Tensorflow学习

一、处理数据的结构

案例代码如下:

import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
import numpy as np# create data
x_data = np.random.rand(100).astype(np.float32)
y_data = x_data*0.1 + 0.3# 创建结构(一维结构)
Weights = tf.Variable(tf.random.uniform([1],-1.0,1.0))
biases = tf.Variable(tf.zeros([1]))y = Weights*x_data + biases# 计算丢失值
loss = tf.reduce_mean(tf.square(y - y_data))
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)init =tf.initialize_all_variables()sess = tf.Session()
sess.run(init) #激活for step in range(201):sess.run(train)if step%20 ==0:print(step,sess.run(Weights),sess.run(biases))

 二、Session会话控制

案例代码如下:

import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
import numpy as npmatrix1 = tf.constant([[3,3]])
matrix2 = tf.constant([[2],[2]])# 矩阵相乘
product = tf.matmul(matrix1,matrix2)#会话控制
sess = tf.Session()
result = sess.run(product)
print(result)
sess.close()

输出结果为:[[12]]

 三、Variable变量

import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()state = tf.Variable(0,name = 'counter')
# print(state.name)
one = tf.constant(1)new_value = tf.add(state , one)update = tf.assign(state,new_value)init = tf.initialize_all_variables()# 必须使用Session激活
with tf.Session() as sess:sess.run(init)for _ in range(3):sess.run(update)print(sess.run(state))

四、placeholder传入值

import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()input1 = tf.placeholder(tf.float32)
input2 = tf.placeholder(tf.float32)output = tf.multiply(input1,input2)with tf.Session() as sess:print(sess.run(output,feed_dict = {input1:[7.],input2:[2.]}))

输出结果为:[14.]

五、激励函数

 将线性函数扭曲为非线性函数的一种函数

六、添加神经层

def add_layer(inputs,in_size,out_size,activation_function = None):Weights = tf.Variable(tf.random.uniform([in_size,out_size]))biases = tf.Variable(tf.zeros([1,out_size])) + 0.1# 相乘Wx_plus_b = tf.matmul(inputs,Weights) + biases# 激活if activation_function is None:outputs = Wx_plus_belse:outputs = activation_function(Wx_plus_b)return outputs

七、建立神经网络

案例代码如下:

import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
import numpy as npdef add_layer(inputs,in_size,out_size,activation_function = None):Weights = tf.Variable(tf.random.uniform([in_size,out_size]))biases = tf.Variable(tf.zeros([1,out_size])) + 0.1# 相乘Wx_plus_b = tf.matmul(inputs,Weights) + biases# 激活if activation_function is None:outputs = Wx_plus_belse:outputs = activation_function(Wx_plus_b)return outputs
# 定义数据形式
x_data = np.linspace(-1,1,300)[:,np.newaxis] #增加数据维度
noise = np.random.normal(0,0.05,x_data.shape)
y_data = np.square(x_data) - 0.5 + noisexs = tf.placeholder(tf.float32,[None,1])
ys = tf.placeholder(tf.float32,[None,1])# 构建隐藏层
l1 = add_layer(xs,1,10,activation_function=tf.nn.relu)
# 构建输出层
predition = add_layer(l1,10,1,activation_function=None)# 计算误差
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - predition),reduction_indices=[1]))# 对误差进行更正
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)init = tf.initialize_all_variables()sess = tf.Session()sess.run(init)for i in range(1000):sess.run(train_step,feed_dict={xs:x_data,ys:y_data})if i%50 == 0:print(sess.run(loss,feed_dict={xs:x_data,ys:y_data}))

运行结果如下:

可观察到误差不断减小 ，说明预测准确性在不断增加