恢复 TensorFlow 模型但结果不正确

Question

我仍在尝试掌握如何从磁盘恢复已保存的张量流图并通过字典将其馈送到模型。我查看了multiple sources，但无法解决此问题。下面的通用 MLP 代码（第一个 sn-p）将文件保存到磁盘，但是在恢复后（第二个 sn-p），我的准确性返回值 None。任何想法这可能是什么原因？

# Import MINST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
import tensorflow as tf

# Parameters
learning_rate = 0.001
training_epochs = 15
batch_size = 100
display_step = 1

# Network Parameters
n_hidden_1 = 256 # 1st layer number of features
n_hidden_2 = 256 # 2nd layer number of features
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)

with tf.name_scope('placeholders'):
# tf Graph input
    x = tf.placeholder("float", [None, n_input],name='x')
    y = tf.placeholder("float", [None, n_classes],name='y')

with tf.name_scope('Layer-1'):
    NN_weights_1=tf.Variable(tf.random_normal([n_input, n_hidden_1],seed=1),name='NN_weights_1')
    NN_biases_1=tf.Variable(tf.constant(0.0,shape=[n_hidden_1],name='Const'),name='NN_biases_1')
    func=tf.add(tf.matmul(x, NN_weights_1,name='matmul'), NN_biases_1,name='Addition')
    func_2=tf.nn.relu(func)

with tf.name_scope('Layer-2'):
    NN_weights_2=tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2],seed=2),name='NN_weights_2')
    NN_biases_2=tf.Variable(tf.constant(0.0,shape=[n_hidden_2],name='Const'),name='NN_biases_2')
    func_3=tf.add(tf.matmul(func_2, NN_weights_2,name='matmul'), NN_biases_2,name='Addition')
    func_4=tf.nn.relu(func_3)

with tf.name_scope('Output'):
    NN_weights_3=tf.Variable(tf.random_normal([n_hidden_2, n_classes],seed=3),name='NN_weights_3')
    NN_biases_3=tf.Variable(tf.constant(0.0,shape=[n_classes],name='Const'),name='NN_biases_3')
    func_3=tf.add(tf.matmul(func_4, NN_weights_3,name='matmul'), NN_biases_3,name='Addition')
    func_4=tf.nn.sigmoid(func_3)

    # Define loss and optimizer
with tf.name_scope('Operations_'):
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=func_4, labels=y),name='cost')
    optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
    # Test model
    correct_prediction = tf.equal(tf.argmax(func_4, 1), tf.argmax(y, 1),name='correct_prediction')
    # Calculate accuracy
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"),name='accuracy')
    # Initializing the variables
    init = tf.global_variables_initializer()

# Launch the graph
with tf.Session() as sess:
    sess.run(init)
    saver = tf.train.Saver()

    # Training cycle
    for epoch in range(training_epochs):
        avg_cost = 0.
        total_batch = int(mnist.train.num_examples/batch_size)
        # Loop over all batches
        for i in range(total_batch):
            batch_x, batch_y = mnist.train.next_batch(batch_size)
            # Run optimization op (backprop) and cost op (to get loss value)
            _, c = sess.run([optimizer, cost], feed_dict={x: batch_x,
                                                          y: batch_y})
            # Compute average loss
            avg_cost += c / total_batch
        # Display logs per epoch step
        if epoch % display_step == 0:
            print (("Epoch:", '%04d' % (epoch+1), "cost="), \
                "{:.9f}".format(avg_cost))
    print ("Optimization Finished!")
    print ("Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))
    saver.save(sess, 'my_test_model',global_step=1000)

恢复模型并传递字典以确保准确性：

import tensorflow as tf

sess=tf.Session()    
#First let's load meta graph and restore weights
saver = tf.train.import_meta_graph('my_test_model-1000.meta')
saver.restore(sess,"my_test_model-1000")
graph = tf.get_default_graph()
accuracy=graph.get_operation_by_name("Operations_/accuracy")
# Access saved Variables directly
print(sess.run('Layer-1/NN_weights_1:0'))
# This will print 2, which is the value of bias that we saved

print ("Accuracy:", sess.run([accuracy],feed_dict={'placeholders/x:0': mnist.test.images, 'placeholders/y:0': mnist.test.labels}))

Answer 1

改成：

accuracy=graph.get_operation_by_name("Operations_/accuracy").outputs[0]

Tensorflow 会丢弃通过 Session.run 执行的 Operation 对象的输出。详细解释见这里：TensorFlow: eval restored graph