A placeholder has the role of feeding the tensor. The Data to flow inside the tensors are initialized by the Placeholder. To provide a placeholder, we need to use the method feed_dict. The placeholder will be fed only within a session.

Syntax:

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

arguments:

• `dtype`: Type of data
• `shape`: the dimension of the placeholder. Optional. By default, the shape of the data
• `name`: Name of the placeholder. Optional

import tensorflow as tf  
data_placeholder_a = tf.placeholder(tf.float32, name = "data_placeholder_a")  
print(data_placeholder_a)

The output will be Tensor(“data_placeholder_a:0”, dtype=float32)