tensorflow使用神经网络实现mnist分类

本文实例为大家分享了tensorflow神经网络实现mnist分类的具体代码，供大家参考，具体内容如下

只有两层的神经网络，直接上代码

#引入包import tensorflow as tfimport numpy as npimport matplotlib.pyplot as plt#引入input_data文件from tensorflow.examples.tutorials.mnist import input_data#读取文件mnist = input_data.read_data_sets('F:/mnist/data/',one_hot=True)#定义第一个隐藏层和第二个隐藏层，输入层输出层n_hidden_1 = 256n_hidden_2 = 128n_input = 784n_classes = 10#由于不知道输入图片个数，所以用placeholderx = tf.placeholder("float",[None,n_input])y = tf.placeholder("float",[None,n_classes])stddev = 0.1#定义权重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))        }#定义偏置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 is Ready")#前向传播def multilayer_perceptrin(_X,_weights,_biases):  layer1 = tf.nn.sigmoid(tf.add(tf.matmul(_X,_weights['w1']),_biases['b1']))  layer2 = tf.nn.sigmoid(tf.add(tf.matmul(layer1,_weights['w2']),_biases['b2']))  return (tf.matmul(layer2,_weights['out'])+_biases['out'])#定义优化函数，精准度等pred = multilayer_perceptrin(x,weights,biases)cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = pred,labels=y))optm = tf.train.GradientDescentOptimizer(learning_rate = 0.001).minimize(cost)corr = tf.equal(tf.argmax(pred,1),tf.argmax(y,1))accr = tf.reduce_mean(tf.cast(corr,"float"))print("Functions is ready")#定义超参数training_epochs = 80batch_size = 200display_step = 4#会话开始init = tf.global_variables_initializer()sess = tf.Session()sess.run(init)#优化for epoch in range(training_epochs):  avg_cost=0.  total_batch = int(mnist.train.num_examples/batch_size)  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  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")

程序部分运行结果如下：

Train accuracy:0.605Test accuracy:0.633Epoch:071/080 cost:1.810029302Train accuracy:0.600Test accuracy:0.645Epoch:075/080 cost:1.761531130Train accuracy:0.690Test accuracy:0.649Epoch:079/080 cost:1.711757494Train accuracy:0.640Test accuracy:0.660Optimization Finished