tf.train.range_input_producer不起作用

时间:2018-03-22 02:18:12

标签: tensorflow

那里,我是tensorflow的新手,当我尝试tf.train.range_input_producer时,它在我的代码中不起作用:

import tensorflow as tf
if __name__ == '__main__':
    with tf.Graph().as_default():
        with tf.Session() as sess:
            queue = tf.train.range_input_producer(tf.Variable(5, tf.int8), num_epochs=1, shuffle=True, seed=None,
                                                  capacity=32)
            # Start input enqueue threads.
            coord = tf.train.Coordinator()
            threads = tf.train.start_queue_runners(sess=sess, coord=coord)
            # Run training steps or whatever
            print('queue size:{}'.format(sess.run(queue.size())))
            coord.request_stop()
            # Terminate as usual.  It is innocuous to request stop twice.
            coord.join(threads)
            sess.close()

我的队列大小为:0

我的代码出了什么问题?提前感谢!

1 个答案:

答案 0 :(得分:0)

您需要在启动队列运行程序之前初始化本地和全局变量。

sess.run([tf.local_variables_initializer(), tf.global_variables_initializer()])