tensorflow:保存與讀取網絡結構,參數

訓練一個神經網絡的目的是啥？不就是有朝一日讓它有用武之地嗎？可是，在別處使用訓練好的網絡，得先把網絡的參數（就是那些variables）保存下來，怎么保存呢？其實，tensorflow已經給我們提供了很方便的API，來幫助我們實現訓練參數的存儲與讀取，如果想了解詳情，請看晦澀難懂的官方API，接下來我簡單介紹一下我的理解。

保存與讀取數據全靠下面這個類實現：

class tf.train.Saver

當我們需要存儲數據時，下面2條指令就夠了

saver = tf.train.Saver()
save_path = saver.save(sess, model_path)

解釋一下，首先創建一個saver類，然后調用saver的save方法（函數），save需要傳遞兩個參數，一個是你的訓練session，另一個是文件存儲路徑，例如“/tmp/superNet.ckpt”，這個存儲路徑是可以包含文件名的。save方法會返回一個存儲路徑。當然，save方法還有別的參數可以傳遞，這里不再介紹。
然后怎么讀取數據呢？看下面

saver = tf.train.Saver()
load_path = saver.restore(sess, model_path)

和存儲數據神似啊！不再贅述。

下面是重點！關於tf.train.Saver()使用的幾點小心得！

• 1、save方法在實現數據讀取時，它僅僅讀數據，關鍵是得有一些提前聲明好的variables來接受這些數據，因此，當save讀取數據到sess時，需要提前聲明與數據匹配的variables，否則程序就報錯了。
• 2、save讀取的數據不需要initialize。
• 3、目前想到的就這么多，隨時補充。

為了對數據存儲和讀取有更直觀的認識，我自己寫了兩個實驗小程序，下面是第一個，訓練網絡並存儲數據，用的MNIST數據集

import tensorflow as tf
import sys

# load MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('data', one_hot=True)

# 一些 hyper parameters
activation = tf.nn.relu
batch_size = 100
iteration = 20000
hidden1_units = 30
# 注意！這里是存儲路徑！
model_path = sys.path[0] + '/simple_mnist.ckpt'

X = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])

W_fc1 = tf.Variable(tf.truncated_normal([784, hidden1_units], stddev=0.2))
b_fc1 = tf.Variable(tf.zeros([hidden1_units]))
W_fc2 = tf.Variable(tf.truncated_normal([hidden1_units, 10], stddev=0.2))
b_fc2 = tf.Variable(tf.zeros([10]))

def inference(img):
    fc1 = activation(tf.nn.bias_add(tf.matmul(img, W_fc1), b_fc1))
    logits = tf.nn.bias_add(tf.matmul(fc1, W_fc2), b_fc2)
    return logits

def loss(logits, labels):
    cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits, labels)
    loss = tf.reduce_mean(cross_entropy)
    return loss

def evaluation(logits, labels):
    correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(labels, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    return accuracy

logits = inference(X)
loss = loss(logits, y_)
train_op = tf.train.AdamOptimizer(1e-4).minimize(loss)
accuracy = evaluation(logits, y_)

# 先實例化一個Saver()類
saver = tf.train.Saver()
init = tf.initialize_all_variables()

with tf.Session() as sess:
    sess.run(init)
    for i in xrange(iteration):
        batch = mnist.train.next_batch(batch_size)
        if i%1000 == 0 and i:
            train_accuracy = sess.run(accuracy, feed_dict={X: batch[0], y_: batch[1]})
            print "step %d, train accuracy %g" %(i, train_accuracy)
        sess.run(train_op, feed_dict={X: batch[0], y_: batch[1]})
    print '[+] Test accuracy is %f' % sess.run(accuracy, feed_dict={X: mnist.test.images, y_: mnist.test.labels})
    # 存儲訓練好的variables
    save_path = saver.save(sess, model_path)
    print "[+] Model saved in file: %s" % save_path

接下來是讀取數據並做測試！

import tensorflow as tf
import sys

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('data', one_hot=True)

activation = tf.nn.relu
hidden1_units = 30
model_path = sys.path[0] + '/simple_mnist.ckpt'

X = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])

W_fc1 = tf.Variable(tf.truncated_normal([784, hidden1_units], stddev=0.2))
b_fc1 = tf.Variable(tf.zeros([hidden1_units]))
W_fc2 = tf.Variable(tf.truncated_normal([hidden1_units, 10], stddev=0.2))
b_fc2 = tf.Variable(tf.zeros([10]))

def inference(img):
    fc1 = activation(tf.nn.bias_add(tf.matmul(img, W_fc1), b_fc1))
    logits = tf.nn.bias_add(tf.matmul(fc1, W_fc2), b_fc2)
    return logits

def evaluation(logits, labels):
    correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(labels, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    return accuracy

logits = inference(X)
accuracy = evaluation(logits, y_)

saver = tf.train.Saver()

with tf.Session() as sess:
    # 讀取之前訓練好的數據
    load_path = saver.restore(sess, model_path)
    print "[+] Model restored from %s" % load_path
    print '[+] Test accuracy is %f' % sess.run(accuracy, feed_dict={X: mnist.test.images, y_: mnist.test.labels})

 

 

 

轉：https://www.jianshu.com/p/83fa3aa2d0e9