TF - 构造基本神经网络

目录

• 单层神经网络
• 两层神经网络

---

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

Extracting data/train-images-idx3-ubyte.gz
Extracting data/train-labels-idx1-ubyte.gz
Extracting data/t10k-images-idx3-ubyte.gz
Extracting data/t10k-labels-idx1-ubyte.gz

---

单层神经网络

---

参数设置

numClasses = 10 
inputSize = 784 
numHiddenUnits = 50 # 隐层单元个数，将 784 个像素点，映射成 50个特征
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)
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))

step 0, training accuracy 0.13
step 1000, training accuracy 0.79
step 2000, training accuracy 0.83
step 3000, training accuracy 0.88
step 4000, training accuracy 0.91
step 5000, training accuracy 0.87
step 6000, training accuracy 0.89
step 7000, training accuracy 0.84
step 8000, training accuracy 0.89
step 9000, training accuracy 1

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))

step 0, training accuracy 0.1
step 1000, training accuracy 0.97
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 0.99
step 7000, training accuracy 1
step 8000, training accuracy 0.99
step 9000, training accuracy 1
testing accuracy: 0.9700999855995178

---