TF Minest 构造神经网络

[toc]

简单的神经网络

mnist = input_data.read_data_sets("data/", one_hot=True)

# 参数设置
numClasses = 10 # 输出10类
inputSize = 784 # 784 个像素点
numHiddenUnits = 50 # 隐藏层单元格数；把 784 个像素点，映射成 50 个新的特征
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))  # 交叉熵损失
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))

---

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))

---

卷积神经网络

增加卷积层和池化层

mnist = input_data.read_data_sets("data/", one_hot=True)

tf.reset_default_graph() 
sess = tf.InteractiveSession()
x = tf.placeholder("float", shape = [None, 28,28,1]) #shape in CNNs is always None x height x width x color channels
y_ = tf.placeholder("float", shape = [None, 10]) #shape is always None x number of classes


W_conv1 = tf.Variable(tf.truncated_normal([5, 5, 1, 32], stddev=0.1))#shape is filter x filter x input channels x output channels
b_conv1 = tf.Variable(tf.constant(.1, shape = [32])) #shape of the bias just has to match output channels of the filter

h_conv1 = tf.nn.conv2d(input=x, filter=W_conv1, strides=[1, 1, 1, 1], padding='SAME') + b_conv1
h_conv1 = tf.nn.relu(h_conv1)
h_pool1 = tf.nn.max_pool(h_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')

def conv2d(x, W):
    return tf.nn.conv2d(input=x, filter=W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')

# Second Conv and Pool Layers 
W_conv2 = tf.Variable(tf.truncated_normal([5, 5, 32, 64], stddev=0.1))
b_conv2 = tf.Variable(tf.constant(.1, shape = [64]))
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

# First Fully Connected Layer 第一个全连接层
W_fc1 = tf.Variable(tf.truncated_normal([7 * 7 * 64, 1024], stddev=0.1))
b_fc1 = tf.Variable(tf.constant(.1, shape = [1024]))
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

# Dropout Layer
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

# Second Fully Connected Layer
W_fc2 = tf.Variable(tf.truncated_normal([1024, 10], stddev=0.1))
b_fc2 = tf.Variable(tf.constant(.1, shape = [10]))

#Final Layer
y = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

crossEntropyLoss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y_, logits = y))
trainStep = tf.train.AdamOptimizer().minimize(crossEntropyLoss)  # 指定 AdamOptimizer 优化器，会自适应调整学习率；以前使用过梯度下降来优化。
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

sess.run(tf.global_variables_initializer())

batchSize = 50
for i in range(1000):
    batch = mnist.train.next_batch(batchSize)
    trainingInputs = batch[0].reshape([batchSize,28,28,1])
    trainingLabels = batch[1]
    if i%100 == 0:
        trainAccuracy = accuracy.eval(session=sess, feed_dict={x:trainingInputs, y_: trainingLabels, keep_prob: 1.0})
        print ("step %d, training accuracy %g"%(i, trainAccuracy))
    trainStep.run(session=sess, feed_dict={x: trainingInputs, y_: trainingLabels, keep_prob: 0.5})

---