import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
import input_data
mnist = input_data.read_data_sets('data/', one_hot=True)
先初始化所有输入输出和参数
# NETWORK TOPOLOGIES
n_hidden_1 = 256 #第一层的神经元个数
n_hidden_2 = 128 #第二层的神经元个数
n_input = 784 #输入的像素的大小
n_classes = 10 #输出的分类的结果
# INPUTS AND OUTPUTS,参数初始化
x = tf.placeholder("float", [None, n_input])#x为样本个数和对应像素大小
y = tf.placeholder("float", [None, n_classes])#y为样本个数和对应的像素大小
# NETWORK PARAMETERS
stddev = 0.1
#w1,w2等用高斯初始化,方差为0.1的高斯
weights = {
'w1': tf.Variable(tf.random_normal([n_input, n_hidden_1], stddev=stddev)),
'w2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2], stddev=stddev)),
'out': tf.Variable(tf.random_normal([n_hidden_2, n_classes], stddev=stddev))
}
biases = {
'b1': tf.Variable(tf.random_normal([n_hidden_1])),
'b2': tf.Variable(tf.random_normal([n_hidden_2])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
print ("NETWORK READY")
def multilayer_perceptron(_X, _weights, _biases):
layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(_X, _weights['w1']), _biases['b1']))
layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, _weights['w2']), _biases['b2']))
return (tf.matmul(layer_2, _weights['out']) + _biases['out'])
# PREDICTION
pred = multilayer_perceptron(x, weights, biases)
# LOSS AND OPTIMIZER
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y)) #交叉商函数定义损失函数pred是网络预测值,y为真实的值,reduce_mean是平均的cost
optm = tf.train.GradientDescentOptimizer(learning_rate=0.001).minimize(cost) #梯度下降法
corr = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1)) #准确值判断,得出时ture,下面语句是转化为0和1
accr = tf.reduce_mean(tf.cast(corr, "float"))
# INITIALIZER
init = tf.global_variables_initializer()#全局初始化,后面要run()
print ("FUNCTIONS READY")
training_epochs = 20
batch_size = 100
display_step = 4
# LAUNCH THE GRAPH
sess = tf.Session()
sess.run(init)
# OPTIMIZE
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = int(mnist.train.num_examples/batch_size)
# ITERATION
for i in range(total_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
feeds = {x: batch_xs, y: batch_ys}
sess.run(optm, feed_dict=feeds)
avg_cost += sess.run(cost, feed_dict=feeds)
avg_cost = avg_cost / total_batch
# DISPLAY
if (epoch+1) % display_step == 0:
print ("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost))
feeds = {x: batch_xs, y: batch_ys}
train_acc = sess.run(accr, feed_dict=feeds)
print ("TRAIN ACCURACY: %.3f" % (train_acc))
feeds = {x: mnist.test.images, y: mnist.test.labels}
test_acc = sess.run(accr, feed_dict=feeds)
print ("TEST ACCURACY: %.3f" % (test_acc))
print ("OPTIMIZATION FINISHED")