Question

这是我的第一个张量流代码。

如果我分开添加它可以工作，但我相信有一种方法可以在一行中添加N个张量。

import tensorflow as tf

# Create a graph.
g = tf.Graph()

# Establish the graph as the "default" graph.
with g.as_default():
  # Assemble a graph consisting of the following three operations:
  #   * Two tf.constant operations to create the operands.
  #   * One tf.add operation to add the two operands.
  x = tf.constant(8, name="x_const")
  y = tf.constant(5, name="y_const")
  z = tf.constant(4, name="z_const")
  my_sum = tf.add_n(x, y, z, name="z_y_x_sum")

  # Now create a session.
  # The session will run the default graph.
  with tf.Session() as sess:
    print my_sum.eval()

你可以帮我弄清楚是什么问题吗？

Answer 1

您需要将张量放入列表中：

my_sum = tf.add_n([x, y, z], name="z_y_x_sum")

add_n（）最多需要2个参数（给定4个）

1 个答案: