tf.train.GradientDescentOptimizer(learning_rate, use_locking=False, name='GradientDescent')

tf.train.AdagradOptimizer(learning_rate, initial_accumulator_value=0.1, use_locking=False,name='Adagrad')

tf.train.MomentumOptimizer.__init__(learning_rate, momentum, use_locking=False, name='Momentum', use_nesterov=False)

tf.train.RMSPropOptimizer(learning_rate, decay=0.9, momentum=0.0, epsilon=1e-10, use_locking=False, name='RMSProp')

tf.train.AdamOptimizer(learning_rate=0.001, beta1=0.9, beta2=0.999, epsilon=1e-08, use_locking=False, name='Adam')

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")
with tf.name_scope("loss"):
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=ys,logits = prediction),name = 'loss')
    #label是標(biāo)簽，logits是預(yù)測值，交叉熵。
    tf.summary.scalar("loss",loss)
train = tf.train.GradientDescentOptimizer(0.2).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)

train = tf.train.GradientDescentOptimizer(0.2).minimize(loss)

train = tf.train.GradientDescentOptimizer(0.2).minimize(loss)

train = tf.train.AdagradOptimizer(0.1).minimize(loss)

train = tf.train.MomentumOptimizer(learning_rate=0.05, momentum=0.9).minimize(loss)

train = tf.train.RMSPropOptimizer(0.01).minimize(loss)

train = tf.train.AdamOptimizer(0.004).minimize(loss)