tensorflow(5)——神经网络

最新推荐文章于 2023-10-25 17:57:37 发布

转载最新推荐文章于 2023-10-25 17:57:37 发布 · 282 阅读

Tensorflow基础专栏收录该内容

6 篇文章

订阅专栏

本文通过构建单层及双层神经网络模型，使用TensorFlow框架和Mnist数据集，详细介绍了神经网络在手写数字识别任务中的应用。实验结果显示，双层神经网络在训练迭代过程中表现出更高的准确率。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

以Mnist数据集为例
一、神经网络结构

二、单层神经网络

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("data/", one_hot=True)

#设置参数
numClasses = 10
inputSize = 784
numHiddenUnits = 50   #隐藏层神经元个数
trainingIterations = 10000
batchSize = 100

#指定X和y的大小
X = tf.placeholder(tf.float32, shape = [None, inputSize])
y = tf.placeholder(tf.float32, shape = [None, numClasses])

#参数初始化
W1 = tf.Variable(tf.truncated_normal([inputSize, numHiddenUnits], stddev=0.1))
B1 = tf.Variable(tf.constant(0.1), [numHiddenUnits])
W2 = tf.Variable(tf.truncated_normal([numHiddenUnits, numClasses], stddev=0.1))
B2 = tf.Variable(tf.constant(0.1), [numClasses])

#网络结构
hiddenLayerOutput = tf.matmul(X, W1) + B1
hiddenLayerOutput = tf.nn.relu(hiddenLayerOutput)
finalOutput = tf.matmul(hiddenLayerOutput, W2) + B2
finalOutput = tf.nn.relu(finalOutput)

#训练
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y, logits = finalOutput))
opt = tf.train.GradientDescentOptimizer(learning_rate = .1).minimize(loss)

#预测
correct_prediction = tf.equal(tf.argmax(finalOutput,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

sess = tf.Session()
init = tf.global_variables_initializer()
sess.run(init)

for i in range(trainingIterations):
    batch = mnist.train.next_batch(batchSize)
    batchInput = batch[0]
    batchLabels = batch[1]
    _, trainingLoss = sess.run([opt, loss], feed_dict={X: batchInput, y: batchLabels})
    if i%1000 == 0:
        trainAccuracy = accuracy.eval(session=sess, feed_dict={X: batchInput, y: batchLabels})
        print ("step %d, training accuracy %g"%(i, trainAccuracy))

结果：
step 0, training accuracy 0.11
step 1000, training accuracy 0.91
step 2000, training accuracy 0.93
step 3000, training accuracy 0.94
step 4000, training accuracy 0.97
step 5000, training accuracy 0.94
step 6000, training accuracy 0.96
step 7000, training accuracy 0.98
step 8000, training accuracy 0.98
step 9000, training accuracy 0.97

三、两层神经网络

numHiddenUnitsLayer2 = 100
trainingIterations = 10000

X = tf.placeholder(tf.float32, shape = [None, inputSize])
y = tf.placeholder(tf.float32, shape = [None, numClasses])

W1 = tf.Variable(tf.random_normal([inputSize, numHiddenUnits], stddev=0.1))
B1 = tf.Variable(tf.constant(0.1), [numHiddenUnits])
W2 = tf.Variable(tf.random_normal([numHiddenUnits, numHiddenUnitsLayer2], stddev=0.1))
B2 = tf.Variable(tf.constant(0.1), [numHiddenUnitsLayer2])
W3 = tf.Variable(tf.random_normal([numHiddenUnitsLayer2, numClasses], stddev=0.1))
B3 = tf.Variable(tf.constant(0.1), [numClasses])

hiddenLayerOutput = tf.matmul(X, W1) + B1
hiddenLayerOutput = tf.nn.relu(hiddenLayerOutput)
hiddenLayer2Output = tf.matmul(hiddenLayerOutput, W2) + B2
hiddenLayer2Output = tf.nn.relu(hiddenLayer2Output)
finalOutput = tf.matmul(hiddenLayer2Output, W3) + B3

loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y, logits = finalOutput))
opt = tf.train.GradientDescentOptimizer(learning_rate = .1).minimize(loss)

correct_prediction = tf.equal(tf.argmax(finalOutput,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

sess = tf.Session()
init = tf.global_variables_initializer()
sess.run(init)

for i in range(trainingIterations):
    batch = mnist.train.next_batch(batchSize)
    batchInput = batch[0]
    batchLabels = batch[1]
    _, trainingLoss = sess.run([opt, loss], feed_dict={X: batchInput, y: batchLabels})
    if i%1000 == 0:
        train_accuracy = accuracy.eval(session=sess, feed_dict={X: batchInput, y: batchLabels})
        print ("step %d, training accuracy %g"%(i, train_accuracy))

testInputs = mnist.test.images
testLabels = mnist.test.labels
acc = accuracy.eval(session=sess, feed_dict = {X: testInputs, y: testLabels})
print("testing accuracy: {}".format(acc))

结果是：
step 0, training accuracy 0.06
step 1000, training accuracy 0.98
step 2000, training accuracy 0.96
step 3000, training accuracy 0.96
step 4000, training accuracy 1
step 5000, training accuracy 1
step 6000, training accuracy 0.99
step 7000, training accuracy 1
step 8000, training accuracy 0.99
step 9000, training accuracy 1
testing accuracy: 0.9726999998092651