本文共计369个文字，预计阅读时间需要2分钟。

`tf.placeholder(dtype, shape=None, name=None) 添加一个用于输入张量的占位符。注意：此张量如果被评估将引发错误。其值必须通过 feed_dict 可选参数提供。`

tf.placeholder

tf.placeholder(
dtype,
shape=None,
name=None
)

Inserts a placeholder for a tensor that will be always fed.

Important: This tensor will produce an error if evaluated. Its value must be fed using thefeed_dictoptional argument toSession.run(),Tensor.eval(), orOperation.run().

在构建graph的过程中，tensor是没有实际数据的，只是表达计算过程，那么通过placeholder函数对tensor变量进行占位表示。然后在Session执行过程中，通过feed_dict对占位的tensor进行feed值

Args:

• dtype: The type of elements in the tensor to be fed.指定数据类型
• shape: The shape of the tensor to be fed (optional). If the shape is not specified, you can feed a tensor of any shape.指定tensor的维度,如果没有指定，可以feed任意维度的tensor
• name: A name for the operation (optional).

Returns:

ATensorthat may be used as a handle for feeding a value, but not evaluated directly.

Raises:

• RuntimeError: if eager execution is enabled

1 import tensorflow as tf 2 import numpy as np 3 4 5 x = tf.placeholder(tf.float32, shape=(1024, 1024)) 6 y = tf.matmul(x, x) 7 8 with tf.Session() as sess: 9 #print(sess.run(y)) # ERROR: will fail because x was not fed. 10 rand_array = np.random.rand(1024, 1024) 11 print(sess.run(y, feed_dict={x: rand_array})) # Will succeed.