tensorflow实现二分类

读万卷书，不如行万里路。之前看了不少机器学习方面的书籍，但是实战很少。这次因为项目接触到tensorflow，用一个最简单的深层神经网络实现分类和回归任务。

首先说分类任务，分类任务的两个思路：

如果是多分类，输出层为计算出的预测值Z3(1,classes)，可以利用softmax交叉熵损失函数，将Z3中的值转化为概率值，概率值最大的即为预测值。

在tensorflow中，多分类的损失函数为：

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=Z3, labels=Y))

为了匹配Z3和Y的尺寸，需要将输入Y进行one-hot编码，

from keras.utils import to_categorical

Y_train = to_categorical(Y_train)
计算准确性：

correct_prediction = tf.equal(tf.argmax(Z3,axis=1), tf.argmax(Y,1) )  # tf.argmax找出每一列最大值的索引
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))  # tf.cast转化数据类型
print("Train Accuracy:", sess.run(accuracy,feed_dict={X: X_train, Y: Y_train}))
print("Test Accuracy: ",sess.run(accuracy,feed_dict={X:X_test,Y:Y_test}))
完整代码如下：

# -*- coding: utf-8 -*-

import numpy as np
import tensorflow as tf
import math
from sklearn.model_selection import train_test_split
from keras.utils import to_categorical
import keras
import scipy
import os
import csv
import pandas as pd
from keras.utils import to_categorical

from sklearn.preprocessing import normalize


#创建placeholders对象
def create_placeholders(n_x,n_y):
    """
    placeholder是TensorFlow的占位符节点，由placeholder方法创建，其也是一种常量，但是由用户在调用run方法是传递的.
    也可以将placeholder理解为一种形参。
    即其不像constant那样直接可以使用，需要用户传递常数值。
    """
    X=tf.placeholder(tf.float32,shape=[None,n_x],name='X')
    Y=tf.placeholder(tf.float32,shape=[None,n_y],name='Y')

    return X,Y

#初始化参数
def initialize_parameters(m,n):
    #设置种子后，每次生成的参数都是相同的，保证重复实验的结果可以参考
    tf.set_random_seed(1)
    W1 = tf.get_variable("W1", shape=[n, n], initializer=tf.contrib.layers.xavier_initializer(seed=1))
    b1 = tf.get_variable("b1", shape=[1, n], initializer=tf.zeros_initializer())
    W2=tf.get_variable("W2",shape=[n,2],initializer=tf.contrib.layers.xavier_initializer(seed=1))
    b2=tf.get_variable("b2",shape=[1,2],initializer=tf.zeros_initializer())
    parameters={
        "W1": W1,
        "b1":b1,
        "W2":W2,
        "b2":b2
    }
    return parameters

#前向传播
def forward_propagation(X,parameters,lambd):
    W1=parameters['W1']
    b1=parameters['b1']
    W2 = parameters['W2']
    b2 = parameters['b2']

    #使用L1正则化
    tf.add_to_collection('losses',tf.contrib.layers.l1_regularizer(lambd)(W1))
    tf.add_to_collection('losses', tf.contrib.layers.l1_regularizer(lambd)(W2))

    A1=tf.nn.relu(tf.matmul(X,W1)+b1)
    Z3=tf.matmul(A1,W2)+b2

    return  Z3

def compute_cost(Z3, Y):
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=Z3, labels=Y))
    tf.add_to_collection('losses',cost)
    return tf.add_n(tf.get_collection('losses'))

def model(X_train, Y_train,X_test,Y_test, learning_rate=0.01,minibatch_size=10, num_epochs=30000, print_cost=True):

    tf.set_random_seed(1)
    (m, n_x) = X_train.shape
    n_y = Y_train.shape[1]
    costs = []
    # 创建Placeholders,一个张量
    X,Y=create_placeholders(n_x,n_y)
    print(X.shape, Y.shape)
    # 初始化参数
    parameters=initialize_parameters(m,n_x)
    # 前向传播
    Z3=forward_propagation(X,parameters,0.002)
    # 计算代价
    cost = compute_cost(Z3, Y)

    # 后向传播: 定义tensorflow optimizer对象，这里使用AdamOptimizer.
    optimizer=tf.train.AdadeltaOptimizer(learning_rate=learning_rate).minimize(cost)
    # optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(cost)
    # 初始化所有参数
    init=tf.global_variables_initializer()

    # 启动session来计算tensorflow graph
    with tf.Session() as sess:
        sess.run(init)
        for epoch in range(num_epochs):
            epoch_cost=sess.run([optimizer,cost],feed_dict={X:X_train,Y:Y_train})
            test_cost=sess.run(cost,feed_dict={X:X_test,Y:Y_test})
            epoch_cost=epoch_cost[1]

            if print_cost==True and epoch%100==0:
                print("Cost after epoch %i: %f" %(epoch,epoch_cost))
                print("test_cost: ",test_cost)

        # lets save the parameters in a variable
        parameters = sess.run(parameters)
        print("Parameters have been trained!")
        # 神经网络经过训练后得到的值

        correct_prediction = tf.equal(tf.argmax(Z3,axis=1), tf.argmax(Y,1) )  # tf.argmax找出每一列最大值的索引
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))  # tf.cast转化数据类型
        print("Train Accuracy:", sess.run(accuracy,feed_dict={X: X_train, Y: Y_train}))
        print("Test Accuracy: ",sess.run(accuracy,feed_dict={X:X_test,Y:Y_test}))


        return parameters

def loaddata(file):

    fr=open(file,'r', encoding='utf-8-sig')
    reader = csv.reader(fr)
    data=[]
    fltLine=[]
    for line in reader:
        data.append(line)
    data=np.mat(data)
    data=data.astype(np.float32)
    X=data[1:,0:-1]
    Y=data[1:,-1]
    X=normalize(X,axis=0,norm='max')
    X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.3, random_state=42)
    return X_train, X_test, Y_train, Y_test


if __name__=='__main__':

    X_train, X_test, Y_train, Y_test= loaddata('./data3.csv')
    Y_train=to_categorical(Y_train)
    Y_test = to_categorical(Y_test)
    parmeters=model(X_train,Y_train,X_test,Y_test)
    

另一种是单纯的针对二分类，主要有两点不同，一是损失函数的使用：

输出层Z3为(1,1)

cost= tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=Z3, labels=Y))
另一个就是计算准确率：

one = tf.ones_like(Z3)
zero = tf.zeros_like(Z3)
label = tf.where(tf.less(Z3, 0.5), x=zero, y=one)

correct_prediction = tf.equal(label, Y)  # tf.argmax找出每一列最大值的索引
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))  # tf.cast转化数据类型
print("Train Accuracy:", sess.run(accuracy, feed_dict={X: X_train, Y: Y_train}))
print("Test Accuracy: ", sess.run(accuracy, feed_dict={X: X_test, Y: Y_test}))
完整代码如下：

# -*- coding: utf-8 -*-

import numpy as np
import tensorflow as tf
import math
from sklearn.model_selection import train_test_split
from keras.utils import to_categorical
import keras
import scipy
import os
import csv
import pandas as pd
from keras.utils import to_categorical

from sklearn.preprocessing import normalize


# 创建placeholders对象
def create_placeholders(n_x, n_y):
    """
    placeholder是TensorFlow的占位符节点，由placeholder方法创建，其也是一种常量，但是由用户在调用run方法是传递的.
    也可以将placeholder理解为一种形参。
    即其不像constant那样直接可以使用，需要用户传递常数值。
    """
    X = tf.placeholder(tf.float32, shape=[None, n_x], name='X')
    Y = tf.placeholder(tf.float32, shape=[None, n_y], name='Y')

    return X, Y


# 初始化参数
def initialize_parameters(m, n):
    # 设置种子后，每次生成的参数都是相同的，保证重复实验的结果可以参考
    tf.set_random_seed(1)
    W1 = tf.get_variable("W1", shape=[n, n], initializer=tf.contrib.layers.xavier_initializer(seed=1))
    b1 = tf.get_variable("b1", shape=[1, n], initializer=tf.zeros_initializer())
    W2 = tf.get_variable("W2", shape=[n, 1], initializer=tf.contrib.layers.xavier_initializer(seed=1))
    b2 = tf.get_variable("b2", shape=[1, 1], initializer=tf.zeros_initializer())
    parameters = {
        "W1": W1,
        "b1": b1,
        "W2": W2,
        "b2": b2
    }
    return parameters


# 前向传播
def forward_propagation(X, parameters, lambd):
    W1 = parameters['W1']
    b1 = parameters['b1']
    W2 = parameters['W2']
    b2 = parameters['b2']

    # 使用L1正则化
    #tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(lambd)(W1))
    #tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(lambd)(W2))

    #A1 = tf.nn.relu(tf.matmul(X, W1) + b1)
    Z3 = tf.matmul(X, W2) + b2
    #Z3=tf.sigmoid(Z3)

    return Z3


def compute_cost(Z3, Y):
    # 经过激活函数处理后的交叉熵
    #cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=Z3, labels=Y))
    cost= tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=Z3, labels=Y))
    #cost=-tf.reduce_mean(Y*tf.log(tf.clip_by_value(Z3,1e-10,1.0)))
    tf.add_to_collection('losses', cost)
    return tf.add_n(tf.get_collection('losses'))


def model(X_train, Y_train, X_test, Y_test, learning_rate=0.05, minibatch_size=10, num_epochs=50000, print_cost=True):
    tf.set_random_seed(1)
    (m, n_x) = X_train.shape
    n_y = Y_train.shape[1]
    costs = []
    # 创建Placeholders,一个张量
    X, Y = create_placeholders(n_x, n_y)
    print(X.shape, Y.shape)
    # 初始化参数
    parameters = initialize_parameters(m, n_x)
    # 前向传播
    Z3 = forward_propagation(X, parameters, 0.001)
    # 计算代价
    cost = compute_cost(Z3, Y)

    # 后向传播: 定义tensorflow optimizer对象，这里使用AdamOptimizer.
    optimizer = tf.train.AdadeltaOptimizer(learning_rate=learning_rate).minimize(cost)
    # optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(cost)
    # 初始化所有参数
    init = tf.global_variables_initializer()

    # 启动session来计算tensorflow graph
    with tf.Session() as sess:
        sess.run(init)
        for epoch in range(num_epochs):
            epoch_cost = sess.run([optimizer, cost], feed_dict={X: X_train, Y: Y_train})
            test_cost = sess.run(cost, feed_dict={X: X_test, Y: Y_test})
            epoch_cost = epoch_cost[1]

            if print_cost == True and epoch % 100 == 0:
                print("Cost after epoch %i: %f" % (epoch, epoch_cost))
                print("test_cost: ", test_cost)

        # lets save the parameters in a variable
        parameters = sess.run(parameters)
        print("Parameters have been trained!")
        # 神经网络经过训练后得到的值
        # print(sess.run(Y,feed_dict={Y:Y_train}))
        # Y=tf.cast(Y,tf.int64)

        one = tf.ones_like(Z3)
        zero = tf.zeros_like(Z3)
        label = tf.where(tf.less(Z3, 0.5), x=zero, y=one)

        correct_prediction = tf.equal(label, Y)  # tf.argmax找出每一列最大值的索引
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))  # tf.cast转化数据类型
        print("Train Accuracy:", sess.run(accuracy, feed_dict={X: X_train, Y: Y_train}))
        print("Test Accuracy: ", sess.run(accuracy, feed_dict={X: X_test, Y: Y_test}))

        return parameters


def loaddata(file):
    fr = open(file, 'r', encoding='utf-8-sig')
    reader = csv.reader(fr)
    data = []
    fltLine = []
    for line in reader:
        data.append(line)
    data = np.mat(data)
    data = data.astype(np.float32)
    X = data[1:, 0:-1]
    Y = data[1:, -1]
    X = normalize(X, axis=0, norm='max')
    X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.3, random_state=42)
    return X_train, X_test, Y_train, Y_test


if __name__ == '__main__':

    X_train, X_test, Y_train, Y_test = loaddata('./data3.csv')
    #Y_train = to_categorical(Y_train)
    #Y_test = to_categorical(Y_test)

    parmeters = model(X_train, Y_train, X_test, Y_test)