.plot(hist[epoch], hist[mae], labelTrain Error)plt.plot(hist[epoch], hist[val_mae], labelVal Error)plt.ylim([0, 5])plt.legend()plt.figure()plt.xlabel(Epoch)plt.ylabel(Mean Squaree ERROR [PMG])plt.plot(hist[epoch], hist[mse], labelTrain Error)plt.plot(hist[epoch], hist[val_mse], labelVal Error)plt.ylim([0, 20])plt.legend()plt.show()plot_history(history)# 看下测试集合的效果loss, mae, mse model.evaluate(norm_test_data, test_labels, verbose2)print(loss)print(mae)print(mse)# 做预测test_preditions model.predict(norm_test_data)test_preditions test_preditions.flatten()plt.scatter(test_labels, test_preditions)plt.xlabel(True Values [MPG])plt.ylabel(Predictios [MPG])plt.axis(equal)plt.axis(square)plt.xlim([0, plt.xlim()[1]])plt.ylim([0, plt.ylim()[1]])_ plt.plot([-100, 100], [-100, 100])# 看一下误差分布error test_preditions - test_labelsplt.hist(error, bins25)plt.xlabel(Prediction Error [MPG])_ plt.ylabel(Count)
