# coding: utf-8
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#print(“hello”)
#载入数据集
mnist = input_data.read_data_sets(“F:\\TensorflowProject\\MNIST_data”,one_hot=True)
#每个批次的大小，训练时一次100张放入神经网络中训练
batch_size = 100
#计算一共有多少个批次
n_batch = mnist.train.num_examples//batch_size
#定义两个placeholder
x = tf.placeholder(tf.float32,[None,784])
#0-9十个数字
y = tf.placeholder(tf.float32,[None,10])
keep_prob = tf.placeholder(tf.float32)
#创建一个神经网络
# W = tf.Variable(tf.zeros([784,10]))
# b = tf.Variable(tf.zeros([10]))
W1 = tf.Variable(tf.truncated_normal([784,2000],stddev=0.1))
b1 = tf.Variable(tf.zeros([2000])+0.1)
L1 = tf.nn.tanh(tf.matmul(x,W1)+b1)
L1_drop = tf.nn.dropout(L1,keep_prob)
#隐藏层1
W2 = tf.Variable(tf.truncated_normal([2000,2000],stddev=0.1))
b2 = tf.Variable(tf.zeros([2000])+0.1)
L2 = tf.nn.tanh(tf.matmul(L1_drop,W2)+b2)
L2_drop = tf.nn.dropout(L2,keep_prob)
#隐藏层2
W3 = tf.Variable(tf.truncated_normal([2000,1000],stddev=0.1))
b3 = tf.Variable(tf.zeros([1000])+0.1)
L3 = tf.nn.tanh(tf.matmul(L2_drop,W3)+b3)
L3_drop = tf.nn.dropout(L3,keep_prob)
W4 = tf.Variable(tf.truncated_normal([1000,10],stddev=0.1))
b4 = tf.Variable(tf.zeros([10])+0.1)
prediction = tf.nn.softmax(tf.matmul(L3_drop,W4)+b4)
#二次代价函数
#loss = tf.reduce_mean(tf.square(y-prediction))
#交叉熵
#loss = tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction)
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
#使用梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)
#初始化变量
init = tf.global_variables_initializer()
#结果存放在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))
#求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
#
with tf.Session() as sess:
sess.run(init)
for epoch in range(30):
for batch in range(n_batch):
batch_xs,batch_ys = mnist.train.next_batch(batch_size)
sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys,keep_prob:1.0})
#测试准确率
test_acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0})
train_acc = sess.run(accuracy,feed_dict={x:mnist.train.images,y:mnist.train.labels,keep_prob:1.0})
print(“Iter: “+str(epoch)+” ,Testing Accuracy “+str(test_acc)+” Train : “+str(train_acc))
###########################运行效果
Extracting F:\TensorflowProject\MNIST_data\train-images-idx3-ubyte.gz Extracting F:\TensorflowProject\MNIST_data\train-labels-idx1-ubyte.gz Extracting F:\TensorflowProject\MNIST_data\t10k-images-idx3-ubyte.gz Extracting F:\TensorflowProject\MNIST_data\t10k-labels-idx1-ubyte.gz WARNING:tensorflow:From <ipython-input-6-c16fee9228bc>:44: softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version. Instructions for updating: Future major versions of TensorFlow will allow gradients to flow into the labels input on backprop by default. See tf.nn.softmax_cross_entropy_with_logits_v2. Iter: 0 ,Testing Accuracy 0.9394 Train : 0.948436 Iter: 1 ,Testing Accuracy 0.9601 Train : 0.974145 Iter: 2 ,Testing Accuracy 0.9639 Train : 0.982691 Iter: 3 ,Testing Accuracy 0.965 Train : 0.9868 Iter: 4 ,Testing Accuracy 0.9691 Train : 0.988891 Iter: 5 ,Testing Accuracy 0.9698 Train : 0.9902 Iter: 6 ,Testing Accuracy 0.9692 Train : 0.9912 Iter: 7 ,Testing Accuracy 0.9706 Train : 0.991836 Iter: 8 ,Testing Accuracy 0.971 Train : 0.992291 Iter: 9 ,Testing Accuracy 0.9701 Train : 0.992818 Iter: 10 ,Testing Accuracy 0.9706 Train : 0.993073 Iter: 11 ,Testing Accuracy 0.9706 Train : 0.993236 Iter: 12 ,Testing Accuracy 0.9713 Train : 0.993491 Iter: 13 ,Testing Accuracy 0.9704 Train : 0.993782 Iter: 14 ,Testing Accuracy 0.9707 Train : 0.994036 Iter: 15 ,Testing Accuracy 0.9716 Train : 0.994236 Iter: 16 ,Testing Accuracy 0.9713 Train : 0.994509 Iter: 17 ,Testing Accuracy 0.9712 Train : 0.994691 Iter: 18 ,Testing Accuracy 0.9714 Train : 0.994891 Iter: 19 ,Testing Accuracy 0.9718 Train : 0.995055 Iter: 20 ,Testing Accuracy 0.9726 Train : 0.995236 Iter: 21 ,Testing Accuracy 0.972 Train : 0.995382 Iter: 22 ,Testing Accuracy 0.9725 Train : 0.995473 Iter: 23 ,Testing Accuracy 0.9728 Train : 0.995527 Iter: 24 ,Testing Accuracy 0.9725 Train : 0.995582 Iter: 25 ,Testing Accuracy 0.9725 Train : 0.995618 Iter: 26 ,Testing Accuracy 0.9723 Train : 0.995673 Iter: 27 ,Testing Accuracy 0.9726 Train : 0.9958 Iter: 28 ,Testing Accuracy 0.9721 Train : 0.995836 Iter: 29 ,Testing Accuracy 0.9721 Train : 0.995873
