Tesorflow占位符依赖于其他占位符

Question

我有一个占位符，它的形状依赖于另一个占位符。如何在占位符初始化期间连接它们？

nUsers = tf.placeholder(tf.float32, [None, 1])
p = tf.placeholder(tf.float32, [None, 10 , ???] )

...in？我需要将批次中该项目的大小放入nUsers中的数字。

Answer 1

你可以很容易地用x.get_shape() (check the difference between tf.shape(x))得到张量的形状。所以你需要这样的东西：

import tensorflow as tf
import numpy as np
nUsers = tf.placeholder(tf.float32, [None, 1])
p = tf.placeholder(tf.float32, [None, 10 , nUsers.get_shape()[0]])

with tf.Session() as sess:
    print sess.run(p, {nUsers: np.ones((2, 1)), p: np.ones((3, 10, 2))})