版权声明：人工智能/机器学习/深度学习交流QQ群：811460433 , 微信公众号：程序员深度学习 https://blog.csdn.net/sinat_24143931/article/details/86430602
人工智能/机器学习/深度学习交流QQ群：116270156 也可以扫一扫下面二维码加入微信群，如果二维码失效，可以添加博主个人微信，拉你进群 
将训练好的模型参数保存起来，以便以后进行验证或测试，这是我们经常要做的事情。tf里面提供模型保存的是tf.train.Saver()模块。
1. 代码详解
模型保存，先要创建一个Saver对象：如
saver=tf.train.Saver()
在创建这个Saver对象的时候，有一个参数我们经常会用到，就是 max_to_keep 参数，这个是用来设置保存模型的个数，默认为5，即 max_to_keep=5，保存最近的5个模型。如果你想每训练一代（epoch)就想保存一次模型，则可以将 max_to_keep设置为None或者0，如：
saver=tf.train.Saver(max_to_keep=0)
但是这样做除了多占用硬盘，并没有实际多大的用处，因此不推荐。
当然，如果你只想保存最后一代的模型，则只需要将max_to_keep设置为1即可，即
saver=tf.train.Saver(max_to_keep=1)
创建完saver对象后，就可以保存训练好的模型了，如：
saver.save(sess,'ckpt/mnist.ckpt',global_step=step)
第一个参数sess,这个就不用说了。第二个参数设定保存的路径和名字，第三个参数将训练的次数作为后缀加入到模型名字中。
saver.save(sess, ‘my-model’, global_step=0) ==> filename: ‘my-model-0’
…
saver.save(sess, ‘my-model’, global_step=1000) ==> filename: ‘my-model-1000’
下面看下mnist实例：
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# number 1 to 10 data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
def compute_accuracy(v_xs, v_ys):
global prediction
y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1})
correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1})
return result
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W):
# stride [1, x_movement, y_movement, 1]
# Must have strides[0] = strides[3] = 1
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
# stride [1, x_movement, y_movement, 1]
#ksize [1,pool_op_length,pool_op_width,1]
# Must have ksize[0] = ksize[3] = 1
return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784]) # 28x28
ys = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs, [-1, 28, 28, 1])
# print(x_image.shape) # [n_samples, 28,28,1]
## conv1 layer ##
W_conv1 = weight_variable([5,5, 1,32]) # patch 5x5, in size 1, out size 32
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 28x28x32
h_pool1 = max_pool_2x2(h_conv1) # output size 14x14x32
## conv2 layer ##
W_conv2 = weight_variable([5,5, 32, 64]) # patch 5x5, in size 32, out size 64
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 14x14x64
h_pool2 = max_pool_2x2(h_conv2) # output size 7x7x64
##flat h_pool2##
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64]) # [n_samples, 7, 7, 64] ->> [n_samples, 7*7*64]
## fc1 layer ##
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
## fc2 layer ##
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
reduction_indices=[1])) # loss
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
saver=tf.train.Saver(max_to_keep=1)
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5})
if i % 50 == 0:
print(compute_accuracy(mnist.test.images, mnist.test.labels))
saver.save(sess,'ckpt/mnist.ckpt',global_step=i+1)
下面两行代码就是保存模型的代码，虽然我在每训练完一代的时候，都进行了保存，但后一次保存的模型会覆盖前一次的，最终只会保存最后一次。因此我们可以节省时间，将保存代码放到循环之外（仅适用max_to_keep=1,否则还是需要放在循环内).
saver=tf.train.Saver(max_to_keep=1)
saver.save(sess,'ckpt/mnist.ckpt',global_step=i+1)
在实验中，最后一代可能并不是验证精度最高的一代，因此我们并不想默认保存最后一代，而是想保存验证精度最高的一代，则加个中间变量和判断语句就可以了。
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
saver=tf.train.Saver(max_to_keep=1)
max_acc=0
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5})
if i % 50 == 0:
val_acc = compute_accuracy(mnist.test.images, mnist.test.labels)
print(val_acc)
if val_acc>max_acc:
max_acc=val_acc
saver.save(sess,'ckpt/mnist.ckpt',global_step=i+1)
模型的恢复用的是restore()函数，它需要两个参数restore(sess, save_path)，save_path指的是保存的模型路径。我们可以使用tf.train.latest_checkpoint（）来自动获取最后一次保存的模型。如：
model_file=tf.train.latest_checkpoint('ckpt/')
saver.restore(sess,model_file)
则程序后半段代码我们可以改为：
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
is_train=False
saver=tf.train.Saver(max_to_keep=1)
#训练阶段
if is_train:
max_acc=0
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5})
if i % 50 == 0:
val_acc = compute_accuracy(mnist.test.images, mnist.test.labels)
print(val_acc)
if val_acc>max_acc:
max_acc=val_acc
saver.save(sess,'ckpt/mnist.ckpt',global_step=i+1)
#验证阶段
else:
model_file=tf.train.latest_checkpoint('ckpt/')
saver.restore(sess,model_file)
val_acc = compute_accuracy(mnist.test.images, mnist.test.labels)
print('val_acc:%f'%(val_acc))
下面的代码就是模型保存与恢复的代码，用一个bool变量is_train来控制训练和验证两个阶段。
is_train=False
saver=tf.train.Saver(max_to_keep=1)
if val_acc>max_acc:
max_acc=val_acc
saver.save(sess,'ckpt/mnist.ckpt',global_step=i+1)
model_file=tf.train.latest_checkpoint('ckpt/')
saver.restore(sess,model_file)
整个源程序：
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# number 1 to 10 data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
def compute_accuracy(v_xs, v_ys):
global prediction
y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1})
correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1})
return result
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W):
# stride [1, x_movement, y_movement, 1]
# Must have strides[0] = strides[3] = 1
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
# stride [1, x_movement, y_movement, 1]
#ksize [1,pool_op_length,pool_op_width,1]
# Must have ksize[0] = ksize[3] = 1
return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784]) # 28x28
ys = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs, [-1, 28, 28, 1])
# print(x_image.shape) # [n_samples, 28,28,1]
## conv1 layer ##
W_conv1 = weight_variable([5,5, 1,32]) # patch 5x5, in size 1, out size 32
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 28x28x32
h_pool1 = max_pool_2x2(h_conv1) # output size 14x14x32
## conv2 layer ##
W_conv2 = weight_variable([5,5, 32, 64]) # patch 5x5, in size 32, out size 64
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 14x14x64
h_pool2 = max_pool_2x2(h_conv2) # output size 7x7x64
##flat h_pool2##
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64]) # [n_samples, 7, 7, 64] ->> [n_samples, 7*7*64]
## fc1 layer ##
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
## fc2 layer ##
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
reduction_indices=[1])) # loss
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
is_train=False
saver=tf.train.Saver(max_to_keep=1)
#训练阶段
if is_train:
max_acc=0
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5})
if i % 50 == 0:
val_acc = compute_accuracy(mnist.test.images, mnist.test.labels)
print(val_acc)
if val_acc>max_acc:
max_acc=val_acc
saver.save(sess,'ckpt/mnist.ckpt',global_step=i+1)
#验证阶段
else:
model_file=tf.train.latest_checkpoint('ckpt/')
saver.restore(sess,model_file)
val_acc = compute_accuracy(mnist.test.images, mnist.test.labels)
print('val_acc:%f'%(val_acc))
2. 最后
欢迎大家扫一扫下面二维码加入微信交流群，如果二维码失效，可以添加博主个人微信，拉你进群
传送门----->Tensorflow系列教程