TensorFlow学习笔记(3)--MINIST数字识别

learn TensorFlow third

Posted by 石头人m on December 14, 2017

1.MNIST数据

​ MNIST数据集是NIST数据集的一个子集,包含60000张图片作为训练数据,10000张图片作为测试数据。每张图片大小为28x28。详细介绍:http:yann.lecun.com/exdb/mnist 。

​ TensorFlow提供了一个类来处理MNIST数据。这个类会自动下载并转化MNIST数据的格式,将数据从原始的数据包中解析成训练和测试神经网络时使用的格式。

​ 在MNIST数据集上实现 激活函数、隐藏层、指数衰减学习率、正则化、滑动平均模型 :

# -*- coding: utf-8 -*-
# @Time    : 2017-12-11 19:29
# @Author  : Storm
# @File    : chapter05-01.py

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

# MNIST数据集相关的常数
INPUT_NODE = 784  # 输入层的节点数。对于MNIST数据集,这个就等于图片的像素。
OUTPUT_NODE = 10  # 输出层的节点数。等于类别的数目(0~9 这10个数字)。

# 配置神经网络的参数
LAYER1_NODE = 500  # 隐藏层节点数。
BATCH_SIZE = 100  # batch的数据个数。

LEARNING_RATE_BASE = 0.8  # 基础学习率
LEARNING_RATE_DECAY = 0.99  # 学习率的衰减率
REGULARIZATION_RATE = 0.0001  # 正则化项在损失函数中的系数
TRAINING_STEPS = 50000  # 训练轮数
MOVING_AVERAGE_DECAY = 0.99  # 滑动平均衰减率


# 一个辅助函数,给定神经网络的输入和所有参数,计算神经网络的前向传播结果
def inference(input_tensor, avg_class, weights1, biases1, weights2, biases2):
    # 不使用滑动平均类
    if avg_class == None:
        layer1 = tf.nn.relu(tf.matmul(input_tensor, weights1) + biases1)
        return tf.matmul(layer1, weights2) + biases2

    else:
        # 使用滑动平均类
        layer1 = tf.nn.relu(tf.matmul(input_tensor, avg_class.average(weights1)) + avg_class.average(biases1))
        return tf.matmul(layer1, avg_class.average(weights2)) + avg_class.average(biases2)


# 训练模型的过程
def train(mnist):
    x = tf.placeholder(tf.float32, [None, INPUT_NODE], name='x-input')
    y_ = tf.placeholder(tf.float32, [None, OUTPUT_NODE], name='y-input')
    # 生成隐藏层的参数。
    weights1 = tf.Variable(tf.truncated_normal([INPUT_NODE, LAYER1_NODE], stddev=0.1))
    biases1 = tf.Variable(tf.constant(0.1, shape=[LAYER1_NODE]))
    # 生成输出层的参数。
    weights2 = tf.Variable(tf.truncated_normal([LAYER1_NODE, OUTPUT_NODE], stddev=0.1))
    biases2 = tf.Variable(tf.constant(0.1, shape=[OUTPUT_NODE]))

    # 计算不含滑动平均类的前向传播结果
    y = inference(x, None, weights1, biases1, weights2, biases2)

    # 定义训练轮数及相关的滑动平均类
    global_step = tf.Variable(0, trainable=False)
    variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
    variables_averages_op = variable_averages.apply(tf.trainable_variables())
    average_y = inference(x, variable_averages, weights1, biases1, weights2, biases2)

    # 计算交叉熵及其平均值
    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
    cross_entropy_mean = tf.reduce_mean(cross_entropy)

    # 损失函数的计算
    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
    regularaztion = regularizer(weights1) + regularizer(weights2)
    loss = cross_entropy_mean + regularaztion

    # 设置指数衰减的学习率。
    learning_rate = tf.train.exponential_decay(
        LEARNING_RATE_BASE,
        global_step,
        mnist.train.num_examples / BATCH_SIZE,
        LEARNING_RATE_DECAY,
        staircase=True)

    # 优化损失函数
    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)

    # 反向传播更新参数和更新每一个参数的滑动平均值
    with tf.control_dependencies([train_step, variables_averages_op]):
        train_op = tf.no_op(name='train')

    # 计算正确率
    correct_prediction = tf.equal(tf.argmax(average_y, 1), tf.argmax(y_, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    # 初始化会话,并开始训练过程。
    with tf.Session() as sess:
        tf.global_variables_initializer().run()
        validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels}
        test_feed = {x: mnist.test.images, y_: mnist.test.labels}

        # 循环的训练神经网络。
        for i in range(TRAINING_STEPS):
            if i % 1000 == 0:
                validate_acc = sess.run(accuracy, feed_dict=validate_feed)
                print("After %d training step(s), validation accuracy using average model is %g " % (i, validate_acc))

            xs, ys = mnist.train.next_batch(BATCH_SIZE)
            sess.run(train_op, feed_dict={x: xs, y_: ys})

        test_acc = sess.run(accuracy, feed_dict=test_feed)
        print(("After %d training step(s), test accuracy using average model is %g" % (TRAINING_STEPS, test_acc)))


def main(argv=None):
    mnist = input_data.read_data_sets("./datasets/MNIST_data", one_hot=True)
    train(mnist)


if __name__ == '__main__':
    main()

2.变量管理

​ TensorFlow提供了通过变量名称来创建或者获取一个变量的机制。这样 在不同的函数中可以直接通过变量的名字来使用变量,而不需要将变量通过参数的形式到处传递。tf.get_variable和tf.variable_scope两个函数。

​ 通过tf.variable_scope函数可以控制tf.get_variable函数的语义:

import tensorflow as tf

# 在名字为foo的命名空间内创建名字为v的变量
with tf.variable_scope("foo"):
    v = tf.get_variable("v", [1], initializer=tf.constant_initializer(1.0))

# 因为在命名空间foo中已经存在名字为v的变量,所以下面的代码会出错
# with tf.variable_scope("foo"):
# v = tf.get_variable("v", [1])

# 在生成上下文管理器时,将参数reuse设置为True。这样tf.get_variable函数将直接获取已经声明的变量。
with tf.variable_scope("foo", reuse=True):
    v1 = tf.get_variable("v", [1])
print(v == v1)  #True

# 将参数reuse设置为True时,tf.get_variable将只能获取已经创建过的变量。下面的语句会出错。
# with tf.variable_scope("bar", reuse=True):
# v = tf.get_variable("v", [1])

​ 嵌套上下文管理器中的reuse参数的使用:

with tf.variable_scope("root"):
    print(tf.get_variable_scope().reuse)

    with tf.variable_scope("foo", reuse=True):
        print(tf.get_variable_scope().reuse)

        # 新建一个嵌套的上下文管理器,不指定reuse,这是reuse会与外面一层保持一致
        with tf.variable_scope("bar"):
            print(tf.get_variable_scope().reuse)

    print(tf.get_variable_scope().reuse)
# False
# True
# True
# False

​ 通过variable_scope来管理变量,可以通过变量的名称来获取变量:

v1 = tf.get_variable("v", [1])
print(v1.name)  # v:0

with tf.variable_scope("foo", reuse=True):
    v2 = tf.get_variable("v", [1])
print(v2.name)  # foo/v:0

with tf.variable_scope("foo"):
    with tf.variable_scope("bar"):
        v3 = tf.get_variable("v", [1])
        print(v3.name)  # foo/bar/v:0

v4 = tf.get_variable("v1", [1])
print(v4.name)  # v1:0

with tf.variable_scope("", reuse=True):
    v5 = tf.get_variable("foo/bar/v", [1])
    print(v5 == v3)  # True
    v6 = tf.get_variable("v1", [1])
    print(v6 == v4)  # True

3.模型持久化

​ TensorFlow提供了一个非常简单的API来保存和还原一个神经网络模型,tf.train.Saver类。

# -*- coding: utf-8 -*-
# @Time    : 2017-12-12 20:28
# @Author  : Storm
# @File    : chapter05-03.py
# 模型持久化

import tensorflow as tf

# 1. 保存计算两个变量和的模型。
v1 = tf.Variable(tf.constant(1.0, shape=[1]), name="v1")
v2 = tf.Variable(tf.constant(2.0, shape=[1]), name="v2")
result = v1 + v2

init_op = tf.global_variables_initializer()
saver = tf.train.Saver()

with tf.Session() as sess:
    sess.run(init_op)
    saver.save(sess, "Saved_model/model.ckpt")

# 2. 加载保存了两个变量和的模型。
with tf.Session() as sess:
    saver.restore(sess, "Saved_model/model.ckpt")
    print(sess.run(result))

# 3. 直接加载持久化的图。
saver = tf.train.import_meta_graph("Saved_model/model.ckpt.meta")
with tf.Session() as sess:
    saver.restore(sess, "Saved_model/model.ckpt")
    print(sess.run(tf.get_default_graph().get_tensor_by_name("add:0")))

# 4. 变量重命名。
v1 = tf.Variable(tf.constant(1.0, shape=[1]), name="other-v1")
v2 = tf.Variable(tf.constant(2.0, shape=[1]), name="other-v2")
saver = tf.train.Saver({"v1": v1, "v2": v2})

​ 滑动平均类的保存:

# -*- coding: utf-8 -*-
# @Time    : 2017-12-12 20:37
# @Author  : Storm
# @File    : chapter05-04.py
# 滑动平均类的保存

import tensorflow as tf

# 1.使用滑动平均。
v = tf.Variable(0, dtype=tf.float32, name="v")
for variables in tf.global_variables():
    print(variables.name)

ema = tf.train.ExponentialMovingAverage(0.99)
maintain_averages_op = ema.apply(tf.global_variables())
for variables in tf.global_variables():
    print(variables.name)

# 2.保存滑动平均模型。
saver = tf.train.Saver()
with tf.Session() as sess:
    init_op = tf.global_variables_initializer()
    sess.run(init_op)

    sess.run(tf.assign(v, 10))
    sess.run(maintain_averages_op)
    # 保存的时候会将v:0  v/ExponentialMovingAverage:0这两个变量都存下来。
    saver.save(sess, "Saved_model/model2.ckpt")
    print(sess.run([v, ema.average(v)]))

# 3.加载滑动平均模型。
v = tf.Variable(0, dtype=tf.float32, name="v")

# 通过变量重命名将原来变量v的滑动平均值直接赋值给v。
saver = tf.train.Saver({"v/ExponentialMovingAverage": v})
with tf.Session() as sess:
    saver.restore(sess, "Saved_model/model2.ckpt")
    print(sess.run(v))

​ variables_to_restore函数的使用样例:

import tensorflow as tf

v = tf.Variable(0, dtype=tf.float32, name="v")
ema = tf.train.ExponentialMovingAverage(0.99)
print(ema.variables_to_restore())
# {'v/ExponentialMovingAverage': <tf.Variable 'v:0' shape=() dtype=float32_ref>}

saver = tf.train.Saver({"v/ExponentialMovingAverage": v})
with tf.Session() as sess:
    saver.restore(sess, "Saved_model/model2.ckpt")
    print(sess.run(v))
# 0.0999999

4.TensorFlow最佳实践样例程序

​ 每隔一段时间保存一次模型训练的中间结果,将训练和测试分成两个独立的程序,将前向传播过程抽象成一个单独的库函数。

​ minst_inference.py,定义了前向传播的过程以及神经网络中的参数:

# -*- coding: utf-8 -*-
# @Time    : 2017-12-14 10:28
# @Author  : Storm
# @File    : mnist_inference.py

import tensorflow as tf

INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500


def get_weight_variable(shape, regularizer):
    weights = tf.get_variable("weights", shape, initializer=tf.truncated_normal_initializer(stddev=0.1))
    if regularizer != None: tf.add_to_collection('losses', regularizer(weights))
    return weights


def inference(input_tensor, regularizer):
    with tf.variable_scope('layer1'):
        weights = get_weight_variable([INPUT_NODE, LAYER1_NODE], regularizer)
        biases = tf.get_variable("biases", [LAYER1_NODE], initializer=tf.constant_initializer(0.0))
        layer1 = tf.nn.relu(tf.matmul(input_tensor, weights) + biases)

    with tf.variable_scope('layer2'):
        weights = get_weight_variable([LAYER1_NODE, OUTPUT_NODE], regularizer)
        biases = tf.get_variable("biases", [OUTPUT_NODE], initializer=tf.constant_initializer(0.0))
        layer2 = tf.matmul(layer1, weights) + biases

    return layer2

​ mnist_train.py,定义了神经网络的训练过程:

# -*- coding: utf-8 -*-
# @Time    : 2017-12-14 10:29
# @Author  : Storm
# @File    : mnist_train.py

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
import os

BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 30000
MOVING_AVERAGE_DECAY = 0.99
MODEL_SAVE_PATH = "MNIST_model/"
MODEL_NAME = "mnist_model"


def train(mnist):
    x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')
    y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')

    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
    y = mnist_inference.inference(x, regularizer)
    global_step = tf.Variable(0, trainable=False)

    variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
    variables_averages_op = variable_averages.apply(tf.trainable_variables())
    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
    cross_entropy_mean = tf.reduce_mean(cross_entropy)
    loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))
    learning_rate = tf.train.exponential_decay(
        LEARNING_RATE_BASE,
        global_step,
        mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY,
        staircase=True)
    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
    with tf.control_dependencies([train_step, variables_averages_op]):
        train_op = tf.no_op(name='train')

    saver = tf.train.Saver()
    with tf.Session() as sess:
        tf.global_variables_initializer().run()

        for i in range(TRAINING_STEPS):
            xs, ys = mnist.train.next_batch(BATCH_SIZE)
            _, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: xs, y_: ys})
            if i % 1000 == 0:
                print("After %d training step(s), loss on training batch is %g." % (step, loss_value))
                saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)


def main(argv=None):
    mnist = input_data.read_data_sets("../datasets/MNIST_data", one_hot=True)
    train(mnist)


if __name__ == '__main__':
    tf.app.run()

​ mnist_eval.py,定义了测试过程:

# -*- coding: utf-8 -*-
# @Time    : 2017-12-14 10:31
# @Author  : Storm
# @File    : mnist_eval.py

import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
import mnist_train

# 加载的时间间隔。
EVAL_INTERVAL_SECS = 10


def evaluate(mnist):
    with tf.Graph().as_default() as g:
        x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')
        y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')
        validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels}

        y = mnist_inference.inference(x, None)
        correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

        variable_averages = tf.train.ExponentialMovingAverage(mnist_train.MOVING_AVERAGE_DECAY)
        variables_to_restore = variable_averages.variables_to_restore()
        saver = tf.train.Saver(variables_to_restore)

        while True:
            with tf.Session() as sess:
                ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)
                if ckpt and ckpt.model_checkpoint_path:
                    saver.restore(sess, ckpt.model_checkpoint_path)
                    global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
                    accuracy_score = sess.run(accuracy, feed_dict=validate_feed)
                    print("After %s training step(s), validation accuracy = %g" % (global_step, accuracy_score))
                else:
                    print('No checkpoint file found')
                    return
            time.sleep(EVAL_INTERVAL_SECS)


def main(argv=None):
    mnist = input_data.read_data_sets("../datasets/MNIST_data", one_hot=True)
    evaluate(mnist)


if __name__ == '__main__':
    main()

TensorFlow 实战Google深度学习框架(第五章)