TensorFlow结合mnist进行卷积模型训练

TensorFlow 卷积

 2018/11/26   Share

卷积神经网络组成

输入层INPUT
卷积层CONV
激活函数RELU
池化层POOL
全连接层FC

卷积模型训练

初始化

import os

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

mnist = input_data.read_data_sets('../MNIST_DATA', one_hot=True)

# 每个批次的大小
batch_size = 100
# 计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size


# 初始化权值
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)  # 生成一个截断的正态分布
    return tf.Variable(initial)


# 初始化偏置
def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)


# 卷积层
def conv2d(x, W):
    # x input tensor of shape `[batch, in_height, in_width, in_channels]` 通道数，黑白为1，彩色为3
    # W filter / kernel tensor of shape [filter_height, filter_width, in_channels, out_channels]
    # `strides[0] = strides[3] = 1`. strides[1]代表x方向的步长，strides[2]代表y方向的步长
    # padding: A `string` from: `"SAME", "VALID"` same会补0，valid不会补0
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')


# 池化层
def max_pool_2x2(x):
    # ksize [1,x,y,1] 窗口大小
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')


# 定义两个placeholder
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
# 改变x的格式转为4D的向量[batch, in_height, in_width, in_channels]`
x_image = tf.reshape(x, [-1, 28, 28, 1])

卷积与池化

# 初始化第一个卷积层的权值和偏置
W_conv1 = weight_variable([5, 5, 1, 32])  # 5*5的采样窗口，32个卷积核从1个平面抽取特征
b_conv1 = bias_variable([32])  # 每一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，然后应用于relu激活函数
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)  # 进行max-pooling

# 初始化第二个卷积层的权值和偏置
W_conv2 = weight_variable([5, 5, 32, 64])  # 5*5的采样窗口，64个卷积核从32个平面抽取特征
b_conv2 = bias_variable([64])  # 每一个卷积核一个偏置值

# 把h_pool1和权值向量进行卷积，再加上偏置值，然后应用于relu激活函数
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)  # 进行max-pooling

全连接与输出

# 初始化第一个全连接层的权值
W_fc1 = weight_variable([7 * 7 * 64, 1024])  # 上一层有7*7*64个神经元，全连接层有1024个神经元
b_fc1 = bias_variable([1024])  # 1024个节点

# 把池化层2的输出扁平化为1维
h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
# 求第一个全连接层的输出
wx_plus_b1 = tf.matmul(h_pool2_flat, W_fc1) + b_fc1
h_fc1 = tf.nn.relu(wx_plus_b1)

# keep_prob用来表示神经元的输出概率
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

# 初始化第二个全连接层
W_fc2 = weight_variable([1024, 10])  # 10代表有10个分类
b_fc2 = bias_variable([10])

输出与预测

# 计算输出
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

# 交叉熵代价函数
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction))

# 使用AdamOptimizer进行优化
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

# 结果存放在一个布尔列表中
correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))  # argmax返回一维张量中最大的值所在的位置
# 求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

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

sess = tf.Session()
sess.run(tf.global_variables_initializer())
for epoch in range(1):
    for batch in range(n_batch):
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        sess.run(train_step, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 0.7})

    acc = sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels, keep_prob: 1.0})
    print("Iter " + str(epoch) + ", Testing Accuracy= " + str(acc))

variables = [W_conv1, b_conv1, W_conv2, b_conv2, W_fc1, b_fc1, W_fc2, b_fc2]
saver = tf.train.Saver(variables)

path = saver.save(
    sess, os.path.join(os.path.dirname(__file__), "model", "convolution_model"),
    write_state=False, write_meta_graph=False
)
print("模型保存路径：", path)

Next Post

Tensorflow的GPU版本安装
Previous Post

flask发布手写字识别模型

CATALOG

1. 卷积神经网络组成
2. 卷积模型训练



缺失模块。
1、请确保node版本大于6.2
2、在博客根目录（注意不是archer根目录）执行以下命令：
npm i hexo-generator-json-content --save
3、在根目录_config.yml里添加配置：

jsonContent:
  meta: false
  pages: false
  posts:
    title: true
    date: true
    path: true
    text: false
    raw: false
    content: false
    slug: false
    updated: false
    comments: false
    link: false
    permalink: false
    excerpt: false
    categories: true
    tags: true