保存和读取 TensorFlow 模型

保存和读取 TensorFlow 模型

训练一个模型的时间很长。但是你一旦关闭了 TensorFlow session，你所有训练的权重和偏置项都丢失了。如果你计划在之后重新使用这个模型，你需要重新训练！

幸运的是，TensorFlow 可以让你通过一个叫 tf.train.Saver 的类把你的进程保存下来。这个类可以把任何 tf.Variable存到你的文件系统。

保存变量

让我们通过一个简单地例子来保存 weights 和 bias Tensors。第一个例子你只是存两个变量，后面会教你如何把一个实际模型的所有权重保存下来。

import tensorflow as tf

# The file path to save the data
# 文件保存路径
save_file = './model.ckpt'

# Two Tensor Variables: weights and bias
# 两个 Tensor 变量：权重和偏置项
weights = tf.Variable(tf.truncated_normal([2, 3]))
bias = tf.Variable(tf.truncated_normal([3]))

# Class used to save and/or restore Tensor Variables
# 用来存取 Tensor 变量的类
saver = tf.train.Saver()

with tf.Session() as sess:
    # Initialize all the Variables
    # 初始化所有变量
    sess.run(tf.global_variables_initializer())

    # Show the values of weights and bias
   # 显示变量和权重
    print('Weights:')
    print(sess.run(weights))
    print('Bias:')
    print(sess.run(bias))

    # Save the model
    # 保存模型
    saver.save(sess, save_file)

Weights:

[[-0.97990924 1.03016174 0.74119264]

[-0.82581609 -0.07361362 -0.86653847]]

Bias:

[ 1.62978125 -0.37812829 0.64723819]

weights 和 bias Tensors 用 tf.truncated_normal() 函数设定了随机值。用  tf.train.Saver.save() 函数把这些值被保存在save_file 位置，命名为 "model.ckpt"，（".ckpt" 扩展名表示"checkpoint"）。

如果你使用 TensorFlow 0.11.0RC1 或者更新的版本，还会生成一个包含了 TensorFlow graph 的文件 "model.ckpt.meta"。

加载变量

现在这些变量已经存好了，让我们把它们加载到新模型里。

# Remove the previous weights and bias
# 移除之前的权重和偏置项
tf.reset_default_graph()

# Two Variables: weights and bias
# 两个变量：权重和偏置项
weights = tf.Variable(tf.truncated_normal([2, 3]))
bias = tf.Variable(tf.truncated_normal([3]))

# Class used to save and/or restore Tensor Variables
# 用来存取 Tensor 变量的类
saver = tf.train.Saver()

with tf.Session() as sess:
    # Load the weights and bias
    # 加载权重和偏置项
    saver.restore(sess, save_file)

    # Show the values of weights and bias
    # 显示权重和偏置项
    print('Weight:')
    print(sess.run(weights))
    print('Bias:')
    print(sess.run(bias))

Weights:

[[-0.97990924 1.03016174 0.74119264]

[-0.82581609 -0.07361362 -0.86653847]]

Bias:

[ 1.62978125 -0.37812829 0.64723819]

注意，你依然需要在 Python 中创建 weights 和 bias Tensors。tf.train.Saver.restore() 函数把之前保存的数据加载到  weights 和 bias 当中。

因为 tf.train.Saver.restore() 设定了 TensorFlow 变量，这里你不需要调用 tf.global_variables_initializer()了。

保存一个训练好的模型

让我们看看如何训练一个模型并保存它的权重。

从一个模型开始：

# Remove previous Tensors and Operations
# 移除之前的  Tensors 和运算
tf.reset_default_graph()

from tensorflow.examples.tutorials.mnist import input_data
import numpy as np

learning_rate = 0.001
n_input = 784  # MNIST 数据输入 (图片尺寸: 28*28)
n_classes = 10  # MNIST 总计类别 (数字 0-9)

# Import MNIST data
# 加载 MNIST 数据
mnist = input_data.read_data_sets('.', one_hot=True)

# Features and Labels
# 特征和标签
features = tf.placeholder(tf.float32, [None, n_input])
labels = tf.placeholder(tf.float32, [None, n_classes])

# Weights & bias
# 权重和偏置项
weights = tf.Variable(tf.random_normal([n_input, n_classes]))
bias = tf.Variable(tf.random_normal([n_classes]))

# Logits - xW + b
logits = tf.add(tf.matmul(features, weights), bias)

# Define loss and optimizer
# 定义损失函数和优化器
cost = tf.reduce_mean(\
    tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=labels))
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)\
    .minimize(cost)

# Calculate accuracy
# 计算准确率
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(labels, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

让我们训练模型并保存权重：

import math

save_file = './train_model.ckpt'
batch_size = 128
n_epochs = 100

saver = tf.train.Saver()

# Launch the graph
# 启动图
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    # Training cycle
    # 训练循环
    for epoch in range(n_epochs):
        total_batch = math.ceil(mnist.train.num_examples / batch_size)

        # Loop over all batches
        # 遍历所有 batch
        for i in range(total_batch):
            batch_features, batch_labels = mnist.train.next_batch(batch_size)
            sess.run(
                optimizer,
                feed_dict={features: batch_features, labels: batch_labels})

        # Print status for every 10 epochs
        # 每运行10个 epoch 打印一次状态
        if epoch % 10 == 0:
            valid_accuracy = sess.run(
                accuracy,
                feed_dict={
                    features: mnist.validation.images,
                    labels: mnist.validation.labels})
            print('Epoch {:<3} - Validation Accuracy: {}'.format(
                epoch,
                valid_accuracy))

    # Save the model
    # 保存模型
    saver.save(sess, save_file)
    print('Trained Model Saved.')

Epoch 0 - Validation Accuracy: 0.06859999895095825

Epoch 10 - Validation Accuracy: 0.20239999890327454

Epoch 20 - Validation Accuracy: 0.36980000138282776

Epoch 30 - Validation Accuracy: 0.48820000886917114

Epoch 40 - Validation Accuracy: 0.5601999759674072

Epoch 50 - Validation Accuracy: 0.6097999811172485

Epoch 60 - Validation Accuracy: 0.6425999999046326

Epoch 70 - Validation Accuracy: 0.6733999848365784

Epoch 80 - Validation Accuracy: 0.6916000247001648

Epoch 90 - Validation Accuracy: 0.7113999724388123

Trained Model Saved.

加载训练好的模型

让我们从磁盘中加载权重和偏置项，验证测试集准确率。

saver = tf.train.Saver()

# Launch the graph
# 加载图
with tf.Session() as sess:
    saver.restore(sess, save_file)

    test_accuracy = sess.run(
        accuracy,
        feed_dict={features: mnist.test.images, labels: mnist.test.labels})

print('Test Accuracy: {}'.format(test_accuracy))

Test Accuracy: 0.7229999899864197

就是这样！你现在知道如何保存再加载一个 TensorFlow 的训练模型了。下一章节让我们看看如何把权重和偏置项加载到修改过的模型中。