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

定义--简单一句话“接收数据集”

tf.placeholder(dtype, shape=None, name=None)
用于得到传递进来的真实的训练样本；
不必指定初始值，可在运行时，通过 Session.run 的函数的 feed_dict 参数指定；
这也是其命名的原因所在，仅仅作为一种占位符；

例子

x = tf.placeholder(float, shape=(1024, 1024))
y = tf.matmul(x, x)

with tf.Session() as sess:
  print sess.run(y)  # ERROR: will fail because x was not fed.

  rand_array = np.random.rand(1024, 1024)
  print sess.run(y, feed_dict={x: rand_array})  # Will succeed.

参数

• dtype: 元素类型.
• shape: The shape of the tensor to be fed (optional). If the shape is not specified, you can feed a tensor of any shape.
• name: A name for the operation (optional).

返回

A Tensor that may be used as a handle for feeding a value, but not evaluated directly.