一篇文章让你秒懂如果用tensorflow保存和加载模型

废话不多说，直接上代码，模型保存的代码如下：

# coding: utf-8
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'


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')


if __name__ == '__main__':
    # 读入数据
    mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
    # x为训练图像的占位符、y_为训练图像标签的占位符
    x = tf.placeholder(tf.float32, [None, 784], name='x')
    y_ = tf.placeholder(tf.float32, [None, 10], name='y_')

    # 将单张图片从784维向量重新还原为28x28的矩阵图片
    x_image = tf.reshape(x, [-1, 28, 28, 1])

    # 第一层卷积层
    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)

    # 第二层卷积层
    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)

    # 全连接层，输出为1024维的向量
    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)
    # 使用Dropout，keep_prob是一个占位符，训练时为0.5，测试时为1
    keep_prob = tf.placeholder(tf.float32, name='keep_prob')
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

    # 把1024维的向量转换成10维，对应10个类别
    W_fc2 = weight_variable([1024, 10])
    b_fc2 = bias_variable([10])
    y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

    # 我们不采用先Softmax再计算交叉熵的方法，而是直接用tf.nn.softmax_cross_entropy_with_logits直接计算
    cross_entropy = tf.reduce_mean(
        tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
    # 同样定义train_step
    train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

    # 定义测试的准确率
    correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name='accuracy')

    # 创建Session和变量初始化
    sess = tf.InteractiveSession()
    sess.run(tf.global_variables_initializer())

    saver = tf.train.Saver(max_to_keep=2)  # 建立保存实例

    # 训练20000步
    for i in range(500):
        batch = mnist.train.next_batch(50)
        train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
        print(i)
    saver.save(sess, 'model', global_step=500)  # 用实例进行模型的保存

新建一个.py文件进行模型的重载进行预测

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

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

with tf.Session() as sess:
    new_saver = tf.train.import_meta_graph('model-500.meta')   # 加载模型图
    new_saver.restore(sess, tf.train.latest_checkpoint("./"))  # 加载模型里面参与计算的变量
    graph = tf.get_default_graph()  # 建立默认图实例对象
    x1 = graph.get_tensor_by_name('x:0')  # 获取结构图变量
    y_1 = graph.get_tensor_by_name('y_:0')
    keep_prob = graph.get_tensor_by_name('keep_prob:0')
    accu = graph.get_tensor_by_name('accuracy:0')
    a = mnist.test.images
    b = mnist.test.labels
    feed_dict = {x1: a, y_1: b, keep_prob: 1.0}
    print(sess.run(accu, feed_dict))  # 赋值计算

来源：CSDN

作者：机器视觉深度学习超人

链接：https://blog.csdn.net/my_name_is_learn/article/details/103850603