L1正则化
import tensorflow as tf
from matplotlib import pyplot as plt
import numpy as np
import pandas as pd
df = pd.read_csv('dot.csv')#读入数据/标签 生成x_train和y_train
x_data = np.array(df[['x1','x2']]) #输入特征
y_data = np.array(df['y_c'])#标签
x_train = np.vstack(x_data).reshape(-1,2)
y_train = np.vstack(y_data).reshape(-1,1)
Y_c = [['red' if y else 'blue'] for y in y_train]
#转换x的数据类型,否则后面矩阵相乘时会因数据类型问题报错
x_train = tf.cast(x_train,tf.float32)
y_train = tf.cast(y_train,tf.float32)
#from_tensor_slices 函数切片传入的张量的第一个维度,生成相应的数据集,使输入特征和标签值一一对应
train_db = tf.data.Dataset.from_tensor_slices((x_train,y_train)).batch(32)
#生成神经网络的参数,输入层为2个神经元(x1和x2),隐藏层为11个神经元,1层隐藏层,输出层为1个神经元
#用tf.Variable()保证参数可训练
w1 = tf.Variable(tf.random.normal([2,11]),dtype=tf.float32)
b1 = tf.Variable(tf.constant(0.01,shape=[11]))
w2 = tf.Variable(tf.random.normal([11,1]),dtype=tf.float32)
b2 = tf.Variable(tf.constant(0.01,shape=[1]))
lr = 0.005#学习率
epoch = 800
#训练部分:
for epoch in range(epoch):
for step,(x_train,y_train) in enumerate(train_db):
with tf.GradientTape() as tape: #在with中完成前向传播
h1 = tf.matmul(x_train,w1) + b1
h1 = tf.nn.relu(h1)
y = tf.matmul(h1,w2)+b2
#采用均方误差损失函数 mse = mean(sum(y-out)^2)
loss = tf.reduce_mean(tf.square(y_train - y))
variables = [w1,b1,w2,b2]
grads = tape.gradient(loss,variables)#loss分别对w1,b1,w2,b2求偏导
#实现梯度更新,分别更新w1,b1,w2,b2
#w1 = w1 -lr*w1_grad;tape.gradient是自动求导,结果与[w1,b1,w2,b2]索引为0 1 2 3
w1.assign_sub(lr*grads[0])
b1.assign_sub(lr*grads[1])
w2.assign_sub(lr*grads[2])
b2.assign_sub(lr*grads[3])
#每20个epoch,打印loss信息
if epoch % 20 == 0:
print('epoch:',epoch,'loss:',float(loss))
#预测部分
print("*************predict*******************")
#xx在-3到3之间以步长为0.01,yy在-3到3之间以步长0.01,生成间隔数值点
#生成网格坐标点,密度为0.1
xx,yy = np.mgrid[-3:3:.1,-3:3:.1]
#将xx,yy拉直,并合并配对为二维张量,生成二维坐标点
grid = np.c_[xx.ravel(),yy.ravel()]
grid = tf.cast(grid,tf.float32)
#将网格坐标点喂入神经网络,进行预测,probs为输出
probs = []
#把每个网格坐标点送入神经网络,得到预测值y
for x_test in grid:
#使用训练好的参数进行预测
h1 = tf.matmul([x_test],w1) + b1
h1 = tf.nn.relu(h1)
y = tf.matmul(h1,w2) + b2
probs.append(y)
#取第0列给x1,取第1列给x2
x1 = x_data[:,0]
x2 = x_data[:,1]
#probs的shape调整成xx的样子
probs = np.array(probs).reshape(xx.shape)
plt.scatter(x1,x2,color=np.squeeze(Y_c))#画出x1,x2散点
#squeeze去掉维度是1的维度,相当于去掉['red']['blue'],内层括号变为['red']['blue']
#把坐标xx yy和对应的值probs放入contour函数,给probs值为0.5的所有点上色,plt.show()后,显示的是红蓝点的分界线
plt.contour(xx,yy,probs,levels=[.5])#画出预测值y为0.5的曲线
plt.show()
#读入红蓝点,画出分割线,不包含正则化
#不清楚的数据,建议print出来查看
加入L2正则化
#导入所需模块
import tensorflow as tf
from matplotlib import pyplot as plt
import numpy as np
import pandas as pd
#读入数据/标签,生成x_train,y_train
df = pd.read_csv('dot.csv')
x_data = np.array(df[['x1','x2']])
y_data = np.array(df['y_c'])
x_train = x_data
y_train = y_data.reshape(-1,1)
Y_c = [['red' if y else 'blue'] for y in y_train]
#转换x的数据类型,否则后面矩阵相乘时会因为数据类型问题报错
x_train = tf.cast(x_train,tf.float32)
y_train = tf.cast(y_train,tf.float32)
#from_tensor_slices 函数切分传入的张量的第一个维度,生成相应的数据集,使输入特征和标签值一一对应
train_db = tf.data.Dataset.from_tensor_slices((x_train,y_train)).batch(32)
#生成神经网络的参数,输入层为2个神经元,隐藏层为11个神经元,1层隐藏层,输出层为1个神经元
#用tf.Variable()保证参数可训练
w1 = tf.Variable(tf.random.normal([2,11]),dtype=tf.float32)
b1 = tf.Variable(tf.constant(0.01,shape=[11]))
w2 = tf.Variable(tf.random.normal([11,1]),dtype=tf.float32)
b2 = tf.Variable(tf.constant(0.01,shape=[1]))
lr = 0.005#学习率
epoch = 800#循环数
#训练部分
for epoch in range(epoch):
for step,(x_train,y_train) in enumerate(train_db):
with tf.GradientTape() as tape:
h1 = tf.matmul(x_train,w1) + b1
h1 = tf.nn.relu(h1)
y = tf.matmul(h1,w2) + b2
#采用均方误差损失函数 mse = mean(sum(y-out)^2)
loss_mse = tf.reduce_mean(tf.square(y_train - y))
#添加L2正则化
loss_regularization = []
#tf.nn,l2_loss(w) = sum(w**2)/2
loss_regularization.append(tf.nn.l2_loss(w1))
loss_regularization.append(tf.nn.l2_loss(w2))
#求和
loss_regularization = tf.reduce_sum(loss_regularization)
loss = loss_mse + 0.03*loss_regularization
#计算loss,对各个参数的梯度
variables = [w1,b1,w2,b2]
grads = tape.gradient(loss,variables)
#实现梯度更新
#w1 = w1 - lr*w1_grad
w1.assign_sub(lr*grads[0])
b1.assign_sub(lr*grads[1])
w2.assign_sub(lr*grads[2])
b2.assign_sub(lr*grads[3])
#每20个epoch,打印loss信息
if epoch %20 == 0:
print('epoch:',epoch,'loss:',float(loss))
#预测部分
print("*************predict*******************")
xx,yy = np.mgrid[-3:3:.1,-3:3:.1]
grid = np.c_[xx.ravel(),yy.ravel()]
grid = tf.cast(grid,tf.float32)
probs = []
for x_predict in grid:
h1 = tf.matmul([x_predict],w1) + b1
h1 = tf.nn.relu(h1)
y = tf.matmul(h1,w2) + b2
probs.append(y)
x1 = x_data[:,0]
x2 = x_data[:,1]
probs = np.array(probs).reshape(xx.shape)
plt.scatter(x1,x2,color=np.squeeze(Y_c))
plt.contour(xx,yy,probs,levels=[.5])
plt.show()