tensorflow下MNIST程序的运行、结果的保存、变量的重载

程序主要包括两部分：

程序的保存

程序变量的重载

第一部分：程序的保存

import tensorflow as tf
import numpy as np
import os
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
train_x, train_y, test_x, test_y = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels

X = tf.placeholder("float", [None, 784])
Y = tf.placeholder("float", [None, 10])

def init_weights(shapes):
    return tf.Variable(tf.random_normal(shapes, stddev=0.01))

def model(X, w_h, w_h2, w_ho, p_keep_input, p_keep_hidden):
    X = tf.nn.dropout(X, p_keep_input)
    h = tf.nn.relu(tf.matmul(X, w_h))

    h = tf.nn.dropout(h, p_keep_hidden)
    h2 = tf.nn.relu(tf.matmul(h, w_h2))

    h2 = tf.nn.dropout(h2, p_keep_hidden)
    return tf.matmul(h2, w_ho)

w_h = init_weights([784, 625])
w_h2 = init_weights([625, 625])
w_ho = init_weights([625, 10])

p_keep_input = tf.placeholder("float")
p_keep_hidden = tf.placeholder("float")
py_x = model(X, w_h, w_h2, w_ho, p_keep_input, p_keep_hidden)


cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y))
train_op = tf.train.RMSPropOptimizer(0.01, 0.9).minimize(cost)
predict_op = tf.argmax(py_x, 1)

ckpt_dir = "./ckpt_dir"
if not os.path.exists(ckpt_dir):
    os.makedirs(ckpt_dir)

global_step = tf.Variable(0, name='global_step', trainable=False)

saver = tf.train.Saver()

with tf.Session() as sess:
    tf.global_variables_initializer().run()

    start = global_step.eval()
    print("start from: ", start)

    for i in range(start, 100):
        for start, end in zip(range(0, len(train_x), 128), range(128, len(train_x)+1, 128)):
            sess.run(train_op, feed_dict={X: train_x[start: end], Y: train_y[start: end], p_keep_input: 0.8,
                                          p_keep_hidden: 0.5})
        global_step.assign(i).eval()
        saver.save(sess, ckpt_dir + "/model.ckpt", global_step=global_step)

第二部分：程序的重载

import tensorflow as tf
import numpy as np
import os
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
train_x, train_y, test_x, test_y = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels

X = tf.placeholder("float", [None, 784])
Y = tf.placeholder("float", [None, 10])

def init_weights(shapes):
    return tf.Variable(tf.random_normal(shapes, stddev=0.01))

def model(X, w_h, w_h2, w_ho, p_keep_input, p_keep_hidden):
    X = tf.nn.dropout(X, p_keep_input)
    h = tf.nn.relu(tf.matmul(X, w_h))

    h = tf.nn.dropout(h, p_keep_hidden)
    h2 = tf.nn.relu(tf.matmul(h, w_h2))

    h2 = tf.nn.dropout(h2, p_keep_hidden)
    return tf.matmul(h2, w_ho)

w_h = init_weights([784, 625])
w_h2 = init_weights([625, 625])
w_ho = init_weights([625, 10])

p_keep_input = tf.placeholder("float")
p_keep_hidden = tf.placeholder("float")
py_x = model(X, w_h, w_h2, w_ho, p_keep_input, p_keep_hidden)


cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y))
train_op = tf.train.RMSPropOptimizer(0.01, 0.9).minimize(cost)
predict_op = tf.argmax(py_x, 1)

ckpt_dir = "./ckpt_dir"
if not os.path.exists(ckpt_dir):
    os.makedirs(ckpt_dir)

global_step = tf.Variable(0, name='global_step', trainable=False)

saver = tf.train.Saver()

with tf.Session() as sess:
    tf.global_variables_initializer().run()
    ckpt = tf.train.get_checkpoint_state(ckpt_dir)
    if ckpt and ckpt.model_checkpoint_path:
        print(ckpt.model_checkpoint_path)
        saver.restore(sess, ckpt.model_checkpoint_path)

    print(sess.run(global_step))
    start = global_step.eval()
    for i in range(start, 100):
        for start, end in zip(range(0, len(train_x), 128), range(128, len(train_x)+1, 128)):
            sess.run(train_op, feed_dict={X: train_x[start: end], Y: train_y[start: end],
                                          p_keep_input: 0.8, p_keep_hidden: 0.5})
        global_step.assign(i).eval()
        print(sess.run(global_step))
        saver.save(sess, ckpt_dir + "/model.ckpt", global_step=global_step)