CNN循环神经网络MNIST数据集分类+tensorboard

本文来源吾爱破解论坛

昨天的例子https://www.52pojie.cn/thread-903416-1-1.html是一个简单的三层神经网络，acc达到0.98
今天分享同样数据集的CNN处理方式，同时加上tensorboard，可以看到清晰的结构图，迭代1000次acc收敛到0.992
先放代码，注释比较详细，变量名字看单词就能知道啥意思
[Python] 纯文本查看 复制代码

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

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

batch_size = 100
n_batch = mnist.train.num_examples // batch_size

def weight_variable(shape, name):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial, name=name)

def bias_variable(shape, name):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial, name=name)

def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding="SAME")     # 1, 3位是1/   2， 4位是步长

def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME")  # 2， 3是步长

with tf.name_scope('input'):
    x = tf.placeholder(tf.float32, [None, 784], name='x_input')
    y = tf.placeholder(tf.float32, [None, 10], name='y_input')
    with tf.name_scope('x_image'):
        # 转变x格式为4D向量[batch, in_height, in_width, in_channels] 通道为1表示黑白
        x_image = tf.reshape(x, [-1, 28, 28, 1], name='x_image')

with tf.name_scope('Converlution_1'):
    # 初始化第一个卷积层的权重和偏置
    with tf.name_scope('Weight_Converlution_1'):
        Weight_Converlution_1 = weight_variable([5, 5, 1, 32],
                                                name='Weight_Converlution_1')  # 5 * 5的卷积窗口，32个卷积核从1个平面抽取特征
                                                                                # 生成32个特征图
    with tf.name_scope('Biase_Converlution_1'):
        Biase_Converlution_1 = bias_variable([32], name='Biase_Converlution_1')  # 每个卷积核一个偏置值

    # 把x_image和权值向量进行卷积，再加上偏置值，应用于relu激活函数
    with tf.name_scope('Converlution2d_1'):
        Converlution2d_1 = conv2d(x_image, Weight_Converlution_1) + Biase_Converlution_1
    with tf.name_scope('ReLu_1'):
        ReLu_Converlution_l = tf.nn.relu(Converlution2d_1)
    with tf.name_scope('Pool_1'):
        Pooling_1 = max_pool_2x2(ReLu_Converlution_l)  # max-pooling

with tf.name_scope('Converlution_2'):
    # 初始化第二个卷积层的权重和偏置
    with tf.name_scope('Weight_Converlution_2'):
        Weight_Converlution_2 = weight_variable([5, 5, 32, 64],
                                                name='Weight_Converlution_2')  # 5 * 5的卷积窗口，64个卷积核从32个平面抽取特征
        # 生成64个特征图
    with tf.name_scope('Biase_Converlution_2'):
        Biase_Converlution_2 = bias_variable([64], name='Biase_Converlution_2')
    with tf.name_scope('Cov2d_2'):
        Converlution2d_2 = conv2d(Pooling_1, Weight_Converlution_2) + Biase_Converlution_2
    with tf.name_scope('ReLu_2'):
        ReLu_Converlution_2 = tf.nn.relu(Converlution2d_2)
    with tf.name_scope('Pool_2'):
        Pooling_2 = max_pool_2x2(ReLu_Converlution_2)

# 初始化第一个全连接层
with tf.name_scope('Fully_Connected_L1'):
    with tf.name_scope('Weight_Fully_Connected_L1'):
        Weight_Fully_Connected_L1 = weight_variable([7 * 7 * 64, 1024],
                                                    name='Weight_Fully_Connected_L1')  # 上一层有7*7*64个神经元，全连接层有1024个神经元
    with tf.name_scope('Biase_Fully_Connected_L1'):
        Biase_Fully_Connected_L1 = bias_variable([1024], name='Biase_Fully_Connected_L1')

    # 把池化层2的输出扁平化为1维
    with tf.name_scope('Pooling_2_to_Flat'):
        Pooling_2_to_Flat = tf.reshape(Pooling_2, [-1, 7 * 7 * 64], name='Pooling_2_to_Flat')  # -1表示任意值
    with tf.name_scope('Wx_Plus_B1'):
        Wx_Plus_B1 = tf.matmul(Pooling_2_to_Flat, Weight_Fully_Connected_L1) + Biase_Fully_Connected_L1
    with tf.name_scope('ReLu_Fully_Connected_L1'):
        ReLu_Fully_Connected_L1 = tf.nn.relu(Wx_Plus_B1)
    # Keep——Prob
    with tf.name_scope('keep_prob'):
        keep_prob = tf.placeholder(tf.float32, name='keep_prob')
    with tf.name_scope('Fully_Connected_L1_Drop'):
        Fully_Connected_L1_Drop = tf.nn.dropout(ReLu_Fully_Connected_L1, keep_prob, name='Fully_Connected_L1_Drop')

# 初始化第二个全连接层
with tf.name_scope('Fully_Connected_L2'):
    with tf.name_scope('Weight_Fully_Connected_L2'):
        Weight_Fully_Connected_L2 = weight_variable([1024, 10], name='Weight_Fully_Connected_L2')
    with tf.name_scope('Biase_Fully_Connected_L2'):
        Biase_Fully_Connected_L2 = bias_variable([10], name='Biase_Fully_Connected_L1')
    with tf.name_scope('Wx_Plus_B2'):
        Wx_Plus_B2 = tf.matmul(Fully_Connected_L1_Drop, Weight_Fully_Connected_L2) + Biase_Fully_Connected_L2
    with tf.name_scope('SoftMax'):
        prediction = tf.nn.softmax(Wx_Plus_B2)
# 交叉熵函数
with tf.name_scope('cross_entropy'):
    cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=y,
                                                                              logits=prediction), name='cross_entropy')
    tf.summary.scalar('cross_entropy', cross_entropy)    # 显示标量信息  tf.summary.scalar(tags, values, collections=None, name=None)
# AdamOptimizer优化器
with tf.name_scope('train'):
    train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

with tf.name_scope('accuracy'):
    with tf.name_scope('correct_prediction'):
        correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
    with tf.name_scope('accuracy'):
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
        tf.summary.scalar('accuracy', accuracy)

# 合并所有summary
merged = tf.summary.merge_all()

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    train_writer = tf.summary.FileWriter('logs/train', sess.graph)
    test_writer = tf.summary.FileWriter('logs/test', sess.graph)
    for i in range(101):
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        sess.run(train_step, feed_dict={x: batch_xs,
                                        y: batch_ys,
                                        keep_prob: 0.5})
        # 记录训练集计算的参数
        summary = sess.run(merged, feed_dict={x: batch_xs,
                                              y: batch_ys,
                                              keep_prob: 1})
        train_writer.add_summary(summary, i)

        # 记录训练集计算的参数
        batch_xs, batch_ys = mnist.test.next_batch(batch_size)

        summary = sess.run(merged, feed_dict={x: batch_xs,
                                              y: batch_ys,
                                              keep_prob: 1.0})
        test_writer.add_summary(summary, i)

        test_acc = sess.run(accuracy, feed_dict={x: mnist.test.images,
                                                 y: mnist.test.labels,
                                                 keep_prob: 1.0})
        train_acc = sess.run(accuracy, feed_dict={x: mnist.train.images[:10000],
                                                  y: mnist.train.labels[:10000],
                                                  keep_prob: 1.0})
        print("Iter " + str(i) +
              ", Testing Accuracy " + str(test_acc) +
              ", Training Accuracy " + str(train_acc))

TIM图片20190319210730.png (43.92 KB, 下载次数: 5)

下载附件  保存到相册

2019-3-19 21:08 上传

TIM图片20190319210713.png (40.09 KB, 下载次数: 2)

下载附件  保存到相册

2019-3-19 21:08 上传

TIM图片20190319210241.png (55.04 KB, 下载次数: 0)

下载附件  保存到相册

2019-3-19 21:08 上传