【Tool】Tensorflow 基础学习 II 模型保存和加载

Tags: Tool DeepLearning

在训练模型的时候，我们经常需要保存一些中间的训练结果，以便中断训练后能够再从checkpoints处继续上次训练；或者有时候进行迁移学习的时候，我们要继续别人的训练结果，这个时候就用到别人训练好的模型。
Tensorflow中涉及到模型的保存和加载主要是tf.train.Saver()这个类。其中主要用到save和restore两个方法。
Saver类构造函数：

__init__(
    var_list=None,
    reshape=False,
    sharded=False,
    max_to_keep=5,
    keep_checkpoint_every_n_hours=10000.0,
    name=None,
    restore_sequentially=False,
    saver_def=None,
    builder=None,
    defer_build=False,
    allow_empty=False,
    write_version=tf.train.SaverDef.V2,
    pad_step_number=False,
    save_relative_paths=False,
    filename=None
)

• var_list: 需要保存的变量，如果不指定保存sess中所有变量
• max_to_keep: 最多的保存checkpoint数目，默认是5
• keep_checkpoint_every_n_hours: 多久保存一次，默认是10,000小时
  save方法:

save(
    sess,
    save_path,
    global_step=None,
    latest_filename=None,
    meta_graph_suffix='meta',
    write_meta_graph=True,
    write_state=True,
    strip_default_attrs=False
)

通过传如sess, 和sava_path来保存checkpoints, 返回保存路径的前缀。
restore方法：

restore(
    sess,
    save_path
)

• save_path: 可以使用前面save方法返回的路径也可以使用latest_checkpoint()来获得保存路径。

下面这个例子使用minist数据集解释了如何在训练过程中保存训练中间结果，以及如何从上次训练的结果处继续训练。

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
import tensorflow as tf 

# parameters
learning_rate = 0.001
batch_size = 100
display_step = 1
model_path = "/tmp/model.ckpt"

# network parameters
n_input = 784 # (28*28)
n_hidden_1 = 128
n_hidden_2 = 256
n_classes = 10

# Graph Input
x = tf.placeholder("float", [None, n_input])
y = tf.placeholder("float", [None, n_classes])

def multilayer_perceptron(x, weights, biases):
    layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
    layer_1 = tf.nn.relu(layer_1)
    layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
    layer_2 = tf.nn.relu(layer_2)

    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]))
}

pred = multilayer_perceptron(x, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

init = tf.global_variables_initializer()

# 'Saver' op to save and restore all the variables
saver = tf.train.Saver()

# Running first session
print("Starting 1st session...")
with tf.Session() as sess:
    # Initialize variables
    sess.run(init)

    # Training cycle
    for epoch in range(10):
        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})) # ??

    # Save model weights to disk
    save_path = saver.save(sess, model_path)
    print("Model saved in file: %s" % save_path)

# 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}))