1. MNIST数据处理
1.1 input_data.read_data_sets函数
功能: 该函数生成的类能将MNIST数据集划分为train, validation和test三个数据集:
- train: 55000张图片
- validation: 5000张
- test: 10000张
trian和validation组成了训练数据集.
每一张图片是一个长度为784(=28*28像素)的一维数组.
- 1: 黑像素点
- 0: 白像素点
1.2 mnist.train.next_batch函数
从所有的训练数据集中读取一小部分(batch)用来训练.
2. 模型的训练
2.1 训练神经网络
2.1.1 inference函数
功能: 给定神经网络的输入和所有的参数, 计算前向传播结果.
使用ReLU作为激活函数.
def inference(input_tensor, avg_class, weights1, biases1, weights2, biases2):
# 不使用滑动平均类
if avg_class == None:
layer1 = tf.nn.relu(tf.matmul(input_tensor, weights1) + biases1)
return tf.matmul(layer1, weights2) + biases2
else:
# 使用滑动平均类
layer1 = tf.nn.relu(tf.matmul(input_tensor, avg_class.average(weights1)) + avg_class.average(biases1))
return tf.matmul(layer1, avg_class.average(weights2)) + avg_class.average(biases2)
2.1.2 train函数
功能: 定义训练过程.
def train(mnist):
x = tf.placeholder(tf.float32, [None, INPUT_NODE], name='x-input')
y_ = tf.placeholder(tf.float32, [None, OUTPUT_NODE], name='y-input')
# 生成隐藏层的参数。
weights1 = tf.Variable(tf.truncated_normal([INPUT_NODE, LAYER1_NODE], stddev=0.1))
biases1 = tf.Variable(tf.constant(0.1, shape=[LAYER1_NODE]))
# 生成输出层的参数。
weights2 = tf.Variable(tf.truncated_normal([LAYER1_NODE, OUTPUT_NODE], stddev=0.1))
biases2 = tf.Variable(tf.constant(0.1, shape=[OUTPUT_NODE]))
# 计算不含滑动平均类的前向传播结果
y = inference(x, None, weights1, biases1, weights2, biases2)
# 定义训练轮数及相关的滑动平均类
global_step = tf.Variable(0, trainable=False)
variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables())
average_y = inference(x, variable_averages, weights1, biases1, weights2, biases2)
# 计算交叉熵及其平均值
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
cross_entropy_mean = tf.reduce_mean(cross_entropy)
# 损失函数的计算
regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)
regularaztion = regularizer(weights1) + regularizer(weights2)
loss = cross_entropy_mean + regularaztion
# 设置指数衰减的学习率。
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,
mnist.train.num_examples / BATCH_SIZE,
LEARNING_RATE_DECAY,
staircase=True)
# 优化损失函数
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
# 反向传播更新参数和更新每一个参数的滑动平均值
with tf.control_dependencies([train_step, variables_averages_op]):
train_op = tf.no_op(name='train')
# 计算正确率
correct_prediction = tf.equal(tf.argmax(average_y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# 初始化会话,并开始训练过程。
with tf.Session() as sess:
tf.global_variables_initializer().run()
validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels}
test_feed = {x: mnist.test.images, y_: mnist.test.labels}
# 循环的训练神经网络。
for i in range(TRAINING_STEPS):
if i % 1000 == 0:
validate_acc = sess.run(accuracy, feed_dict=validate_feed)
print("After %d training step(s), validation accuracy using average model is %g " % (i, validate_acc))
xs,ys=mnist.train.next_batch(BATCH_SIZE)
sess.run(train_op,feed_dict={x:xs,y_:ys})
test_acc=sess.run(accuracy,feed_dict=test_feed)
print(("After %d training step(s), test accuracy using average model is %g" %(TRAINING_STEPS, test_acc)))
2.1.3 主程序入口
def main(argv=None):
mnist = input_data.read_data_sets("../../../datasets/MNIST_data", one_hot=True)
train(mnist)
if __name__=='__main__':
main()
2.2 用验证数据集判断模型效果
为了估计模型在未知数据上的效果, 必须保证测试数据集在训练过程中是不可见的. 因为如果使用测试数据集来选取参数可能会导致神经网络过度拟合测试数据, 从而致使其泛化能力大大降低. 这也是为什么要抽取一部分数据作为验证数据.
3. 变量管理
主要是使用如下几个函数:
- tf.variable.scope()
- tf.get_variable()
INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500
def get_weight_variable(shape, regularizer):
weights = tf.get_variable("weights", shape, initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer != None: tf.add_to_collection('losses', regularizer(weights))
return weights
def inference(input_tensor, regularizer):
with tf.variable_scope('layer1'):
weights = get_weight_variable([INPUT_NODE, LAYER1_NODE], regularizer)
biases = tf.get_variable("biases", [LAYER1_NODE], initializer=tf.constant_initializer(0.0))
layer1 = tf.nn.relu(tf.matmul(input_tensor, weights) + biases)
with tf.variable_scope('layer2'):
weights = get_weight_variable([LAYER1_NODE, OUTPUT_NODE], regularizer)
biases = tf.get_variable("biases", [OUTPUT_NODE], initializer=tf.constant_initializer(0.0))
layer2 = tf.matmul(layer1, weights) + biases
return layer2