TensorFlow神经网络

如上图，在使用mnist时，神经网络的的作用就是计算当前输入数字图片属于各个数字的概率值，然后将概率值最高的数字作为预测值输出，从而达到分类任务。

单层神经网络如下图所示：

单层神经网络代码如下：

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#MNIST数据输入
mnist = input_data.read_data_sets("data/", one_hot=True)

#参数设置
numClasses = 10
inputSize = 784
numHiddenUnits = 50
trainingIterations = 10000
batchSize = 100

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)#激活函数
finalOutput = tf.matmul(hiddenLayerOutput, W2) + B2
finalOutput = tf.nn.relu(finalOutput)

#网络迭代
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:
        trainAccuracy = accuracy.eval(session=sess, feed_dict={X: batchInput, y: batchLabels})
        print ("step %d, training accuracy %g"%(i, trainAccuracy))
testInputs = mnist.test.images
testLabels = mnist.test.labels
acc = accuracy.eval(session=sess, feed_dict = {X: testInputs, y: testLabels})
print("testing accuracy: {}".format(acc))

打印：

step 0, training accuracy 0.03
step 1000, training accuracy 0.9
step 2000, training accuracy 0.97
step 3000, training accuracy 0.99
step 4000, training accuracy 0.97
step 5000, training accuracy 0.98
step 6000, training accuracy 1
step 7000, training accuracy 0.97
step 8000, training accuracy 0.96
step 9000, training accuracy 0.99
testing accuracy: 0.968500018119812

---

下面再添加一层隐藏层：

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#MNIST数据输入
mnist = input_data.read_data_sets("data/", one_hot=True)

#参数设置
numClasses = 10
inputSize = 784
numHiddenUnits = 50
trainingIterations = 10000
batchSize = 100

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))

打印：

step 0, training accuracy 0.18
step 1000, training accuracy 1
step 2000, training accuracy 0.98
step 3000, training accuracy 1
step 4000, training accuracy 0.99
step 5000, training accuracy 1
step 6000, training accuracy 1
step 7000, training accuracy 0.99
step 8000, training accuracy 1
step 9000, training accuracy 1
testing accuracy: 0.9714000225067139