8-CNN模型的保存和重载

import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
import input_data

mnist = input_data.read_data_sets('./data/MNIST/', one_hot=True)
trainimg   = mnist.train.images
trainlabel = mnist.train.labels
testimg    = mnist.test.images
testlabel  = mnist.test.labels

n_input = 784
n_output = 10
stddev = 0.1
# [3,3,1,64]表示[h, w, c, depth]
weights = {
    'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64], stddev=stddev)),
    'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128], stddev=stddev)),
    'wd1': tf.Variable(tf.random_normal([7 * 7 * 128, 1024], stddev=stddev)),
    #7 = 28 / 2 / 2，经过两次pooling压缩
    'wd2': tf.Variable(tf.random_normal([1024, n_output], stddev=stddev))
}
biases = {
    'bc1': tf.Variable(tf.random_normal([64], stddev=stddev)),
    'bc2': tf.Variable(tf.random_normal([128], stddev=stddev)),
    'bd1': tf.Variable(tf.random_normal([1024], stddev=stddev)),
    'bd2': tf.Variable(tf.random_normal([n_output], stddev=stddev))
}

def conv_basic(_input, _w, _b, _keepratio):
        # INPUT
        _input_r = tf.reshape(_input, shape=[-1, 28, 28, 1])
        # CONV LAYER 1
        _conv1 = tf.nn.conv2d(_input_r, _w['wc1'], strides=[1, 1, 1, 1], padding='SAME')
        #_mean, _var = tf.nn.moments(_conv1, [0, 1, 2])
        #_conv1 = tf.nn.batch_normalization(_conv1, _mean, _var, 0, 1, 0.0001)
        _conv1 = tf.nn.relu(tf.nn.bias_add(_conv1, _b['bc1']))
        _pool1 = tf.nn.max_pool(_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
        _pool_dr1 = tf.nn.dropout(_pool1, _keepratio)
        # CONV LAYER 2
        _conv2 = tf.nn.conv2d(_pool_dr1, _w['wc2'], strides=[1, 1, 1, 1], padding='SAME')
        #_mean, _var = tf.nn.moments(_conv2, [0, 1, 2])
        #_conv2 = tf.nn.batch_normalization(_conv2, _mean, _var, 0, 1, 0.0001)
        _conv2 = tf.nn.relu(tf.nn.bias_add(_conv2, _b['bc2']))
        _pool2 = tf.nn.max_pool(_conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
        _pool_dr2 = tf.nn.dropout(_pool2, _keepratio)
        # VECTORIZE
        _dense1 = tf.reshape(_pool_dr2, [-1, _w['wd1'].get_shape().as_list()[0]])
        # FULLY CONNECTED LAYER 1
        _fc1 = tf.nn.relu(tf.add(tf.matmul(_dense1, _w['wd1']), _b['bd1']))
        _fc_dr1 = tf.nn.dropout(_fc1, _keepratio)
        # FULLY CONNECTED LAYER 2
        _out = tf.add(tf.matmul(_fc_dr1, _w['wd2']), _b['bd2'])
        # RETURN
        out = { 'input_r': _input_r, 'conv1': _conv1, 'pool1': _pool1, 'pool1_dr1': _pool_dr1,
            'conv2': _conv2, 'pool2': _pool2, 'pool_dr2': _pool_dr2, 'dense1': _dense1,
            'fc1': _fc1, 'fc_dr1': _fc_dr1, 'out': _out
        }
        return out

x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_output])
keepratio = tf.placeholder(tf.float32)

# FUNCTIONS

_pred = conv_basic(x, weights, biases, keepratio)['out']
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=_pred, labels=y))
optm = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
_corr = tf.equal(tf.argmax(_pred,1), tf.argmax(y,1)) 
accr = tf.reduce_mean(tf.cast(_corr, tf.float32)) 
init = tf.global_variables_initializer()

SAVER

save_step = 1   #保存步长
saver = tf.train.Saver(max_to_keep=3) #最多保存的数据个数

设置标志位do_train

• 1表示训练
• 0表示测试

do_train = 1
sess = tf.Session()
sess.run(init)

training_epochs = 15
batch_size      = 16
display_step    = 1
if do_train == 1:
    for epoch in range(training_epochs):
        avg_cost = 0.
        #total_batch = int(mnist.train.num_examples/batch_size)
        total_batch = 10
        # Loop over all batches
        for i in range(total_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            # Fit training using batch data
            sess.run(optm, feed_dict={x: batch_xs, y: batch_ys, keepratio:0.7})
            # Compute average loss
            avg_cost += sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keepratio:1.})/total_batch

        # Display logs per epoch step
        if epoch % display_step == 0: 
            print ("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost))
            train_acc = sess.run(accr, feed_dict={x: batch_xs, y: batch_ys, keepratio:1.})
            print (" Training accuracy: %.3f" % (train_acc))
            #test_acc = sess.run(accr, feed_dict={x: testimg, y: testlabel, keepratio:1.})
            #print (" Test accuracy: %.3f" % (test_acc))
            
        # Save Net
        if epoch % save_step == 0:
            saver.save(sess, "save/CNNnets/cnn_mnist_basic.ckpt-" + str(epoch))

    print ("OPTIMIZATION FINISHED")

Epoch: 000/015 cost: 5.006800950
 Training accuracy: 0.438
Epoch: 001/015 cost: 1.933123469
 Training accuracy: 0.562
Epoch: 002/015 cost: 1.148783058
 Training accuracy: 0.625
Epoch: 003/015 cost: 1.174695367
 Training accuracy: 0.688
WARNING:tensorflow:From C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py:966: remove_checkpoint (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to delete files with this prefix.
Epoch: 004/015 cost: 0.984622568
 Training accuracy: 0.625
Epoch: 005/015 cost: 1.013936806
 Training accuracy: 0.562
Epoch: 006/015 cost: 0.942555690
 Training accuracy: 0.750
Epoch: 007/015 cost: 0.737268138
 Training accuracy: 0.688
Epoch: 008/015 cost: 0.723523247
 Training accuracy: 0.688
Epoch: 009/015 cost: 0.599508539
 Training accuracy: 0.812
Epoch: 010/015 cost: 0.467553186
 Training accuracy: 1.000
Epoch: 011/015 cost: 0.608258069
 Training accuracy: 0.812
Epoch: 012/015 cost: 0.464240515
 Training accuracy: 0.812
Epoch: 013/015 cost: 0.504054409
 Training accuracy: 0.812
Epoch: 014/015 cost: 0.488834512
 Training accuracy: 1.000
OPTIMIZATION FINISHED

init = tf.global_variables_initializer()
do_train = 0
sess = tf.Session()
sess.run(init)

if do_train == 0:
    epoch = training_epochs-1
    saver.restore(sess, "save/CNNnets/cnn_mnist_basic.ckpt-" + str(epoch))
    
    test_acc = sess.run(accr, feed_dict={x: testimg, y: testlabel, keepratio:1.})
    print (" TEST ACCURACY: %.3f" % (test_acc))

WARNING:tensorflow:From C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py:1266: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
INFO:tensorflow:Restoring parameters from save/CNNnets/cnn_mnist_basic.ckpt-14



---------------------------------------------------------------------------

ResourceExhaustedError                    Traceback (most recent call last)