前言
首先，我们从一个直观的例子，讲解如何实现Tensorflow模型参数的保存以及保存后模型的读取。
然后，我们在之前多层感知机的基础上进行模型的参数保存，以及参数的读取。该项技术可以用于Tensorflow分段训练模型以及对经典模型进行fine tuning（微调）
Tensorflow 模型的保存与读取（直观）
模型参数存储
import tensorflow as tf
# 随机生成v1与v2变量
v1 = tf.Variable(tf.random_normal([1,2]), name="v1")
v2 = tf.Variable(tf.random_normal([2,3]), name="v2")
# 全局初始化
init_op = tf.global_variables_initializer()
# 调用Saver方法（重要）
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(init_op)
print ("V1:",sess.run(v1))
print ("V2:",sess.run(v2))
# 存储Session工作空间
saver_path = saver.save(sess, "./save/model.ckpt")
print ("Model saved in file: ", saver_path)
V1: [[1.2366687 0.4373563]]
V2: [[-0.9465265 -0.7147392 -2.421146 ]
[-0.48401725 0.40536404 0.21300188]]
Model saved in file: ./save/model.ckpt
模型存储的文件格式如下图所示：
模型存储文件
模型参数读取
import tensorflow as tf
v1 = tf.Variable(tf.random_normal([1,2]), name="v1")
v2 = tf.Variable(tf.random_normal([2,3]), name="v2")
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, "./save/model.ckpt")
print ("V1:",sess.run(v1))
print ("V2:",sess.run(v2))
print ("Model restored")
INFO:tensorflow:Restoring parameters from ./save/model.ckpt
V1: [[1.2366687 0.4373563]]
V2: [[-0.9465265 -0.7147392 -2.421146 ]
[-0.48401725 0.40536404 0.21300188]]
Model restored
Tensorflow 模型的保存与读取（多层感知机）
导入数据集
from __future__ import print_function
# Import MINST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("./data/", one_hot=True)
import tensorflow as tf
Extracting ./data/train-images-idx3-ubyte.gz
Extracting ./data/train-labels-idx1-ubyte.gz
Extracting ./data/t10k-images-idx3-ubyte.gz
Extracting ./data/t10k-labels-idx1-ubyte.gz
创建多层感知机模型
# 训练参数设置
learning_rate = 0.001
batch_size = 100
display_step = 1
model_path = "./save/model.ckpt" #模型存储路径
# 网络参数设置
n_hidden_1 = 256 # 1st layer number of features
n_hidden_2 = 256 # 2nd layer number of features
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)
# tf Graph input
x = tf.placeholder("float", [None, n_input])
y = tf.placeholder("float", [None, n_classes])
# Create model
def multilayer_perceptron(x, weights, biases):
# Hidden layer with RELU activation
layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
layer_1 = tf.nn.relu(layer_1)
# Hidden layer with RELU activation
layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
layer_2 = tf.nn.relu(layer_2)
# Output layer with linear activation
out_layer = tf.matmul(layer_2, weights['out']) + biases['out']
return out_layer
# Store layers weight & bias
weights = {
'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
'out': tf.Variable(tf.random_normal([n_hidden_2, n_classes]))
}
biases = {
'b1': tf.Variable(tf.random_normal([n_hidden_1])),
'b2': tf.Variable(tf.random_normal([n_hidden_2])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
# Construct model
pred = multilayer_perceptron(x, weights, biases)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Initializing the variables
init = tf.global_variables_initializer()
调用Saver方法
# 'Saver' 操作用于保存与读取所有的变量
saver = tf.train.Saver()
第一次训练（训练完成保存参数）
# Running first session
print("Starting 1st session...")
with tf.Session() as sess:
# Initialize variables
sess.run(init)
# Training cycle（迭代三次）
for epoch in range(3):
avg_cost = 0.
total_batch = int(mnist.train.num_examples/batch_size)
# Loop over all batches
for i in range(total_batch):
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop) and cost op (to get loss value)
_, c = sess.run([optimizer, cost], feed_dict={x: batch_x,
y: batch_y})
# Compute average loss
avg_cost += c / total_batch
# Display logs per epoch step
if epoch % display_step == 0:
print ("Epoch:", '%04d' % (epoch+1), "cost=", \
"{:.9f}".format(avg_cost))
print("First Optimization Finished!")
# Test model
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
# Calculate accuracy
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print("Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))
# 保存模型参数到硬盘上
save_path = saver.save(sess, model_path)
print("Model saved in file: %s" % save_path)
Starting 1st session...
Epoch: 0001 cost= 172.468734065
Epoch: 0002 cost= 43.036823805
Epoch: 0003 cost= 26.978232009
First Optimization Finished!
Accuracy: 0.9084
Model saved in file: ./save/model.ckpt
第二次训练（加载第一次参数）
# Running a new session
print("Starting 2nd session...")
with tf.Session() as sess:
# Initialize variables
sess.run(init)
# Restore model weights from previously saved model
load_path = saver.restore(sess, model_path)
print("Model restored from file: %s" % save_path)
# Resume training
for epoch in range(7):
avg_cost = 0.
total_batch = int(mnist.train.num_examples / batch_size)
# Loop over all batches
for i in range(total_batch):
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop) and cost op (to get loss value)
_, c = sess.run([optimizer, cost], feed_dict={x: batch_x,
y: batch_y})
# Compute average loss
avg_cost += c / total_batch
# Display logs per epoch step
if epoch % display_step == 0:
print("Epoch:", '%04d' % (epoch + 1), "cost=", \
"{:.9f}".format(avg_cost))
print("Second Optimization Finished!")
# Test model
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
# Calculate accuracy
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print("Accuracy:", accuracy.eval(
{x: mnist.test.images, y: mnist.test.labels}))
Starting 2nd session...
INFO:tensorflow:Restoring parameters from ./save/model.ckpt
Model restored from file: ./save/model.ckpt
Epoch: 0001 cost= 18.712020244
Epoch: 0002 cost= 13.624892972
Epoch: 0003 cost= 10.156988694
Epoch: 0004 cost= 7.652410518
Epoch: 0005 cost= 5.658380691
Epoch: 0006 cost= 4.276506317
Epoch: 0007 cost= 3.249772967
Second Optimization Finished!
Accuracy: 0.9381
