终于自己完整实现了一个例子了。这个例子比较简单,但是用到了好多之前没接触的知识,感觉有必要记下来,方便自己以后学习,也能跟大家学习交流。用的是mnist数据集
(其中自己的文件夹路径得换成 '/' 这样的斜杠才行)
# coding: utf-8
# In[48]:
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# In[49]:
#MNIST数据集相关的常数。
INPUT_NODE = 784
OUTPUT_NODE = 10
# In[50]:
#配置神经网络的参数;
LAYER1_NODE = 500
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 5000
MOVING_AVERAGE_DECAY = 0.99
# In[51]:
#定义一个辅助函数,给定神经网络的输入和所有参数,计算前向传播结果;Relu激活函数;
def inference(input_tensor, avg_class, weights1, biases1,
weights2, biases2):
#当没有提供滑动平均类时,直接使用参数当前的取值;
if avg_class == None:
layer1 = tf.nn.relu(tf.matmul(input_tensor, weights1) + biases1)
return tf.matmul(layer1, weights2) + biases2
else:
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)
# In[52]:
def train(mnist):
x = tf.placeholder(tf.float32, [None, INPUT_NODE], name='x-input') #第一层的输入;
y_ = tf.placeholder(tf.float32, [None, OUTPUT_NODE], name='y-input') # 最后一层的输入;
#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]))
#调用之前编写的函数inference;
y = inference(x, None, weights1, biases1, weights2, biases2)
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)
#使用交叉熵作为损失函数;
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)
#计算L2正则化损失函数;
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
regularization = regularizer(weights1) + regularizer(weights2)
loss = cross_entropy_mean + regularization #总损失;
#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)
#使用梯度下降来优化算法;
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
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)))
# In[53]:
def main(argv=None):
mnist = input_data.read_data_sets("Z:/jupyter_notebooks/tensorflow-tutorial-master/Deep_Learning_with_TensorFlow/datasets/MNIST_data", one_hot=True)
train(mnist)
if __name__=='__main__':
main()
# In[ ]: