恢复并评估Tensorflow模型

Question

我已经在培训期间保存了这个模型，但是我很难加载和评估它。在

我尝试了一些不同的方法，但我无法加载保存的模型并对其进行评估，以获得对某个测试样本（图像文件）的预测。在

有人能帮忙吗？正如我所看到的，这似乎不是那么难，但我想念任何能把它做好的事情。在

#!/usr/bin/python
import tensorflow as tf

BATCH_SIZE = 128
NUM_EXAMPLES_PER_EPOCH = 50000
VALIDATION_SIZE = 10000
WIDTH = 128
HEIGHT = 64
CHANNELS = 3
CLASSES = 10
NUMBERS = 4


def inference(inputs):

    with tf.variable_scope("conv_pool_1"):
        kernel = tf.get_variable(name="kernel",
                                 shape=[5, 5, 3, 48],
                                 initializer=tf.truncated_normal_initializer(stddev=0.05),
                                 dtype=tf.float32)
        biases = tf.get_variable(name="biases",
                                 shape=[48],
                                 initializer=tf.constant_initializer(value=0.),
                                 dtype=tf.float32)
        conv = tf.nn.conv2d(input=inputs,
                            filter=kernel,
                            strides=[1, 1, 1, 1],
                            padding="SAME")
        conv_bias = tf.nn.bias_add(value=conv,
                                   bias=biases,
                                   name="add_biases")
        relu = tf.nn.relu(conv_bias)
        pool = tf.nn.max_pool(value=relu,
                              ksize=[1, 2, 2, 1],
                              strides=[1, 2, 2, 1],
                              padding="SAME",
                              name="pooling")

    with tf.variable_scope("conv_pool_2"):
        kernel = tf.get_variable(name="kernel",
                                 shape=[5, 5, 48, 64],
                                 initializer=tf.truncated_normal_initializer(stddev=0.05),
                                 dtype=tf.float32)
        biases = tf.get_variable(name="biases",
                                 shape=[64],
                                 initializer=tf.constant_initializer(value=0.),
                                 dtype=tf.float32)
        conv = tf.nn.conv2d(input=pool,
                            filter=kernel,
                            strides=[1, 1, 1, 1],
                            padding="SAME")
        conv_bias = tf.nn.bias_add(value=conv,
                                   bias=biases,
                                   name="add_biases")
        relu = tf.nn.relu(conv_bias)
        pool = tf.nn.max_pool(value=relu,
                              ksize=[1, 2, 1, 1],
                              strides=[1, 2, 1, 1],
                              padding="SAME",
                              name="pooling")
    with tf.variable_scope("conv_pool_3"):
        kernel = tf.get_variable(name="kernel",
                                 shape=[5, 5, 64, 128],
                                 initializer=tf.truncated_normal_initializer(stddev=0.05),
                                 dtype=tf.float32)
        biases = tf.get_variable(name="biases",
                                 shape=[128],
                                 initializer=tf.constant_initializer(value=0.),
                                 dtype=tf.float32)
        conv = tf.nn.conv2d(input=pool,
                            filter=kernel,
                            strides=[1, 1, 1, 1],
                            padding="SAME")
        conv_bias = tf.nn.bias_add(value=conv,
                                   bias=biases,
                                   name="add_biases")
        relu = tf.nn.relu(conv_bias)
        pool = tf.nn.max_pool(value=relu,
                              ksize=[1, 2, 2, 1],
                              strides=[1, 2, 2, 1],
                              padding="SAME",
                              name="pooling")
    reshape = tf.reshape(pool,
                         shape=[BATCH_SIZE, -1],
                         name="reshape")
    dims = reshape.get_shape().as_list()[-1]
    with tf.variable_scope("fully_conn"):
        weights = tf.get_variable(name="weights",
                                  shape=[dims, 2048],
                                  initializer=tf.truncated_normal_initializer(stddev=0.05),
                                  dtype=tf.float32)
        biases = tf.get_variable(name="biases",
                                 shape=[2048],
                                 initializer=tf.constant_initializer(value=0.),
                                 dtype=tf.float32)
        output = tf.nn.xw_plus_b(x=reshape,
                                 weights=weights,
                                 biases=biases)
        conn = tf.nn.relu(output)
    with tf.variable_scope("output"):
        weights = tf.get_variable(name="weights",
                                  shape=[2048, NUMBERS * CLASSES],
                                  initializer=tf.truncated_normal_initializer(stddev=0.05),
                                  dtype=tf.float32)
        biases = tf.get_variable(name="biases",
                                 shape=[NUMBERS * CLASSES],
                                 initializer=tf.constant_initializer(value=0.),
                                 dtype=tf.float32)
        logits = tf.nn.xw_plus_b(x=conn,
                                 weights=weights,
                                 biases=biases)
        reshape = tf.reshape(logits, shape=[BATCH_SIZE, NUMBERS, CLASSES])
    return reshape


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


def evaluation(logits, labels):
    prediction = tf.argmax(logits, 2)
    actual = tf.argmax(labels, 2)
    equal = tf.equal(prediction, actual)
    # equal = tf.reduce_all(equal, 1)
    accuracy = tf.reduce_mean(tf.cast(equal, tf.float32), name="accuracy")
    return accuracy


def train(loss, learning_rate=0.00001):
    optimizer = tf.train.GradientDescentOptimizer(learning_rate)
    train_op = optimizer.minimize(loss)
    return train_op

Answer 1

现在我正在正确加载

saver = tf.train.import_meta_graph('model/model.ckpt.meta')

init = tf.group(tf.initialize_all_variables(),
                tf.initialize_local_variables())
sess = tf.Session(config=tf.ConfigProto(allow_soft_placement=True))

saver.restore(sess, 'model/model.ckpt')

现在我试着得到预测，我想大概是这样的，但是我不知道如何从我之前创建的模型中获取变量，以便得到它的预测：

^{pr2}$

Answer 2

你怎么保存的？您是否尝试过： （用于保存）

saver = tf.train.Saver()
sess = tf.Session()
sess.run(tf.global_variables_initializer())
saver.save(sess, 'my-model')

（用于装载）

^{pr2}$

它的官方引用：https://www.tensorflow.org/versions/master/api_docs/python/state_ops/exporting_and_importing_meta_graphs（或者在URL中用r0.12代替master的发行号）。在