基于卷积神经网络的手写文字识别代码
时间: 2024-05-18 14:09:12 浏览: 8
基于卷积神经网络的手写文字识别是一个常见的机器学习应用,以下是一份基于Python和TensorFlow的手写数字识别代码,供您参考:
```python
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)
# 定义输入数据的placeholder
x = tf.placeholder(tf.float32, [None, 784])
# 定义卷积层1的权重和偏置
W_conv1 = tf.Variable(tf.truncated_normal([5, 5, 1, 32], stddev=0.1))
b_conv1 = tf.Variable(tf.constant(0.1, shape=[32]))
# 将输入数据reshape成4维张量
x_image = tf.reshape(x, [-1,28,28,1])
# 定义卷积层1和池化层1
h_conv1 = tf.nn.relu(tf.nn.conv2d(x_image, W_conv1, strides=[1, 1, 1, 1], padding='SAME') + b_conv1)
h_pool1 = tf.nn.max_pool(h_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
# 定义卷积层2的权重和偏置
W_conv2 = tf.Variable(tf.truncated_normal([5, 5, 32, 64], stddev=0.1))
b_conv2 = tf.Variable(tf.constant(0.1, shape=[64]))
# 定义卷积层2和池化层2
h_conv2 = tf.nn.relu(tf.nn.conv2d(h_pool1, W_conv2, strides=[1, 1, 1, 1], padding='SAME') + b_conv2)
h_pool2 = tf.nn.max_pool(h_conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
# 将卷积层2的输出reshape成一维向量
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
# 定义全连接层的权重和偏置
W_fc1 = tf.Variable(tf.truncated_normal([7 * 7 * 64, 1024], stddev=0.1))
b_fc1 = tf.Variable(tf.constant(0.1, shape=[1024]))
# 定义全连接层
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# 定义dropout,防止过拟合
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# 定义输出层的权重和偏置
W_fc2 = tf.Variable(tf.truncated_normal([1024, 10], stddev=0.1))
b_fc2 = tf.Variable(tf.constant(0.1, shape=[10]))
# 定义输出层
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
# 定义损失函数和优化器
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
# 定义评估模型的准确率
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# 开始训练模型
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(20000):
batch = mnist.train.next_batch(50)
if i % 100 == 0:
train_accuracy = accuracy.eval(feed_dict={x:batch, y_: batch[1], keep_prob: 1.0})
print("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict={x: batch, y_: batch, keep_prob: 0.5})
print("test accuracy %g"%accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
```