import numpy as np from matplotlib import pyplot as plt from sklearn import neighbors, datasets from matplotlib.colors import ListedColormap from sklearn.neural_network import MLPClassifier ## 加载数据集 np.random.seed(0) # 使用 scikit-learn 自带的 iris 数据集 ir

#K-NN分类 import os import sys import time import operator import cx_Oracle import numpy as np import pandas as pd import tensorflow as tf conn=cx_Oracle.connect('doctor/admin@localhost:1521/tszr') cursor = conn.cursor() #获取数据集 def getdata(surgery,surg

import numpy as np import operator as op from os import listdir def classify0(inX, dataSet, labels, k): dataSetSize = dataSet.shape[0] diffMat = np.tile(inX, (dataSetSize,1)) - dataSet sqDiffMat = diffMat**2 sqDistances = sqDiffMat.sum(axis=1) distan

#用户注册.登录模块 #数据库脚本 CREATE TABLE usertable( userid number(8) primary key not null , username varchar(50) NULL, password varchar(50) NOT NULL, sex varchar(10) NOT NULL, age number(3) NOT NULL, province varchar2(50) null, area varchar(50) NOT NULL ); com

#复诊 import sys import os import time import operator import cx_Oracle import numpy as np import pandas as pd import tensorflow as tf uid = 6 sql = "select username,sex,age,province,area,bumen,ke,result,chufang,jianyi,yiyuaan,yisheng,jianchaxiang,zhen

最近忙里偷闲学习了一点机器学习的知识,看到神经网络算法时我和阿Kun便想到要将它用Python代码实现.我们用了两种不同的方法来编写它.这里只放出我的代码. MNIST数据集基于美国国家标准与技术研究院的两个数据集构建而成.训练集中包含250个人的手写数字,其中50%是高中生,50%来自人口调查局.每个训练集的数字图片像素为28x28.MNIST数据集可通过 下载链接 下载,它包含以下内容: 训练集图像:train-images-idx3-ubyte.gz,包含60000个样本 训练集类标:tr

!pip install gym import random import numpy as np import matplotlib.pyplot as plt from keras.layers import Dense, Dropout, Activation from keras.models import Sequential from keras.optimizers import Adam from keras import backend as K from collection

import tensorflow as tf w1= tf.Variable(tf.random_normal([2, 3], stddev=1, seed=1)) w2= tf.Variable(tf.random_normal([3, 1], stddev=1, seed=1)) x = tf.constant([[0.7, 0.9]]) a = tf.matmul(x, w1) y = tf.matmul(a, w2) sess = tf.Session() sess.run(w1.in

2. 神经网络的搭建以及迁移学习的测试 7.项目总结 通过本次水果图片卷积池化全连接试验分类项目的实践,我对卷积.池化.全连接等相关的理论的理解更加全面和清晰了.试验主要采用python高级编程语言的TensorFlow和Keras这两个库.在实验学习的过程中,开始时,对于TensorFlow和Keras并不是很了解,里面提供的许多方法也不熟悉,但经过老师课堂的讲解和演示一些关键的.和常用的方法或函数,以及对相关参数的传递.变化,如:权值的变化.图片尺寸的变化.图片通道的变化.偏置的设置.优化函

import tensorflow as tf import numpy as np from tensorflow.examples.tutorials.mnist import input_data #设置输入参数 batch_size = 128 test_size = 256 # 初始化权值与定义网络结构,建构一个3个卷积层和3个池化层,一个全连接层和一个输出层的卷积神经网络 # 首先定义初始化权重函数 def init_weights(shape): return tf.Variabl

import osimport numpy as npimport matplotlib.pyplot as pltfrom PIL import Image, ImageChopsfrom skimage import color,data,transform,io #获取所有数据文件夹名称fileList = os.listdir("F:\\data\\flowers")trainDataList = []trianLabel = []testDataList = []testLa

import osimport numpy as npimport matplotlib.pyplot as pltfrom PIL import Image, ImageChopsfrom skimage import color,data,transform,io #获取所有数据文件夹名称fileList = os.listdir("F:\\data\\flowers")trainDataList = []trianLabel = []testDataList = []testLa

import kerasimport matplotlib.pyplot as pltfrom keras.models import Sequentialfrom keras.layers import Dense,Activation,Flatten,Dropout,Convolution2D,MaxPooling2Dfrom keras.utils import np_utilsfrom keras.optimizers import RMSpropfrom skimage import

# coding: utf-8 # In[1]:import osimport numpy as npfrom skimage import color, data, transform, io # In[34]: import tensorflow as tfimport numpy as np train10_images = np.load('train10_images.npy')train10_labels = np.load('train10_labels.npy') y=tf.pl

import osimport kerasimport timeimport numpy as npimport tensorflow as tffrom random import shufflefrom keras.utils import np_utilsfrom skimage import color, data, transform, io trainDataDirList = os.listdir("F:\\MachineLearn\\ML-xiaoxueqi\\fruits\\t

import osimport numpy as npimport matplotlib.pyplot as pltfrom skimage import color,data,transform,io labelList = os.listdir("F:\\MachineLearn\\ML-xiaoxueqi\\fruits\\Training")allFruitsImageName = []for i in range(10): allFruitsImageName.append(

import numpy as np import matplotlib.pyplot as plt from sklearn import datasets,ensemble from sklearn.model_selection import train_test_split def load_data_classification(): ''' 加载用于分类问题的数据集 ''' # 使用 scikit-learn 自带的 digits 数据集 digits=datasets.load_d

import numpy as np import matplotlib.pyplot as plt from sklearn import datasets,ensemble from sklearn.model_selection import train_test_split def load_data_classification(): ''' 加载用于分类问题的数据集 ''' # 使用 scikit-learn 自带的 digits 数据集 digits=datasets.load_d

import numpy as np import matplotlib.pyplot as plt from sklearn import metrics from sklearn import datasets from sklearn.semi_supervised import LabelPropagation def load_data(): ''' 加载数据集 ''' digits = datasets.load_digits() ###### 混洗样本 ######## rng =

import numpy as np from matplotlib import pyplot as plt from mpl_toolkits.mplot3d import Axes3D from sklearn.neural_network import MLPClassifier def creat_data(n): ''' 创建线性可分数据集 :param n: 正例样本的个数(同时也是负例样本的个数) :return: 返回一个线性可分数据集,数据集大小为 2*n ''' np.ra