简单的CNN

最新推荐文章于 2022-08-26 17:24:12 发布

神坑教无心

最新推荐文章于 2022-08-26 17:24:12 发布

阅读量461

点赞数

CC 4.0 BY-SA版权

分类专栏： tensorflow

本文链接：https://blog.youkuaiyun.com/qq_34000894/article/details/80483314

tensorflow 专栏收录该内容

22 篇文章

订阅专栏

本文介绍了一个使用TensorFlow实现的手写数字识别模型。该模型采用卷积神经网络（CNN），通过多轮训练，在MNIST数据集上达到了99.33%的准确率。文章详细展示了模型构建过程，包括权重初始化、卷积层、池化层的设计及训练步骤。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

# -*- coding:utf-8 -*-
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
sess = tf.InteractiveSession()

def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding="SAME")

def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
x_image = tf.reshape(x, [-1, 28, 28, 1])

W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

W_conv2 = weight_variable([5,5,32,64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.global_variables_initializer().run()
for i in range(20000):
    batch = mnist.train.next_batch(50)
    if i % 100 == 0:
        train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_:batch[1], keep_prob:1.0})
        print("step %d, training accuracy %g" %(i, train_accuracy))
    train_step.run(feed_dict={x:batch[0], y_:batch[1], keep_prob:0.5})
for i in range(mnist.test.labels.shape[0]):
    batch = mnist.test.next_batch(50)
    train_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
    mean_value += train_accuracy
print("test accuracy %g" % (mean_value / mnist.test.labels.shape[0]))

test accuracy 0.9933