Tensorflow模型的保存和加载

最新推荐文章于 2023-01-07 14:27:58 发布

魇餍

最新推荐文章于 2023-01-07 14:27:58 发布

阅读量235

点赞数

CC 4.0 BY-SA版权

分类专栏： tensorflow

本文链接：https://blog.youkuaiyun.com/Chang_Shuang/article/details/79416060

tensorflow 专栏收录该内容

22 篇文章

订阅专栏

本文介绍使用TensorFlow实现MNIST手写数字识别的简单神经网络，并演示如何保存及加载已训练的模型。通过实例展示了模型训练过程及准确率评估。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

模型的保存

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

# 载入数据集
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
# 每个批次的大小
batch_size = 100
# 计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size

# 定义两个placeholder
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])

# 创建一个简单的神经网络
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([1, 10]))
prediction = tf.nn.softmax(tf.matmul(x, W) + b)

# 定义二次代价函数
loss = tf.reduce_mean(tf.square(y - prediction))
# 交叉熵
# loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels= y, logits= prediction))
# 定义梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)

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

# 结果存储在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(prediction, 1))
# 求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(21):
        for batch in range(n_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            sess.run(train_step, feed_dict={x: batch_xs, y: batch_ys})

        acc = sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels})
        print("Iter" + str(epoch) + ", Testing Accuracy" + str(acc))

    # 保存训练好的网络模型
    saver = tf.train.Saver()
    saver.save(sess, 'net/my_net.ckpt')

模型的加载

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

# 载入数据集
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
# 每个批次的大小
batch_size = 100
# 计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size

# 定义两个placeholder
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])

# 创建一个简单的神经网络
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([1, 10]))
prediction = tf.nn.softmax(tf.matmul(x, W) + b)

# 定义二次代价函数
loss = tf.reduce_mean(tf.square(y - prediction))
# 交叉熵
# loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels= y, logits= prediction))
# 定义梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)

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

# 结果存储在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(prediction, 1))
# 求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

with tf.Session() as sess:
    sess.run(init)
    print(sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels}))

    saver = tf.train.Saver()
    saver.restore(sess, 'net/my_net.ckpt')
    print(sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels}))