dnn手写数字识别代码

以下是基于Python和TensorFlow的手写数字识别的DNN代码实现：

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

# 导入MNIST数据集
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

# 定义超参数
learning_rate = 0.1
num_epochs = 50
batch_size = 128
display_step = 1

# 定义输入输出占位符
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])

# 定义网络参数
n_hidden_1 = 256
n_hidden_2 = 256
n_input = 784
n_classes = 10

# 定义隐藏层和输出层的权重和偏置项
weights = {
    'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
    'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
    'out': tf.Variable(tf.random_normal([n_hidden_2, n_classes]))
}

biases = {
    'b1': tf.Variable(tf.random_normal([n_hidden_1])),
    'b2': tf.Variable(tf.random_normal([n_hidden_2])),
    'out': tf.Variable(tf.random_normal([n_classes]))
}

# 定义DNN模型
def neural_net(x):
    layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
    layer_1 = tf.nn.relu(layer_1)
    layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
    layer_2 = tf.nn.relu(layer_2)
    out_layer = tf.matmul(layer_2, weights['out']) + biases['out']
    return out_layer

# 定义损失函数和优化器
logits = neural_net(x)
loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
train_op = optimizer.minimize(loss_op)

# 定义模型评估函数
correct_pred = tf.equal(tf.argmax(logits, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

# 初始化变量
init = tf.global_variables_initializer()

# 训练模型
with tf.Session() as sess:
    sess.run(init)

    for epoch in range(num_epochs):
        avg_cost = 0.
        total_batch = int(mnist.train.num_examples / batch_size)

        for i in range(total_batch):
            batch_x, batch_y = mnist.train.next_batch(batch_size)

            _, c = sess.run([train_op, loss_op], feed_dict={x: batch_x, y: batch_y})

            avg_cost += c / total_batch

        if epoch % display_step == 0:
            print("Epoch:", '%04d' % (epoch+1), "cost={:.9f}".format(avg_cost))

    print("Optimization Finished!")

    # 计算测试集的准确率
    print("Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))

在上述代码中，我们首先导入MNIST数据集，然后定义了超参数和输入输出占位符。接着定义了隐藏层和输出层的权重和偏置项，并且定义了DNN模型和损失函数。最后，我们使用Adam优化器训练模型，并且计算测试集的准确率。