TensorFlow基于卷积神经网络的手写数字图像识别代码实现

这是一个基于TensorFlow框架实现的手写数字图像识别代码，使用的是卷积神经网络（CNN）模型。

首先，导入需要的库：

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

然后，定义一些常量和超参数：

learning_rate = 0.001
training_epochs = 15
batch_size = 100

n_classes = 10
dropout = 0.75

# 输入数据的维度
n_input = 784  # 28*28

接着，定义占位符：

x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32)

定义卷积层和池化层函数：

def conv2d(x, W, b, strides=1):
    x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')
    x = tf.nn.bias_add(x, b)
    return tf.nn.relu(x)

def maxpool2d(x, k=2):
    return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME')

接下来，定义卷积神经网络模型：

def conv_net(x, weights, biases, dropout):
    x = tf.reshape(x, shape=[-1, 28, 28, 1])

    # 第一层卷积层
    conv1 = conv2d(x, weights['wc1'], biases['bc1'])
    conv1 = maxpool2d(conv1, k=2)

    # 第二层卷积层
    conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
    conv2 = maxpool2d(conv2, k=2)

    # 全连接层
    fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])
    fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
    fc1 = tf.nn.relu(fc1)
    fc1 = tf.nn.dropout(fc1, dropout)

    # 输出层
    out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
    return out

然后，初始化权重和偏置：

weights = {
    'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),
    'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),
    'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])),
    'out': tf.Variable(tf.random_normal([1024, n_classes]))
}

biases = {
    'bc1': tf.Variable(tf.random_normal([32])),
    'bc2': tf.Variable(tf.random_normal([64])),
    'bd1': tf.Variable(tf.random_normal([1024])),
    'out': tf.Variable(tf.random_normal([n_classes]))
}

接着，定义损失函数和优化器：

pred = conv_net(x, weights, biases, keep_prob)

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)

定义评估模型的准确率函数：

correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

最后，训练模型：

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

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    # 训练循环
    for epoch in range(training_epochs):
        avg_cost = 0.
        total_batch = int(mnist.train.num_examples/batch_size)

        # 遍历所有批次（batch）
        for i in range(total_batch):
            batch_x, batch_y = mnist.train.next_batch(batch_size)

            # 运行优化器
            sess.run(optimizer, feed_dict={x: batch_x, y: batch_y, keep_prob: dropout})

            # 计算损失值
            avg_cost += sess.run(cost, feed_dict={x: batch_x, y: batch_y, keep_prob: 1.}) / total_batch

        # 显示每一轮训练的结果
        if epoch % 1 == 0:
            print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost))

    # 计算测试数据的准确率
    print("Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels, keep_prob: 1.}))

这样，一个基于TensorFlow框架实现的手写数字图像识别代码就完成了。