训练一个神经网络的目的是啥？不就是有朝一日让它有用武之地吗？可是，在别处使用训练好的网络，得先把网络的参数（就是那些variables）保存下来，怎么保存呢？其实，tensorflow已经给我们提供了很方便的API，来帮助我们实现训练参数的存储与读取，如果想了解详情，请看晦涩难懂的官方API，接下来我简单介绍一下我的理解。
保存与读取数据全靠下面这个类实现：
class tf.train.Saver
当我们需要存储数据时，下面2条指令就够了
saver = tf.train.Saver()
save_path = saver.save(sess, model_path)
解释一下，首先创建一个saver类，然后调用saver的save方法（函数），save需要传递两个参数，一个是你的训练session，另一个是文件存储路径，例如“/tmp/superNet.ckpt”，这个存储路径是可以包含文件名的。save方法会返回一个存储路径。当然，save方法还有别的参数可以传递，这里不再介绍。
然后怎么读取数据呢？看下面
saver = tf.train.Saver()
load_path = saver.restore(sess, model_path)
和存储数据神似啊！不再赘述。
下面是重点！关于tf.train.Saver()使用的几点小心得！
- 1、save方法在实现数据读取时，它仅仅读数据，关键是得有一些提前声明好的variables来接受这些数据，因此，当save读取数据到sess时，需要提前声明与数据匹配的variables，否则程序就报错了。
- 2、save读取的数据不需要initialize。
- 3、目前想到的就这么多，随时补充。
为了对数据存储和读取有更直观的认识，我自己写了两个实验小程序，下面是第一个，训练网络并存储数据，用的MNIST数据集
import tensorflow as tf
import sys
# load MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('data', one_hot=True)
# 一些 hyper parameters
activation = tf.nn.relu
batch_size = 100
iteration = 20000
hidden1_units = 30
# 注意！这里是存储路径！
model_path = sys.path[0] + '/simple_mnist.ckpt'
X = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
W_fc1 = tf.Variable(tf.truncated_normal([784, hidden1_units], stddev=0.2))
b_fc1 = tf.Variable(tf.zeros([hidden1_units]))
W_fc2 = tf.Variable(tf.truncated_normal([hidden1_units, 10], stddev=0.2))
b_fc2 = tf.Variable(tf.zeros([10]))
def inference(img):
fc1 = activation(tf.nn.bias_add(tf.matmul(img, W_fc1), b_fc1))
logits = tf.nn.bias_add(tf.matmul(fc1, W_fc2), b_fc2)
return logits
def loss(logits, labels):
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits, labels)
loss = tf.reduce_mean(cross_entropy)
return loss
def evaluation(logits, labels):
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(labels, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
return accuracy
logits = inference(X)
loss = loss(logits, y_)
train_op = tf.train.AdamOptimizer(1e-4).minimize(loss)
accuracy = evaluation(logits, y_)
# 先实例化一个Saver()类
saver = tf.train.Saver()
init = tf.initialize_all_variables()
with tf.Session() as sess:
sess.run(init)
for i in xrange(iteration):
batch = mnist.train.next_batch(batch_size)
if i%1000 == 0 and i:
train_accuracy = sess.run(accuracy, feed_dict={X: batch[0], y_: batch[1]})
print "step %d, train accuracy %g" %(i, train_accuracy)
sess.run(train_op, feed_dict={X: batch[0], y_: batch[1]})
print '[+] Test accuracy is %f' % sess.run(accuracy, feed_dict={X: mnist.test.images, y_: mnist.test.labels})
# 存储训练好的variables
save_path = saver.save(sess, model_path)
print "[+] Model saved in file: %s" % save_path
接下来是读取数据并做测试！
import tensorflow as tf
import sys
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('data', one_hot=True)
activation = tf.nn.relu
hidden1_units = 30
model_path = sys.path[0] + '/simple_mnist.ckpt'
X = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
W_fc1 = tf.Variable(tf.truncated_normal([784, hidden1_units], stddev=0.2))
b_fc1 = tf.Variable(tf.zeros([hidden1_units]))
W_fc2 = tf.Variable(tf.truncated_normal([hidden1_units, 10], stddev=0.2))
b_fc2 = tf.Variable(tf.zeros([10]))
def inference(img):
fc1 = activation(tf.nn.bias_add(tf.matmul(img, W_fc1), b_fc1))
logits = tf.nn.bias_add(tf.matmul(fc1, W_fc2), b_fc2)
return logits
def evaluation(logits, labels):
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(labels, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
return accuracy
logits = inference(X)
accuracy = evaluation(logits, y_)
saver = tf.train.Saver()
with tf.Session() as sess:
# 读取之前训练好的数据
load_path = saver.restore(sess, model_path)
print "[+] Model restored from %s" % load_path
print '[+] Test accuracy is %f' % sess.run(accuracy, feed_dict={X: mnist.test.images, y_: mnist.test.labels})
