loss = tf.reduce_mean(tf.square(logits-labels))
loss = tf.reduce_mean(tf.square(tf.sub(logits, labels)))
loss = tf.losses.mean_squared_error(logits,labels)

loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=y,logits=logits)
#計(jì)算方式：對(duì)輸入的logits先通過sigmoid函數(shù)計(jì)算，再計(jì)算它們的交叉熵
#但是它對(duì)交叉熵的計(jì)算方式進(jìn)行了優(yōu)化，使得結(jié)果不至于溢出。
loss = tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=logits)
#計(jì)算方式：對(duì)輸入的logits先通過softmax函數(shù)計(jì)算，再計(jì)算它們的交叉熵，
#但是它對(duì)交叉熵的計(jì)算方式進(jìn)行了優(yōu)化，使得結(jié)果不至于溢出。

import numpy as np
import tensorflow as tf
x_data = np.random.rand(100).astype(np.float32) #獲取隨機(jī)X值
y_data = x_data * 0.1 + 0.3                     #計(jì)算對(duì)應(yīng)y值
Weights = tf.Variable(tf.random_uniform([1],-1.0,1.0))  #random_uniform返回[m,n]大小的矩陣，產(chǎn)生于low和high之間，產(chǎn)生的值是均勻分布的。
Biaxs = tf.Variable(tf.zeros([1]))                      #生成0
y = Weights*x_data + Biaxs      
loss = tf.losses.mean_squared_error(y_data,y)              #計(jì)算平方差
#loss = tf.reduce_mean(tf.square(y_data-y))
#loss = tf.reduce_mean(tf.square(tf.sub(y_data,y)))
optimizer = tf.train.GradientDescentOptimizer(0.6)      #梯度下降法
train = optimizer.minimize(loss)
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
for i in range(200):
    sess.run(train)
    if i % 20 == 0:
        print(sess.run(Weights),sess.run(Biaxs))

import tensorflow as tf 
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data",one_hot = "true")
def add_layer(inputs,in_size,out_size,n_layer,activation_function = None):
    layer_name = 'layer%s'%n_layer
    with tf.name_scope(layer_name):
        with tf.name_scope("Weights"):
            Weights = tf.Variable(tf.random_normal([in_size,out_size]),name = "Weights")
            tf.summary.histogram(layer_name+"/weights",Weights)
        with tf.name_scope("biases"):
            biases = tf.Variable(tf.zeros([1,out_size]) + 0.1,name = "biases")
            tf.summary.histogram(layer_name+"/biases",biases)
        with tf.name_scope("Wx_plus_b"):
            Wx_plus_b = tf.matmul(inputs,Weights) + biases
            tf.summary.histogram(layer_name+"/Wx_plus_b",Wx_plus_b)
        if activation_function == None :
            outputs = Wx_plus_b 
        else:
            outputs = activation_function(Wx_plus_b)
        tf.summary.histogram(layer_name+"/outputs",outputs)
        return outputs
def compute_accuracy(x_data,y_data):
    global prediction
    y_pre = sess.run(prediction,feed_dict={xs:x_data})
    correct_prediction = tf.equal(tf.arg_max(y_data,1),tf.arg_max(y_pre,1))     #判斷是否相等
    accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))   #賦予float32數(shù)據(jù)類型，求平均。
    result = sess.run(accuracy,feed_dict = {xs:batch_xs,ys:batch_ys})   #執(zhí)行
    return result
xs = tf.placeholder(tf.float32,[None,784])
ys = tf.placeholder(tf.float32,[None,10])
layer1 = add_layer(xs,784,150,"layer1",activation_function = tf.nn.tanh)
prediction = add_layer(layer1,150,10,"layer2")
#由于loss函數(shù)在運(yùn)算的時(shí)候會(huì)自動(dòng)進(jìn)行softmax或者sigmoid函數(shù)的運(yùn)算，所以不需要特殊激勵(lì)函數(shù)。
with tf.name_scope("loss"):
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=ys,logits = prediction),name = 'loss')
    #loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=ys,logits = prediction),name = 'loss')
    #label是標(biāo)簽，logits是預(yù)測(cè)值，交叉熵。
    tf.summary.scalar("loss",loss)
train = tf.train.AdamOptimizer(4e-3).minimize(loss)
init = tf.initialize_all_variables()
merged = tf.summary.merge_all()
with tf.Session() as sess:
    sess.run(init)
    write = tf.summary.FileWriter("logs/",sess.graph)
    for i in range(5001):
        batch_xs,batch_ys = mnist.train.next_batch(100)
        sess.run(train,feed_dict = {xs:batch_xs,ys:batch_ys})
        if i % 1000 == 0:
            print("訓(xùn)練%d次的識(shí)別率為：%f。"%((i+1),compute_accuracy(mnist.test.images,mnist.test.labels)))
            result = sess.run(merged,feed_dict={xs:batch_xs,ys:batch_ys})
            write.add_summary(result,i)