Question

有没有办法在flask（0.12.2）应用程序中使用预先训练好的char-lstm tensorflow和GPU（1.2）模型？

模型在通过shell启动时无缝运行。我使用下面的代码加载它（没有初始化变量，占位符或类似代码）：

....

saver = tf.train.Saver()

with tf.Session() as sess:

    saver.restore(sess, SAVE_PATH)
....

当尝试通过Flask加载相同的预训练模型（包含3个文件：.meta，.index＆amp; .data）时，它会抛出

ValueError：没有要保存的变量

有没有办法让它发挥作用？非常感谢！

Answer 1

我认为这是因为您需要正确初始化和使用变量。

这是我能找到的最简单的例子：

import tensorflow as tf

# Create TensorFlow object called hello_constant
hello_constant = tf.constant('Hello World!')

with tf.Session() as sess:
    # Run the tf.constant operation in the session
    output = sess.run(hello_constant)
    print(output)

对您更有用的更复杂的例子是：

def model_inputs():
    """
    Create TF Placeholders for input, targets, learning rate, and lengths of source and target sequences.
    :return: Tuple (input, targets, learning rate, keep probability, target sequence length,
    max target sequence length, source sequence length)
    """
    input = tf.placeholder(tf.int32,[None,None],name='input')
    target = tf.placeholder(tf.int32,[None,None])
    target_sequence_len = tf.placeholder(tf.int32, [None], name='target_sequence_length')
    max_target_len = tf.reduce_max(target_sequence_len,name='max_target_length' )
    source_sequence_len = tf.placeholder(tf.int32, [None], name='source_sequence_length')
    learning_rate = tf.placeholder(tf.float32)
    keep_prob = tf.placeholder(tf.float32, name='keep_prob')
    return input, target, learning_rate, keep_prob, target_sequence_len, max_target_len, source_sequence_len

以下是如何在会话中使变量可用

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

主题重要，我发现很难在单个StackOverflow回复中有效地总结它。
如果您想深入了解系统的工作原理，我建议您阅读TensorFlow documentation about variables.

具有预训练张量流模型的烧瓶

1 个答案: