tensorflow 2

import tensorflow as tf
import numpy as npdef test1():#create datax_data=np.random.rand(100).astype(np.float32)y_data=x_data*0.1+0.3#create tensorflow structureWeights=tf.Variable(tf.random_uniform([1],-1.0,1.0)) #一维，范围[-1,1]biases=tf.Variable(tf.zeros([1]))y=Weights*x_data+biasesloss=tf.reduce_mean(tf.square(y-y_data))#建立优化器，减小误差，提高参数准确度，每次迭代都会优化optimizer=tf.train.GradientDescentOptimizer(0.5) #学习效率<1train=optimizer.minimize(loss)#初始化变量init=tf.global_variables_initializer()with tf.Session() as sess:sess.run(init)#trainfor step in range(201):sess.run(train)if step%20==0:print(step,sess.run(Weights),sess.run(biases))def test2():node1 = tf.constant(3.0, dtype=tf.float32)node2 = tf.constant(4.0)# also tf.float32 implicitlyprint(node1, node2)sess = tf.Session()print(sess.run([node1, node2]))node3 = tf.add(node1, node2)print("node3:", node3)print("sess.run(node3):", sess.run(node3))a = tf.placeholder(tf.float32)b = tf.placeholder(tf.float32)adder_node = a + b  # + provides a shortcut for tf.add(a, b)print(sess.run(adder_node, {a:3, b:4.5}))print(sess.run(adder_node, {a: [1,3], b: [2,4]}))add_and_triple = adder_node *3.print(sess.run(add_and_triple, {a:3, b:4.5}))def test3():W = tf.Variable([.3], dtype=tf.float32)b = tf.Variable([-.3], dtype=tf.float32)x = tf.placeholder(tf.float32)linear_model = W*x + b    init = tf.global_variables_initializer()sess = tf.Session()sess.run(init)print(sess.run(linear_model, {x: [1,2,3,4]}))print(sess.run(linear_model, {x: [[1,2],[3,4]]}))y = tf.placeholder(tf.float32)squared_deltas = tf.square(linear_model - y)loss = tf.reduce_sum(squared_deltas)loss1 = tf.reduce_mean(squared_deltas)print(sess.run(linear_model, {x:[1,2,3,4]}))print(sess.run(squared_deltas, {x: [1,2,3,4], y: [0, -1, -2, -3]}))print(sess.run(loss, {x: [1,2,3,4], y: [0, -1, -2, -3]}))print(sess.run(loss/4, {x: [1,2,3,4], y: [0, -1, -2, -3]}))print(sess.run(loss1, {x: [1,2,3,4], y: [0, -1, -2, -3]}))def test4():b = tf.Variable([-.3], dtype=tf.float32)fixb = tf.assign(b, [1.])init = tf.global_variables_initializer()sess = tf.Session()sess.run(init)print(sess.run(fixb))def test5():import tensorflow as tfmnist = tf.keras.datasets.mnist(x_train, y_train),(x_test, y_test) = mnist.load_data()print(type(x_train))print(type(y_train))print(type(x_test))print(type(y_test))x_train, x_test = x_train / 255.0, x_test / 255.0model = tf.keras.models.Sequential([tf.keras.layers.Flatten(input_shape=(28, 28)),tf.keras.layers.Dense(512, activation=tf.nn.relu),tf.keras.layers.Dropout(0.2),tf.keras.layers.Dense(10, activation=tf.nn.softmax)])model.compile(optimizer='adam',loss='sparse_categorical_crossentropy',metrics=['accuracy'])model.fit(x_train, y_train, epochs=5)model.evaluate(x_test, y_test)def test6():# 给定type，tf大部分只能处理float32数据input1 = tf.placeholder(tf.float32)input2 = tf.placeholder(tf.float32)# Tensorflow 1.0 修改版# tf.mul---tf.multiply# tf.sub---tf.subtract# tf.neg---tf.negativeoutput = tf.multiply(input1, input2)with tf.Session() as sess:# placeholder在sess.run()的时候传入值print(sess.run(output, feed_dict={input1: [7.], input2: [2.]}))def add_layer(inputs,in_size,out_size,activation_function=None):#Weights是一个矩阵，[行，列]为[in_size,out_size]Weights=tf.Variable(tf.random_normal([in_size,out_size]))#正态分布#初始值推荐不为0，所以加上0.1，一行，out_size列biases=tf.Variable(tf.zeros([1,out_size])+0.1)#Weights*x+b的初始化的值，也就是未激活的值Wx_plus_b=tf.matmul(inputs,Weights)+biases#激活if activation_function is None:#激活函数为None，也就是线性函数outputs=Wx_plus_belse:outputs=activation_function(Wx_plus_b)return outputsdef test7():"""定义数据形式"""# (-1,1)之间，有300个单位，后面的是维度，x_data是有300行（300个例子）x_data=np.linspace(-1,1,300)[:,np.newaxis]# 加噪声,均值为0，方差为0.05，大小和x_data一样print(x_data.shape)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])"""建立网络"""#定义隐藏层，输入1个节点，输出10个节点l1=add_layer(xs,1,10,activation_function=tf.nn.relu)#定义输出层prediction=add_layer(l1,10,1,activation_function=None)"""预测"""#损失函数,算出的是每个例子的平方，要求和（reduction_indices=[1]，按行求和）,再求均值loss=tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))"""训练"""#优化算法,minimize(loss)以0.1的学习率对loss进行减小train_step=tf.train.GradientDescentOptimizer(0.1).minimize(loss)init=tf.global_variables_initializer()with tf.Session() as sess: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}))def test8():import matplotlib.pylab as plt"""定义数据形式"""# (-1,1)之间，有300个单位，后面的是维度，x_data是有300行（300个例子）x_data=np.linspace(-1,1,300)[:,np.newaxis]# 加噪声,均值为0，方差为0.05，大小和x_data一样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])"""建立网络"""#定义隐藏层，输入1个节点，输出10个节点l1=add_layer(xs,1,10,activation_function=tf.nn.relu)#定义输出层prediction=add_layer(l1,10,1,activation_function=None)"""预测"""#损失函数,算出的是每个例子的平方，要求和（reduction_indices=[1]，按行求和）,再求均值loss=tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))"""训练"""#优化算法,minimize(loss)以0.1的学习率对loss进行减小train_step=tf.train.GradientDescentOptimizer(0.1).minimize(loss)init=tf.global_variables_initializer()with tf.Session() as sess:sess.run(init)fig=plt.figure()#连续性的画图ax=fig.add_subplot(1,1,1)ax.scatter(x_data,y_data)# 不暂停plt.ion()# plt.show()绘制一次就会暂停# plt.show() #也可以用plt.show(block=False)来取消暂停，但是python3.5以后提供了ion的功能，更方便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}))#尝试先抹除，后绘制第二条线#第一次没有线，会报错，try就会忽略错误，然后紧接着执行下面的步骤try:# 画出一条后抹除掉,去除第一个线段，但是只有一个，也就是抹除当前的线段ax.lines.remove(lines[0])except Exception:passprediction_value=sess.run(prediction,feed_dict={xs:x_data})lines=ax.plot(x_data,prediction_value,'r-',lw=5) #lw线宽# 暂停0.1splt.pause(0.1)#test1()
#test2() 
#test3()
#test4()
#test5()    
#test6()
#test7()
test8()