TensorFlow——模型保存与使用

1、ckpt_save

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

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

x = tf.placeholder(tf.float32, [None, 784], name='input')
y_actual = tf.placeholder(tf.float32, [None, 10])

# 初始化权值W
W = tf.Variable(tf.zeros([784, 10]))
# 初始化偏置项b
b = tf.Variable(tf.zeros([10]))
# 加权变换并进行softmax回归，得到预测概率
y_predict = tf.nn.softmax(tf.matmul(x, W) + b, name='output')

# 求交叉熵
loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=y_actual, logits=y_predict)
# 用梯度下降法使得残差最小
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(loss)

# 在测试阶段，测试准确度计算
correct_prediction = tf.equal(tf.argmax(y_predict, 1), tf.argmax(y_actual, 1))
# 多个批次的准确度均值
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

saver = tf.train.Saver()
with tf.Session() as s