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 tfimport numpy as npimport 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(gè)隱藏層和第二個(gè)隱藏層，輸入層輸出層n_hidden_1 = 256n_hidden_2 = 128n_input = 784n_classes = 10#由于不知道輸入圖片個(gè)數(shù)，所以用placeholderx = 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 = 80batch_size = 200display_step = 4#會(huì)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:0.605Test 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