What does a tensorflow "op" do?

Question

Below I have created a tf placeholder named "op testing":

self.center_words = tf.placeholder(tf.int32, shape=[self.batch_size], name='op testing')
print("Extracting the op", self.center_words.op)

When I print that self.center_words.op it prints out a structure like this:

op: "Placeholder"
attr {
  key: "dtype"
  value {
    type: DT_INT32
  }
}
attr {
  key: "shape"
  value {
    shape {
      dim {
        size: 128
      }
    }
  }
}

This works for any TensorFlow variable, function output, etc. What is this .op?

Answer 1

TensorFlow Operations, also known as Ops, are nodes that perform computations on or with Tensor objects. After computation, they return zero or more tensors, which can be used by other Ops later in the graph. To create an Operation, you call its constructor in Python, which takes in whatever Tensor parameters needed for its calculation, known as inputs, as well as any additional information needed to properly create the Op, known as attributes. The Python constructor returns a handle to the Operation’s output (zero or more Tensor objects), and it is this output which can be passed on to other Operations or Session.run