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
importtensorflowastf
importnumpyasnp
importmatplotlib.pyplotasplt
#引入input_data文件
fromtensorflow.examples.tutorials.mnistimportinput_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=256
n_hidden_2=128
n_input=784
n_classes=10
#由于不知道输入图片个数，所以用placeholder
x=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("NetworkisReady")
#前向传播
defmultilayer_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("Functionsisready")
#定义超参数
training_epochs=80
batch_size=200
display_step=4
#会话开始
init=tf.global_variables_initializer()
sess=tf.Session()
sess.run(init)
#优化
forepochinrange(training_epochs):
avg_cost=0.
total_batch=int(mnist.train.num_examples/batch_size)
foriinrange(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/%03dcost:%.9f"%(epoch,training_epochs,avg_cost))
feeds={x:batch_xs,y:batch_ys}
train_acc=sess.run(accr,feed_dict=feeds)
print("Trainaccuracy:%.3f"%(train_acc))
feeds={x:mnist.test.images,y:mnist.test.labels}
test_acc=sess.run(accr,feed_dict=feeds)
print("Testaccuracy:%.3f"%(test_acc))
print("OptimizationFinished")
程序部分运行结果如下：
Trainaccuracy:0.605 Testaccuracy:0.633 Epoch:071/080cost:1.810029302 Trainaccuracy:0.600 Testaccuracy:0.645 Epoch:075/080cost:1.761531130 Trainaccuracy:0.690 Testaccuracy:0.649 Epoch:079/080cost:1.711757494 Trainaccuracy:0.640 Testaccuracy:0.660 OptimizationFinished
以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持毛票票。