2021-01-07 tensorflow笔记

tensorflow笔记

p11： 定义变量后一定要用 

tf.initialize_all_variables()

然后在后面初始化一下

sess.run(init)

 

import tensorflow as tf

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()

with tf.Session() as sess:
    sess.run(init)
    for _ in range(3):
        sess.run(update)
        print(sess.run(state))

p12： tf.placeholder 和 feed_dict是绑定使用，placeholder就是先生成一个变量后面用feed_dict再赋值

import tensorflow as tf

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.]}))

p13：生成一个神经层

import tensorflow as tf

###定义一个神经层###
#activation_function表示是否线性
def add_layer(inputs, in_size, out_size, activation_function=None):
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    #activation_function表示是线性就是原值，如果不是要非线性变化
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    return outputs

P16 建造一个 神经网络

import tensorflow as tf
import numpy as np

#activation_function表示是否线性
def add_layer(inputs, in_size, out_size, activation_function=None):
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    #activation_function表示是线性就是原值，如果不是要非线性变化
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    return outputs

# Make up some real data 生成一组带噪声的二次函数
x_data = np.linspace(-1,1,300)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.square(x_data) - 0.5 + noise

# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 1])
ys = tf.placeholder(tf.float32, [None, 1])
# add hidden layer
l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)
# add output layer
prediction = add_layer(l1, 10, 1, activation_function=None)

# the error between prediction and real data
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),
                     reduction_indices=[1]))
#学习率是0.1
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):
    # training
    sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
    if i % 50 == 0:
        # to see the step improvement
        print(sess.run(loss, feed_dict={xs: x_data, ys: y_data}))

P17 画图

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

#activation_function表示是否线性
def add_layer(inputs, in_size, out_size, activation_function=None):
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    #activation_function表示是线性就是原值，如果不是要非线性变化
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    return outputs

# Make up some real data 生成一组带噪声的二次函数
x_data = np.linspace(-1,1,300)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.square(x_data) - 0.5 + noise

# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 1])
ys = tf.placeholder(tf.float32, [None, 1])
# add hidden layer
l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)
# add output layer
prediction = add_layer(l1, 10, 1, activation_function=None)

# the error between prediction and real data
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),
                     reduction_indices=[1]))
#学习率是0.1
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

#####画图
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(x_data,y_data)
plt.ion()
#plt.show() #会使程序暂停


for i in range(1000):
    # training
    sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
    if i % 20 == 0:
        # to see the step improvement
        #print(sess.run(loss, feed_dict={xs: x_data, ys: y_data}))
        #####画图
        prediction_value = sess.run(prediction,feed_dict={xs:x_data})
        lines = ax.plot(x_data,prediction_value,'r-',lw=5)
        plt.pause(0.1)
        ax.lines.remove(lines[0])