快捷導(dǎo)航

tensorflow使用神經(jīng)網(wǎng)絡(luò)實(shí)現(xiàn)mnist分類

更新時間：2018年09月08日 12:01:20 作者：Missayaa

這篇文章主要為大家詳細(xì)介紹了tensorflow使用神經(jīng)網(wǎng)絡(luò)實(shí)現(xiàn)mnist分類，具有一定的參考價值，感興趣的小伙伴們可以參考一下

本文實(shí)例為大家分享了tensorflow神經(jīng)網(wǎng)絡(luò)實(shí)現(xiàn)mnist分類的具體代碼，供大家參考，具體內(nèi)容如下

只有兩層的神經(jīng)網(wǎng)絡(luò)，直接上代碼

#引入包
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
#引入input_data文件
from tensorflow.examples.tutorials.mnist import input_data
#讀取文件
mnist = input_data.read_data_sets('F:/mnist/data/',one_hot=True)

#定義第一個隱藏層和第二個隱藏層，輸入層輸出層
n_hidden_1 = 256
n_hidden_2 = 128
n_input = 784
n_classes = 10

#由于不知道輸入圖片個數(shù)，所以用placeholder
x = tf.placeholder("float",[None,n_input])
y = tf.placeholder("float",[None,n_classes])

stddev = 0.1

#定義權(quán)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))    
    }

#定義偏置
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")


#前向傳播
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'])

#定義優(yōu)化函數(shù)，精準(zhǔn)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")

#定義超參數(shù)
training_epochs = 80
batch_size = 200
display_step = 4

#會話開始
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)

#優(yōu)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")

程序部分運(yùn)行結(jié)果如下：

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

以上就是本文的全部內(nèi)容，希望對大家的學(xué)習(xí)有所幫助，也希望大家多多支持腳本之家。

您可能感興趣的文章: