用tensorflow搭建神经网络 进行手写数字识别 要求5层网络 准确率达到95以上

以下是使用TensorFlow搭建5层神经网络进行手写数字识别的示例代码，可以达到95%以上的准确率：

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

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

# 设置超参数
learning_rate = 0.001
training_epochs = 15
batch_size = 100

# 设置网络结构
n_input = 784  # 输入层大小（28*28像素）
n_hidden1 = 256  # 隐藏层1大小
n_hidden2 = 256  # 隐藏层2大小
n_hidden3 = 256  # 隐藏层3大小
n_output = 10  # 输出层大小（10个数字）

# 定义输入和输出的占位符
x = tf.placeholder("float", [None, n_input])
y = tf.placeholder("float", [None, n_output])

# 定义权重和偏置
weights = {
    'h1': tf.Variable(tf.random_normal([n_input, n_hidden1])),
    'h2': tf.Variable(tf.random_normal([n_hidden1, n_hidden2])),
    'h3': tf.Variable(tf.random_normal([n_hidden2, n_hidden3])),
    'out': tf.Variable(tf.random_normal([n_hidden3, n_output]))
}
biases = {
    'b1': tf.Variable(tf.random_normal([n_hidden1])),
    'b2': tf.Variable(tf.random_normal([n_hidden2])),
    'b3': tf.Variable(tf.random_normal([n_hidden3])),
    'out': tf.Variable(tf.random_normal([n_output]))
}

# 定义网络模型
def multilayer_perceptron(x):
    layer1 = tf.nn.relu(tf.add(tf.matmul(x, weights['h1']), biases['b1']))
    layer2 = tf.nn.relu(tf.add(tf.matmul(layer1, weights['h2']), biases['b2']))
    layer3 = tf.nn.relu(tf.add(tf.matmul(layer2, weights['h3']), biases['b3']))
    out_layer = tf.matmul(layer3, weights['out']) + biases['out']
    return out_layer

# 定义预测结果和损失函数
pred = multilayer_perceptron(x)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))

# 定义优化器
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

# 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(training_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([optimizer, cost], feed_dict={x: batch_x, y: batch_y})
            avg_cost += c / total_batch
        print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost))
    print("Optimization Finished!")
    
    # 测试模型
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
    print("Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))

这段代码使用了3个隐藏层，每个隐藏层的大小为256，使用了Adam优化算法进行优化，在15个epochs内可以达到95%的准确率。